Academic literature on the topic 'Deep learning for Multimedia Forensics'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the lists of relevant articles, books, theses, conference reports, and other scholarly sources on the topic 'Deep learning for Multimedia Forensics.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Journal articles on the topic "Deep learning for Multimedia Forensics"
1
Amerini, Irene, Aris Anagnostopoulos, Luca Maiano, and Lorenzo Ricciardi Celsi. "Deep Learning for Multimedia Forensics." Foundations and Trends® in Computer Graphics and Vision 12, no. 4 (2021): 309–457. http://dx.doi.org/10.1561/0600000096.
Full text
2
.., Ossama, and Mhmed Algrnaodi. "Deep Learning Fusion for Attack Detection in Internet of Things Communications." Fusion: Practice and Applications 9, no. 2 (2022): 27–47. http://dx.doi.org/10.54216/fpa.090203.
Full textAbstract:
The increasing deep learning techniques used in multimedia and networkIoT solve many problems and increase performance. Securing the deep learning models, multimedia, and networkIoT has become a major area of research in the past few years which is considered to be a challenge during generative adversarial attacks over the multimedia or networkIoT. Many efforts and studies try to provide intelligent forensics techniques to solve security issues. This paper introduces a holistic organization of intelligent multimedia forensics that involve deep learning fusion, multimedia, and networkIoT forensics to attack detection. We highlight the importance of using deep learning fusion techniques to obtain intelligent forensics and security over multimedia or NetworkIoT. Finally, we discuss the key challenges and future directions in the area of intelligent multimedia forensics using deep learning fusion techniques.
3
Celebi, Naciye Hafsa, Tze-Li Hsu, and Qingzhong Liu. "A comparison study to detect seam carving forgery in JPEG images with deep learning models." Journal of Surveillance, Security and Safety 3, no. 3 (2022): 88–100. http://dx.doi.org/10.20517/jsss.2022.02.
Full textAbstract:
Aim: Although deep learning has been applied in image forgery detection, to our knowledge, it still falls short of a comprehensive comparison study in detecting seam-carving images in multimedia forensics by comparing the popular deep learning models, which is addressed in this study. Methods: To investigate the performance in detecting seam-carving-based image forgery with popular deep learning models that were used in image forensics, we compared nine different deep learning models in detecting untouched JPEG images, seam-insertion images, and seam removal images (three-class classification), and in distinguishing modified seam-carving images from untouched JPEG images (binary classification). We also investigate the different learning algorithms with the Efficientnet-B5 in adjusting the learning rate with three popular optimizers in deep learning. Results: Our study shows that EfficientNet performs the best among the nine different deep learning frameworks, followed by SRnet, and LFnet. Different algorithms for adjusting the learning rate result in different detection testing accuracy with Efficientnet-B5. In our experiments, decouples the optimal choice of weight decay factor from the setting of the learning rate (AdamW) is generally superior to Adaptive Moment Estimation (Adam) and Stochastic Gradient Descent (SGD). Our study also indicates that deep learning is very promising for image forensics, such as the detection of image forgery. Conclusion: Deep learning is very promising in image forensics that is hardly discernable to human perceptions, but the performance varies over different learning models and frameworks. In addition to the models, the optimizer has a considerable impact on the final detection performance. We would recommend EfficientNet, LFnet and SRnet for seam-carving detection.
4
Hussain, Israr, Dostdar Hussain, Rashi Kohli, Muhammad Ismail, Saddam Hussain, Syed Sajid Ullah, Roobaea Alroobaea, Wajid Ali, and Fazlullah Umar. "Evaluation of Deep Learning and Conventional Approaches for Image Recaptured Detection in Multimedia Forensics." Mobile Information Systems 2022 (June 15, 2022): 1–10. http://dx.doi.org/10.1155/2022/2847580.
Full textAbstract:
Image recaptured from a high-resolution LED screen or a good quality printer is difficult to distinguish from its original counterpart. The forensic community paid less attention to this type of forgery than to other image alterations such as splicing, copy-move, removal, or image retouching. It is significant to develop secure and automatic techniques to distinguish real and recaptured images without prior knowledge. Image manipulation traces can be hidden using recaptured images. For this reason, being able to detect recapture images becomes a hot research topic for a forensic analyst. The attacker can recapture the manipulated images to fool image forensic system. As far as we know, there is no prior research that has examined the pros and cons of up-to-date image recaptured techniques. The main objective of this survey was to succinctly review the recent outcomes in the field of image recaptured detection and investigated the limitations in existing approaches and datasets. The outcome of this study provides several promising directions for further significant research on image recaptured detection. Finally, some of the challenges in the existing datasets and numerous promising directions on recaptured image detection are proposed to demonstrate how these difficulties might be carried into promising directions for future research. We also discussed the existing image recaptured datasets, their limitations, and dataset collection challenges.
5
Premanand Ghadekar, Vaibhavi Shetty, Prapti Maheshwari, Raj Shah, Anish Shaha, and Vaishnav Sonawane. "Non-Facial Video Spatiotemporal Forensic Analysis Using Deep Learning Techniques." Proceedings of Engineering and Technology Innovation 23 (January 1, 2023): 01–14. http://dx.doi.org/10.46604/peti.2023.10290.
Full textAbstract:
Digital content manipulation software is working as a boon for people to edit recorded video or audio content. To prevent the unethical use of such readily available altering tools, digital multimedia forensics is becoming increasingly important. Hence, this study aims to identify whether the video and audio of the given digital content are fake or real. For temporal video forgery detection, the convolutional 3D layers are used to build a model which can identify temporal forgeries with an average accuracy of 85% on the validation dataset. Also, the identification of audio forgery, using a ResNet-34 pre-trained model and the transfer learning approach, has been achieved. The proposed model achieves an accuracy of 99% with 0.3% validation loss on the validation part of the logical access dataset, which is better than earlier models in the range of 90-95% accuracy on the validation set.
6
Ferreira, Sara, Mário Antunes, and Manuel E. Correia. "Exposing Manipulated Photos and Videos in Digital Forensics Analysis." Journal of Imaging 7, no. 7 (June 24, 2021): 102. http://dx.doi.org/10.3390/jimaging7070102.
Full textAbstract:
Tampered multimedia content is being increasingly used in a broad range of cybercrime activities. The spread of fake news, misinformation, digital kidnapping, and ransomware-related crimes are amongst the most recurrent crimes in which manipulated digital photos and videos are the perpetrating and disseminating medium. Criminal investigation has been challenged in applying machine learning techniques to automatically distinguish between fake and genuine seized photos and videos. Despite the pertinent need for manual validation, easy-to-use platforms for digital forensics are essential to automate and facilitate the detection of tampered content and to help criminal investigators with their work. This paper presents a machine learning Support Vector Machines (SVM) based method to distinguish between genuine and fake multimedia files, namely digital photos and videos, which may indicate the presence of deepfake content. The method was implemented in Python and integrated as new modules in the widely used digital forensics application Autopsy. The implemented approach extracts a set of simple features resulting from the application of a Discrete Fourier Transform (DFT) to digital photos and video frames. The model was evaluated with a large dataset of classified multimedia files containing both legitimate and fake photos and frames extracted from videos. Regarding deepfake detection in videos, the Celeb-DFv1 dataset was used, featuring 590 original videos collected from YouTube, and covering different subjects. The results obtained with the 5-fold cross-validation outperformed those SVM-based methods documented in the literature, by achieving an average F1-score of 99.53%, 79.55%, and 89.10%, respectively for photos, videos, and a mixture of both types of content. A benchmark with state-of-the-art methods was also done, by comparing the proposed SVM method with deep learning approaches, namely Convolutional Neural Networks (CNN). Despite CNN having outperformed the proposed DFT-SVM compound method, the competitiveness of the results attained by DFT-SVM and the substantially reduced processing time make it appropriate to be implemented and embedded into Autopsy modules, by predicting the level of fakeness calculated for each analyzed multimedia file.
7
Parkhi, Abhinav, and Atish Khobragade. "Review on deep learning based techniques for person re-identification." 3C TIC: Cuadernos de desarrollo aplicados a las TIC 11, no. 2 (December 29, 2022): 208–23. http://dx.doi.org/10.17993/3ctic.2022.112.208-223.
Full textAbstract:
In-depth study has recently been concentrated on human re-identification, which is a crucial component of automated video surveillance. Re-identification is the act of identifying someone in photos or videos acquired from other cameras after they have already been recognized in an image or video from one camera. Re-identification, which involves generating consistent labelling between several cameras, or even just one camera, is required to reconnect missing or interrupted tracks. In addition to surveillance, it may be used in forensics, multimedia, and robotics.Re-identification of the person is a difficult problem since their look fluctuates across many cameras with visual ambiguity and spatiotemporal uncertainty. These issues can be largely caused by inadequate video feeds or lowresolution photos that are full of unnecessary facts and prevent re-identification. The geographical or temporal restrictions of the challenge are difficult to capture. The computer vision research community has given the problem a lot of attention because of how widely used and valuable it is. In this article, we look at the issue of human re-identification and discuss some viable approaches.
8
Ferreira, Sara, Mário Antunes, and Manuel E. Correia. "A Dataset of Photos and Videos for Digital Forensics Analysis Using Machine Learning Processing." Data 6, no. 8 (August 5, 2021): 87. http://dx.doi.org/10.3390/data6080087.
Full textAbstract:
Deepfake and manipulated digital photos and videos are being increasingly used in a myriad of cybercrimes. Ransomware, the dissemination of fake news, and digital kidnapping-related crimes are the most recurrent, in which tampered multimedia content has been the primordial disseminating vehicle. Digital forensic analysis tools are being widely used by criminal investigations to automate the identification of digital evidence in seized electronic equipment. The number of files to be processed and the complexity of the crimes under analysis have highlighted the need to employ efficient digital forensics techniques grounded on state-of-the-art technologies. Machine Learning (ML) researchers have been challenged to apply techniques and methods to improve the automatic detection of manipulated multimedia content. However, the implementation of such methods have not yet been massively incorporated into digital forensic tools, mostly due to the lack of realistic and well-structured datasets of photos and videos. The diversity and richness of the datasets are crucial to benchmark the ML models and to evaluate their appropriateness to be applied in real-world digital forensics applications. An example is the development of third-party modules for the widely used Autopsy digital forensic application. This paper presents a dataset obtained by extracting a set of simple features from genuine and manipulated photos and videos, which are part of state-of-the-art existing datasets. The resulting dataset is balanced, and each entry comprises a label and a vector of numeric values corresponding to the features extracted through a Discrete Fourier Transform (DFT). The dataset is available in a GitHub repository, and the total amount of photos and video frames is 40,588 and 12,400, respectively. The dataset was validated and benchmarked with deep learning Convolutional Neural Networks (CNN) and Support Vector Machines (SVM) methods; however, a plethora of other existing ones can be applied. Generically, the results show a better F1-score for CNN when comparing with SVM, both for photos and videos processing. CNN achieved an F1-score of 0.9968 and 0.8415 for photos and videos, respectively. Regarding SVM, the results obtained with 5-fold cross-validation are 0.9953 and 0.7955, respectively, for photos and videos processing. A set of methods written in Python is available for the researchers, namely to preprocess and extract the features from the original photos and videos files and to build the training and testing sets. Additional methods are also available to convert the original PKL files into CSV and TXT, which gives more flexibility for the ML researchers to use the dataset on existing ML frameworks and tools.
9
Meshchaninov, Viacheslav Pavlovich, Ivan Andreevich Molodetskikh, Dmitriy Sergeevich Vatolin, and Alexey Gennadievich Voloboy. "Combining contrastive and supervised learning for video super-resolution detection." Keldysh Institute Preprints, no. 80 (2022): 1–13. http://dx.doi.org/10.20948/prepr-2022-80.
Full textAbstract:
Upscaled video detection is a helpful tool in multimedia forensics, but it’s a challenging task that involves various upscaling and compression algorithms. There are many resolution-enhancement methods, including interpolation and deep-learning based super-resolution, and they leave unique traces. This paper proposes a new upscaled-resolution-detection method based on learning of visual representations using contrastive and cross-entropy losses. To explain how the method detects videos, the major components of our framework are systematically reviewed — in particular, it is shown that most data-augmentation approaches hinder the learning of the method. Through extensive experiments on various datasets, our method has been shown to effectively detects upscaling even in compressed videos and outperforms the state-of-theart alternatives. The code and models are publicly available at https://github.com/msu-video-group/SRDM.
10
Jiang, Jianguo, Boquan Li, Baole Wei, Gang Li, Chao Liu, Weiqing Huang, Meimei Li, and Min Yu. "FakeFilter: A cross-distribution Deepfake detection system with domain adaptation." Journal of Computer Security 29, no. 4 (June 18, 2021): 403–21. http://dx.doi.org/10.3233/jcs-200124.
Full textAbstract:
Abuse of face swap techniques poses serious threats to the integrity and authenticity of digital visual media. More alarmingly, fake images or videos created by deep learning technologies, also known as Deepfakes, are more realistic, high-quality, and reveal few tampering traces, which attracts great attention in digital multimedia forensics research. To address those threats imposed by Deepfakes, previous work attempted to classify real and fake faces by discriminative visual features, which is subjected to various objective conditions such as the angle or posture of a face. Differently, some research devises deep neural networks to discriminate Deepfakes at the microscopic-level semantics of images, which achieves promising results. Nevertheless, such methods show limited success as encountering unseen Deepfakes created with different methods from the training sets. Therefore, we propose a novel Deepfake detection system, named FakeFilter, in which we formulate the challenge of unseen Deepfake detection into a problem of cross-distribution data classification, and address the issue with a strategy of domain adaptation. By mapping different distributions of Deepfakes into similar features in a certain space, the detection system achieves comparable performance on both seen and unseen Deepfakes. Further evaluation and comparison results indicate that the challenge has been successfully addressed by FakeFilter.
Dissertations / Theses on the topic "Deep learning for Multimedia Forensics"
1
Nowroozi, Ehsan. "Machine Learning Techniques for Image Forensics in Adversarial Setting." Doctoral thesis, Università di Siena, 2020. http://hdl.handle.net/11365/1096177.
Full textAbstract:
The use of machine-learning for multimedia forensics is gaining more and more consensus, especially due to the amazing possibilities offered by modern machine learning techniques. By exploiting deep learning tools, new approaches have been proposed whose performance remarkably exceed those achieved by state-of-the-art methods based on standard machine-learning and model-based techniques. However, the inherent vulnerability and fragility of machine learning architectures pose new serious security threats, hindering the use of these tools in security-oriented applications, and, among them, multimedia forensics. The analysis of the security of machine learning-based techniques in the presence of an adversary attempting to impede the forensic analysis, and the development of new solutions capable to improve the security of such techniques is then of primary importance, and, recently, has marked the birth of a new discipline, named Adversarial Machine Learning. By focusing on Image Forensics and image manipulation detection in particular, this thesis contributes to the above mission by developing novel techniques for enhancing the security of binary manipulation detectors based on machine learning in several adversarial scenarios. The validity of the proposed solutions has been assessed by considering several manipulation tasks, ranging from the detection of double compression and contrast adjustment, to the detection of geometric transformations and ltering operations.
2
Stanton, Jamie Alyssa. "Detecting Image Forgery with Color Phenomenology." University of Dayton / OhioLINK, 2019. http://rave.ohiolink.edu/etdc/view?acc_num=dayton15574119887572.
Full text
3
Budnik, Mateusz. "Active and deep learning for multimedia." Thesis, Université Grenoble Alpes (ComUE), 2017. http://www.theses.fr/2017GREAM011.
Full textAbstract:
Les thèmes principaux abordés dans cette thèse sont l'utilisation de méthodes d'apprentissage actif et d'apprentissage profond dans le contexte du traitement de documents multimodaux. Les contributions proposées dans cette thèse abordent ces deux thèmes. Un système d'apprentissage actif a été introduit pour permettre une annotation plus efficace des émissions de télévision grâce à la propagation des étiquettes, à l'utilisation de données multimodales et à des stratégies de sélection efficaces. Plusieurs scénarios et expériences ont été envisagés dans le cadre de l'identification des personnes dans les vidéos, en prenant en compte l'utilisation de différentes modalités (telles que les visages, les segments de la parole et le texte superposé) et différentes stratégies de sélection. Le système complet a été validé au cours d'un ``test à blanc'' impliquant des annotateurs humains réels.Une deuxième contribution majeure a été l'étude et l'utilisation de l'apprentissage profond (en particulier les réseaux de neurones convolutifs) pour la recherche d'information dans les vidéos. Une étude exhaustive a été réalisée en utilisant différentes architectures de réseaux neuronaux et différentes techniques d'apprentissage telles que le réglage fin (fine-tuning) ou des classificateurs plus classiques comme les SVMs. Une comparaison a été faite entre les caractéristiques apprises (la sortie des réseaux neuronaux) et les caractéristiques plus classiques (``engineered features''). Malgré la performance inférieure des seconds, une fusion de ces deux types de caractéristiques augmente la performance globale.Enfin, l'utilisation d'un réseau neuronal convolutif pour l'identification des locuteurs à l'aide de spectrogrammes a été explorée. Les résultats ont été comparés à ceux obtenus avec d'autres systèmes d'identification de locuteurs récents. Différentes approches de fusion ont également été testées. L'approche proposée a permis d'obtenir des résultats comparables à ceux certains des autres systèmes testés et a offert une augmentation de la performance lorsqu'elle est fusionnée avec la sortie du meilleur systèmeThe main topics of this thesis include the use of active learning-based methods and deep learning in the context of retrieval of multimodal documents. The contributions proposed during this thesis address both these topics. An active learning framework was introduced, which allows for a more efficient annotation of broadcast TV videos thanks to the propagation of labels, the use of multimodal data and selection strategies. Several different scenarios and experiments were considered in the context of person identification in videos, including using different modalities (such as faces, speech segments and overlaid text) and different selection strategies. The whole system was additionally validated in a dry run involving real human annotators.A second major contribution was the investigation and use of deep learning (in particular the convolutional neural network) for video retrieval. A comprehensive study was made using different neural network architectures and training techniques such as fine-tuning or using separate classifiers like SVM. A comparison was made between learned features (the output of neural networks) and engineered features. Despite the lower performance of the engineered features, fusion between these two types of features increases overall performance.Finally, the use of convolutional neural network for speaker identification using spectrograms is explored. The results are compared to other state-of-the-art speaker identification systems. Different fusion approaches are also tested. The proposed approach obtains comparable results to some of the other tested approaches and offers an increase in performance when fused with the output of the best system
4
Ha, Hsin-Yu. "Integrating Deep Learning with Correlation-based Multimedia Semantic Concept Detection." FIU Digital Commons, 2015. http://digitalcommons.fiu.edu/etd/2268.
Full textAbstract:
The rapid advances in technologies make the explosive growth of multimedia data possible and available to the public. Multimedia data can be defined as data collection, which is composed of various data types and different representations. Due to the fact that multimedia data carries knowledgeable information, it has been widely adopted to different genera, like surveillance event detection, medical abnormality detection, and many others. To fulfil various requirements for different applications, it is important to effectively classify multimedia data into semantic concepts across multiple domains. In this dissertation, a correlation-based multimedia semantic concept detection framework is seamlessly integrated with the deep learning technique. The framework aims to explore implicit and explicit correlations among features and concepts while adopting different Convolutional Neural Network (CNN) architectures accordingly. First, the Feature Correlation Maximum Spanning Tree (FC-MST) is proposed to remove the redundant and irrelevant features based on the correlations between the features and positive concepts. FC-MST identifies the effective features and decides the initial layer's dimension in CNNs. Second, the Negative-based Sampling method is proposed to alleviate the data imbalance issue by keeping only the representative negative instances in the training process.
To adjust dierent sizes of training data, the number of iterations for the CNN is determined adaptively and automatically. Finally, an Indirect Association Rule Mining (IARM) approach and a correlation-based re-ranking method are proposed to reveal the implicit relationships from the correlations among concepts, which are further utilized together with the classification scores to enhance the re-ranking process. The framework is evaluated using two benchmark multimedia data sets, TRECVID and NUS-WIDE, which contain large amounts of multimedia data and various semantic concepts.
5
Vukotic, Verdran. "Deep Neural Architectures for Automatic Representation Learning from Multimedia Multimodal Data." Thesis, Rennes, INSA, 2017. http://www.theses.fr/2017ISAR0015/document.
Full textAbstract:
La thèse porte sur le développement d'architectures neuronales profondes permettant d'analyser des contenus textuels ou visuels, ou la combinaison des deux. De manière générale, le travail tire parti de la capacité des réseaux de neurones à apprendre des représentations abstraites. Les principales contributions de la thèse sont les suivantes: 1) Réseaux récurrents pour la compréhension de la parole: différentes architectures de réseaux sont comparées pour cette tâche sur leurs facultés à modéliser les observations ainsi que les dépendances sur les étiquettes à prédire. 2) Prédiction d’image et de mouvement : nous proposons une architecture permettant d'apprendre une représentation d'une image représentant une action humaine afin de prédire l'évolution du mouvement dans une vidéo ; l'originalité du modèle proposé réside dans sa capacité à prédire des images à une distance arbitraire dans une vidéo. 3) Encodeurs bidirectionnels multimodaux : le résultat majeur de la thèse concerne la proposition d'un réseau bidirectionnel permettant de traduire une modalité en une autre, offrant ainsi la possibilité de représenter conjointement plusieurs modalités. L'approche été étudiée principalement en structuration de collections de vidéos, dons le cadre d'évaluations internationales où l'approche proposée s'est imposée comme l'état de l'art. 4) Réseaux adverses pour la fusion multimodale: la thèse propose d'utiliser les architectures génératives adverses pour apprendre des représentations multimodales en offrant la possibilité de visualiser les représentations dans l'espace des imagesIn this dissertation, the thesis that deep neural networks are suited for analysis of visual, textual and fused visual and textual content is discussed. This work evaluates the ability of deep neural networks to learn automatic multimodal representations in either unsupervised or supervised manners and brings the following main contributions:1) Recurrent neural networks for spoken language understanding (slot filling): different architectures are compared for this task with the aim of modeling both the input context and output label dependencies.2) Action prediction from single images: we propose an architecture that allow us to predict human actions from a single image. The architecture is evaluated on videos, by utilizing solely one frame as input.3) Bidirectional multimodal encoders: the main contribution of this thesis consists of neural architecture that translates from one modality to the other and conversely and offers and improved multimodal representation space where the initially disjoint representations can translated and fused. This enables for improved multimodal fusion of multiple modalities. The architecture was extensively studied an evaluated in international benchmarks within the task of video hyperlinking where it defined the state of the art today.4) Generative adversarial networks for multimodal fusion: continuing on the topic of multimodal fusion, we evaluate the possibility of using conditional generative adversarial networks to lean multimodal representations in addition to providing multimodal representations, generative adversarial networks permit to visualize the learned model directly in the image domain
6
Hamm, Simon, and sinonh@angliss edu au. "Digital Audio Video Assessment: Surface or Deep Learning - An Investigation." RMIT University. Education, 2009. http://adt.lib.rmit.edu.au/adt/public/adt-VIT20091216.154300.
Full textAbstract:
This research aims to investigate an assertion, endorsed by a range of commentators, that multimedia teaching and learning approaches encourage learners to adopt a richer, creative and deeper level of understanding and participation within the learning environment than traditional teaching and learning methods. The thesis examines this assertion by investigating one type of multimedia activity defined (for the purposes of this research) as a digital audio video assessment (DAVA). Data was collected using a constructivist epistemology, interpretative and naturalistic perspective using primarily a qualitative methodology. Three types of data collection methods were used to collect data from thirteen Diploma of Event Management students from William Angliss TAFE. Firstly, participants completed the Biggs Study Process Questionnaire (2001) which is a predictor of deep and surface learning preference. Each participant then engaged in a semi-structured interview that elicited participant's self-declared learning preferences and their approaches to completion of the DAVA. These data sources were then compared. Six factors that are critical in informing the way that the participants approached the DAVA emerged from the analysis of the data. Based on these findings it is concluded that the DAVA does not restrict, inhibit or negatively influence a participants learning preference. Learners with a pre-existing, stable learning preference are likely to adopt a learning approach that is consisten t with their preference. Participants that have a learning preference that is less stable (more flexible) may adopt either a surface or deep approach depending on the specific task, activity or assessment.
7
Quan, Weize. "Detection of computer-generated images via deep learning." Thesis, Université Grenoble Alpes, 2020. http://www.theses.fr/2020GRALT076.
Full textAbstract:
Avec les progrès des outils logiciels d'édition et de génération d'images, il est devenu plus facile de falsifier le contenu des images ou de créer de nouvelles images, même pour les novices. Ces images générées, telles que l'image de rendu photoréaliste et l'image colorisée, ont un réalisme visuel de haute qualité et peuvent potentiellement menacer de nombreuses applications importantes. Par exemple, les services judiciaires doivent vérifier que les images ne sont pas produites par la technologie de rendu infographique, les images colorisées peuvent amener les systèmes de reconnaissance / surveillance à produire des décisions incorrectes, etc. Par conséquent, la détection d'images générées par ordinateur a attiré une large attention dans la communauté de recherche en sécurité de multimédia. Dans cette thèse, nous étudions l'identification de différents types d'images générées par ordinateur, y compris l'image de rendu et l'image coloriée. Nous nous intéressons à identifier si une image est acquise par une caméra ou générée par un programme informatique. L'objectif principal est de concevoir un détecteur efficace, qui a une précision de classification élevée et une bonne capacité de généralisation. Nous considérons la construction de jeux de données, l'architecture du réseau de neurones profond, la méthode d'entraînement, la visualisation et la compréhension, pour les problèmes d'investigation légale des images considérés. Nos principales contributions sont : (1) une méthode de détection d'image colorisée basée sur l'insertion d'échantillons négatifs, (2) une méthode d'amélioration de la généralisation pour la détection d'image colorisée, (3) une méthode d'identification d'image naturelle et d'image de rendu basée sur le réseau neuronal convolutif, et (4) une méthode d'identification d'image de rendu basée sur l'amélioration de la diversité des caractéristiques et des échantillons contradictoiresWith the advances of image editing and generation software tools, it has become easier to tamper with the content of images or create new images, even for novices. These generated images, such as computer graphics (CG) image and colorized image (CI), have high-quality visual realism, and potentially throw huge threats to many important scenarios. For instance, the judicial departments need to verify that pictures are not produced by computer graphics rendering technology, colorized images can cause recognition/monitoring systems to produce incorrect decisions, and so on. Therefore, the detection of computer-generated images has attracted widespread attention in the multimedia security research community. In this thesis, we study the identification of different computer-generated images including CG image and CI, namely, identifying whether an image is acquired by a camera or generated by a computer program. The main objective is to design an efficient detector, which has high classification accuracy and good generalization capability. Specifically, we consider dataset construction, network architecture, training methodology, visualization and understanding, for the considered forensic problems. The main contributions are: (1) a colorized image detection method based on negative sample insertion, (2) a generalization method for colorized image detection, (3) a method for the identification of natural image (NI) and CG image based on CNN (Convolutional Neural Network), and (4) a CG image identification method based on the enhancement of feature diversity and adversarial samples
8
MIGLIORELLI, LUCIA. "Towards digital patient monitoring: deep learning methods for the analysis of multimedia data from the actual clinical practice." Doctoral thesis, Università Politecnica delle Marche, 2022. http://hdl.handle.net/11566/295052.
Full textAbstract:
Acquisire informazioni sullo stato di salute dei pazienti a partire dall’analisi di video registrazioni è un’opportunità cruciale per potenziare le attuali pratiche cliniche di valutazione e monitoraggio. Questa Tesi di Dottorato propone quattro sistemi automatici che analizzano dati multimediali tramite algoritmi di apprendimento profondo (deep learning). Tali sistemi sono stati sviluppati per arricchire le modalità valutative -ad oggi basate sull’osservazione diretta del paziente da parte del clinico e sulla compilazione di scale cliniche spesso raccolte in formato cartaceo- di tre categorie di pazienti: i neonati prematuri, gli adolescenti con sindrome dello spettro autistico e gli adulti affetti da neuropatologie (ictus e sclerosi laterale amiotrofica). Ogni sistema nasce dal dialogo con gli specialisti dei settori e risponde all’esigenza di avere a disposizione nuovi strumenti per trattare i pazienti, che raccolgano misurazioni in maniera continuativa ed ordinata, in sistemi sicuri e facilmente accessibili e si svilupperà in futuro per garantire ai medici, sempre più provati dai ritmi lavorativi serrati, più tempo da dedicare ai pazienti, per curarli meglio e al meglio delle proprie capacità.Acquiring information on patients' health status from the analysis of video recordings is a crucial opportunity to enhance current clinical assessment and monitoring practices. This PhD thesis proposes four automated systems that analyse multimedia data using deep learning methodologies. These systems have been developed to enrich current assessment modalities - so far based on direct observation of the patient by trained clinicians coupled with the compilation of clinical scales often collected in paper format- of three categories of patients: preterm infants, adolescents with autism spectrum syndrome and adults affected by neuropathologies (such as stroke and amyotrophic lateral sclerosis). Each system stems from the clinical need of having new tools to treat patients, able at collecting structured, easily accessible and shareable information. This research will continue to be enhanced to ensure that clinicians have more time to devote to patients, to treat them better and to the best of their ability
9
Dutt, Anuvabh. "Continual learning for image classification." Thesis, Université Grenoble Alpes (ComUE), 2019. http://www.theses.fr/2019GREAM063.
Full textAbstract:
Cette thèse traite de l'apprentissage en profondeur appliqu'e aux tâches de classification des images. La principale motivation du travail est de rendre les techniques d’apprentissage en profondeur actuelles plus efficaces et de faire face aux changements dans la distribution des données. Nous travaillons dans le cadre élargi de l’apprentissage continu, dans le but d’avoir 'a l’avenir des modèles d’apprentissage automatique pouvant être améliorés en permanence.Nous examinons d’abord la modification de l’espace étiquette d’un ensemble de données, les échantillons de données restant les mêmes. Nous considérons une hiérarchie d'étiquettes sémantiques à laquelle appartiennent les étiquettes. Nous étudions comment nous pouvons utiliser cette hiérarchie pour obtenir des améliorations dans les modèles formés à différents niveaux de cette hiérarchie.Les deuxième et troisième contributions impliquent un apprentissage continu utilisant un modèle génératif. Nous analysons la facilité d'utilisation des échantillons d'un modèle génératif dans le cas de la formation de bons classificateurs discriminants. Nous proposons des techniques pour améliorer la sélection et la génération d'échantillons à partir d'un modèle génératif. Ensuite, nous observons que les algorithmes d’apprentissage continu subissent certaines pertes de performances lorsqu’ils sont entraînés séquentiellement à plusieurs tâches. Nous analysons la dynamique de la formation dans ce scénario et comparons avec la formation sur plusieurs tâches simultanément. Nous faisons des observations qui indiquent des difficultés potentielles dans l’apprentissage de modèles dans un scénario d’apprentissage continu.Enfin, nous proposons un nouveau modèle de conception pour les réseaux de convolution. Cette architecture permet de former des modèles plus petits sans compromettre les performances. De plus, la conception se prête facilement à la parallélisation, ce qui permet une formation distribuée efficace.En conclusion, nous examinons deux types de scénarios d’apprentissage continu. Nous proposons des méthodes qui conduisent à des améliorations. Notre analyse met 'egalement en évidence des problèmes plus importants, dont nous aurions peut-être besoin de changements dans notre procédure actuelle de formation de réseau neuronalThis thesis deals with deep learning applied to image classification tasks. The primary motivation for the work is to make current deep learning techniques more efficient and to deal with changes in the data distribution. We work in the broad framework of continual learning, with the aim to have in the future machine learning models that can continuously improve.We first look at change in label space of a data set, with the data samples themselves remaining the same. We consider a semantic label hierarchy to which the labels belong. We investigate how we can utilise this hierarchy for obtaining improvements in models which were trained on different levels of this hierarchy.The second and third contribution involve continual learning using a generative model. We analyse the usability of samples from a generative model in the case of training good discriminative classifiers. We propose techniques to improve the selection and generation of samples from a generative model. Following this, we observe that continual learning algorithms do undergo some loss in performance when trained on several tasks sequentially. We analyse the training dynamics in this scenario and compare with training on several tasks simultaneously. We make observations that point to potential difficulties in the learning of models in a continual learning scenario.Finally, we propose a new design template for convolutional networks. This architecture leads to training of smaller models without compromising performance. In addition the design lends itself to easy parallelisation, leading to efficient distributed training.In conclusion, we look at two different types of continual learning scenarios. We propose methods that lead to improvements. Our analysis also points to greater issues, to over come which we might need changes in our current neural network training procedure
10
Darmet, Ludovic. "Vers une approche basée modèle-image flexible et adaptative en criminalistique des images." Thesis, Université Grenoble Alpes, 2020. https://tel.archives-ouvertes.fr/tel-03086427.
Full textAbstract:
Les images numériques sont devenues un moyen de communication standard et universel. Elles prennent place dans notre vie de tous les jours, ce qui entraîne directement des inquiétudes quant à leur intégrité. Nos travaux de recherche étudient différentes méthodes pour examiner l’authenticité d’une image numérique. Nous nous plaçons dans un contexte réaliste où les images sont en grandes quantités et avec une large diversité de manipulations et falsifications ainsi que de sources. Cela nous a poussé à développer des méthodes flexibles et adaptative face à cette diversité.Nous nous sommes en premier lieu intéressés à la détection de manipulations à l’aide de la modélisation statistiques des images. Les manipulations sont des opérations élémentaires telles qu’un flou, l’ajout de bruit ou une compression. Dans ce cadre, nous nous sommes plus particulièrement focalisés sur les effets d’un pré-traitement. A cause de limitations de stockage et autres, une image peut être re-dimensionnée ou re-compressée juste après sa capture. L’ajout d’une manipulation se fait donc ensuite sur une image déjà pré-traitée. Nous montrons qu’un pré-redimensionnement pour les images de test induit une chute de performance pour des détecteurs entraînés avec des images en pleine taille. Partant de ce constat, nous introduisons deux nouvelles méthodes pour mitiger cette chute de performance pour des détecteurs basés sur l’utilisation de mixtures de gaussiennes. Ces détecteurs modélisent les statistiques locales, sur des tuiles (patches), d’images naturelles. Cela nous permet de proposer une adaptation de modèle guidée par les changements dans les statistiques locales de l’image. Notre première méthode est une adaptation entièrement non-supervisée, alors que la seconde requière l’accès à quelques labels, faiblement supervisé, pour les images pré-resizées.Ensuite, nous nous sommes tournés vers la détection de falsifications et plus spécifiquement l’identification de copier-coller. Le copier-coller est l’une des falsification les plus populaires. Une zone source est copiée vers une zone cible de la même image. La grande majorité des détecteurs existants identifient indifféremment les deux zones (source et cible). Dans un scénario opérationnel, seulement la zone cible est intéressante car uniquement elle représente une zone de falsification. Ainsi, nous proposons une méthode pour discerner les deux zones. Notre méthode utilise également la modélisation locale des statistiques de l’image à l’aide de mixtures de gaussiennes. La procédure est spécifique à chaque image et ainsi évite la nécessité d’avoir recours à de larges bases d’entraînement et permet une plus grande flexibilité.Des résultats expérimentaux pour toutes les méthodes précédemment décrites sont présentés sur des benchmarks classiques de la littérature et comparés aux méthodes de l’état de l’art. Nous montrons que le détecteur classique de détection de manipulations basé sur les mixtures de gaussiennes, associé à nos nouvelles méthodes d’adaptation de modèle peut surpasser les résultats de récentes méthodes deep-learning. Notre méthode de discernement entre source/cible pour copier-coller égale ou même surpasse les performances des dernières méthodes d’apprentissage profond. Nous expliquons ces bons résultats des méthodes classiques face aux méthodes d’apprentissage profond par la flexibilité et l’adaptabilité supplémentaire dont elles font preuve.Pour finir, cette thèse s’est déroulée dans le contexte très spécial d’un concours organisé conjointement par l’Agence National de la Recherche et la Direction Général de l’Armement. Nous décrivons dans un appendice, les différents tours de ce concours et les méthodes que nous avons développé. Nous dressons également un bilan des enseignements de cette expérience qui avait pour but de passer de benchmarks publics à une détection de falsifications d’images très réalistesImages are nowadays a standard and mature medium of communication.They appear in our day to day life and therefore they are subject to concernsabout security. In this work, we study different methods to assess theintegrity of images. Because of a context of high volume and versatilityof tampering techniques and image sources, our work is driven by the necessity to developflexible methods to adapt the diversity of images.We first focus on manipulations detection through statistical modeling ofthe images. Manipulations are elementary operations such as blurring,noise addition, or compression. In this context, we are more preciselyinterested in the effects of pre-processing. Because of storagelimitation or other reasons, images can be resized or compressed justafter their capture. Addition of a manipulation would then be applied on analready pre-processed image. We show that a pre-resizing of test datainduces a drop of performance for detectors trained on full-sized images.Based on these observations, we introduce two methods to counterbalancethis performance loss for a pipeline of classification based onGaussian Mixture Models. This pipeline models the local statistics, onpatches, of natural images. It allows us to propose adaptation of themodels driven by the changes in local statistics. Our first method ofadaptation is fully unsupervised while the second one, only requiring a fewlabels, is weakly supervised. Thus, our methods are flexible to adaptversatility of source of images.Then we move to falsification detection and more precisely to copy-moveidentification. Copy-move is one of the most common image tampering technique. Asource area is copied into a target area within the same image. The vastmajority of existing detectors identify indifferently the two zones(source and target). In an operational scenario, only the target arearepresents a tampering area and is thus an area of interest. Accordingly, wepropose a method to disentangle the two zones. Our method takesadvantage of local modeling of statistics in natural images withGaussian Mixture Model. The procedure is specific for each image toavoid the necessity of using a large training dataset and to increase flexibility.Results for all the techniques described above are illustrated on publicbenchmarks and compared to state of the art methods. We show that theclassical pipeline for manipulations detection with Gaussian MixtureModel and adaptation procedure can surpass results of fine-tuned andrecent deep-learning methods. Our method for source/target disentanglingin copy-move also matches or even surpasses performances of the latestdeep-learning methods. We explain the good results of these classicalmethods against deep-learning by their additional flexibility andadaptation abilities.Finally, this thesis has occurred in the special context of a contestjointly organized by the French National Research Agency and theGeneral Directorate of Armament. We describe in the Appendix thedifferent stages of the contest and the methods we have developed, as well asthe lessons we have learned from this experience to move the image forensics domain into the wild
Books on the topic "Deep learning for Multimedia Forensics"
1
Anagnostopoulos, Aris, Irene Amerini, Luca Maiano, and Lorenzo Ricciardi Celsi. Deep Learning for Multimedia Forensics. Now Publishers, 2021.
Find full text
2
Arumugam, Chamundeswari, Suresh Jaganathan, Saraswathi S, and Sanjay Misra. Confluence of AI, Machine, and Deep Learning in Cyber Forensics. IGI Global, 2020.
Find full text
3
Arumugam, Chamundeswari, Suresh Jaganathan, Saraswathi S, and Sanjay Misra. Confluence of AI, Machine, and Deep Learning in Cyber Forensics. IGI Global, 2020.
Find full text
4
Arumugam, Chamundeswari, Suresh Jaganathan, Saraswathi S, and Sanjay Misra. Confluence of AI, Machine, and Deep Learning in Cyber Forensics. IGI Global, 2020.
Find full text
5
Arumugam, Chamundeswari, Suresh Jaganathan, Saraswathi S, and Sanjay Misra. Confluence of AI, Machine, and Deep Learning in Cyber Forensics. IGI Global, 2020.
Find full text
6
Arumugam, Chamundeswari, Suresh Jaganathan, Saraswathi S, and Sanjay Misra. Confluence of Ai, Machine, and Deep Learning in Cyber Forensics. Information Science Reference, 2020.
Find full textBook chapters on the topic "Deep learning for Multimedia Forensics"
1
Stamm, Matthew C., and Xinwei Zhao. "Anti-Forensic Attacks Using Generative Adversarial Networks." In Multimedia Forensics, 467–90. Singapore: Springer Singapore, 2022. http://dx.doi.org/10.1007/978-981-16-7621-5_17.
Full textAbstract:
AbstractThe rise of deep learning has led to rapid advances in multimedia forensics. Algorithms based on deep neural networks are able to automatically learn forensic traces, detect complex forgeries, and localize falsified content with increasingly greater accuracy. At the same time, deep learning has expanded the capabilities of anti-forensic attackers. New anti-forensic attacks have emerged, including those discussed in Chap. 10.1007/978-981-16-7621-5_14 based on adversarial examples, and those based on generative adversarial networks (GANs). In this chapter, we discuss the emerging threat posed by GAN-based anti-forensic attacks. GANs are a powerful machine learning framework that can be used to create realistic, but completely synthetic data. Researchers have recently shown that anti-forensic attacks can be built by using GANs to create synthetic forensic traces. While only a small number of GAN-based anti-forensic attacks currently exist, results show these early attacks are both effective at fooling forensic algorithms and introduce very little distortion into attacked images.
2
Long, Chengjiang, Arslan Basharat, and Anthony Hoogs. "Video Frame Deletion and Duplication." In Multimedia Forensics, 333–62. Singapore: Springer Singapore, 2022. http://dx.doi.org/10.1007/978-981-16-7621-5_13.
Full textAbstract:
AbstractVideos can be manipulated in a number of different ways, including object addition or removal, deep fake videos, temporal removal or duplication of parts of the video, etc. In this chapter, we provide an overview of the previous work related to video frame deletion and duplication and dive into the details of two deep-learning-based approaches for detecting and localizing frame deletion (Chengjiang et al. 2017) and duplication (Chengjiang et al. 2019) manipulations.
3
Zampoglou, Markos, Foteini Markatopoulou, Gregoire Mercier, Despoina Touska, Evlampios Apostolidis, Symeon Papadopoulos, Roger Cozien, Ioannis Patras, Vasileios Mezaris, and Ioannis Kompatsiaris. "Detecting Tampered Videos with Multimedia Forensics and Deep Learning." In MultiMedia Modeling, 374–86. Cham: Springer International Publishing, 2018. http://dx.doi.org/10.1007/978-3-030-05710-7_31.
Full text
4
Neves, João C., Ruben Tolosana, Ruben Vera-Rodriguez, Vasco Lopes, Hugo Proença, and Julian Fierrez. "GAN Fingerprints in Face Image Synthesis." In Multimedia Forensics, 175–204. Singapore: Springer Singapore, 2022. http://dx.doi.org/10.1007/978-981-16-7621-5_8.
Full textAbstract:
AbstractThe availability of large-scale facial databases, together with the remarkable progresses of deep learning technologies, in particular Generative Adversarial Networks (GANs), have led to the generation of extremely realistic fake facial content, raising obvious concerns about the potential for misuse. Such concerns have fostered the research on manipulation detection methods that, contrary to humans, have already achieved astonishing results in various scenarios. This chapter is focused on the analysis of GAN fingerprints in face image synthesis.
5
Cozzolino, Davide, and Luisa Verdoliva. "Multimedia Forensics Before the Deep Learning Era." In Handbook of Digital Face Manipulation and Detection, 45–67. Cham: Springer International Publishing, 2022. http://dx.doi.org/10.1007/978-3-030-87664-7_3.
Full textAbstract:
AbstractImage manipulation is as old as photography itself, and powerful media editing tools have been around for a long time. Using such conventional signal processing methods, it is possible to modify images and videos obtaining very realistic results. This chapter is devoted to describe the most effective strategies to detect the widespread manipulations that rely on traditional approaches and do not require a deep learning strategy. In particular, we will focus on manipulations like adding, replicating, or removing objects and present the major lines of research in multimedia forensics before the deep learning era and the rise of deepfakes. The most popular approaches look for artifacts related to the in-camera processing chain (camera-based clues) or the out-camera processing history (editing-based clues). We will focus on methods that rely on the extraction of a camera fingerprint and need some prior information on pristine data, for example, through a collection of images taken from the camera of interest. Then we will shift to blind methods that do not require any prior knowledge and reveal inconsistencies with respect to some well-defined hypotheses. We will also briefly review the most interesting features of machine learning- based methods and finally present the major challenges in this area.
6
Lyu, Siwei. "DeepFake Detection." In Multimedia Forensics, 313–31. Singapore: Springer Singapore, 2022. http://dx.doi.org/10.1007/978-981-16-7621-5_12.
Full textAbstract:
AbstractOne particular disconcerting form of disinformation are the impersonating audios/videos backed by advanced AI technologies, in particular, deep neural networks (DNNs). These media forgeries are commonly known as the DeepFakes. The AI-based tools are making it easier and faster than ever to create compelling fakes that are challenging to spot. While there are interesting and creative applications of this technology, it can be weaponized to cause negative consequences. In this chapter, we survey the state-of-the-art DeepFake detection methods.
7
Li, Zhuopeng, and Xiaoyan Zhang. "Deep Reinforcement Learning for Automatic Thumbnail Generation." In MultiMedia Modeling, 41–53. Cham: Springer International Publishing, 2018. http://dx.doi.org/10.1007/978-3-030-05716-9_4.
Full text
8
Rossetto, Luca, Mahnaz Amiri Parian, Ralph Gasser, Ivan Giangreco, Silvan Heller, and Heiko Schuldt. "Deep Learning-Based Concept Detection in vitrivr." In MultiMedia Modeling, 616–21. Cham: Springer International Publishing, 2018. http://dx.doi.org/10.1007/978-3-030-05716-9_55.
Full text
9
Dey, Nilanjan, Amira S. Ashour, and Gia Nhu Nguyen. "Deep Learning for Multimedia Content Analysis." In Mining Multimedia Documents, 193–204. Boca Raton : CRC Press, [2017]: Chapman and Hall/CRC, 2017. http://dx.doi.org/10.1201/b21638-14.
Full text
10
Dey, Nilanjan, Amira S. Ashour, and Gia Nhu Nguyen. "Deep Learning for Multimedia Content Analysis." In Mining Multimedia Documents, 193–203. Taylor & Francis Group, 6000 Broken Sound Parkway NW, Suite 300, Boca Raton, FL 33487-2742: CRC Press, 2017. http://dx.doi.org/10.1201/9781315399744-15.
Full textConference papers on the topic "Deep learning for Multimedia Forensics"
1
Verdoliva, Luisa. "Deep Learning in Multimedia Forensics." In IH&MMSec '18: 6th ACM Workshop on Information Hiding and Multimedia Security. New York, NY, USA: ACM, 2018. http://dx.doi.org/10.1145/3206004.3206024.
Full text
2
Liu, Qingzhong, and Naciye Celebi. "Large Feature Mining and Deep Learning in Multimedia Forensics." In CODASPY '21: Eleventh ACM Conference on Data and Application Security and Privacy. New York, NY, USA: ACM, 2021. http://dx.doi.org/10.1145/3445970.3456285.
Full text
3
Mayer, Owen, Belhassen Bayar, and Matthew C. Stamm. "Learning Unified Deep-Features for Multiple Forensic Tasks." In IH&MMSec '18: 6th ACM Workshop on Information Hiding and Multimedia Security. New York, NY, USA: ACM, 2018. http://dx.doi.org/10.1145/3206004.3206022.
Full text
4
Wei, Baole, Min Yu, Kai Chen, and Jianguo Jiang. "Deep-BIF: Blind Image Forensics Based on Deep Learning." In 2019 IEEE Conference on Dependable and Secure Computing (DSC). IEEE, 2019. http://dx.doi.org/10.1109/dsc47296.2019.8937712.
Full text
5
Nazar, Nidhin, Vinod Kumar Shukla, Gagandeep Kaur, and Nitin Pandey. "Integrating Web Server Log Forensics through Deep Learning." In 2021 9th International Conference on Reliability, Infocom Technologies and Optimization (Trends and Future Directions) (ICRITO). IEEE, 2021. http://dx.doi.org/10.1109/icrito51393.2021.9596324.
Full text
6
Andersson, Maria. "Deep learning for behaviour recognition in surveillance applications." In Counterterrorism, Crime Fighting, Forensics, and Surveillance Technologies III, edited by Henri Bouma, Robert J. Stokes, Yitzhak Yitzhaky, and Radhakrishna Prabhu. SPIE, 2019. http://dx.doi.org/10.1117/12.2533764.
Full text
7
Wang, Hsin-Tzu, and Po-Chyi Su. "Deep-Learning-Based Block Similarity Evaluation for Image Forensics." In 2020 IEEE International Conference on Consumer Electronics - Taiwan (ICCE-Taiwan). IEEE, 2020. http://dx.doi.org/10.1109/icce-taiwan49838.2020.9258247.
Full text
8
Buccoli, Michele, Paolo Bestagini, Massimiliano Zanoni, Augusto Sarti, and Stefano Tubaro. "Unsupervised feature learning for bootleg detection using deep learning architectures." In 2014 IEEE International Workshop on Information Forensics and Security (WIFS). IEEE, 2014. http://dx.doi.org/10.1109/wifs.2014.7084316.
Full text
9
Sang, Jitao, Jun Yu, Ramesh Jain, Rainer Lienhart, Peng Cui, and Jiashi Feng. "Deep Learning for Multimedia." In MM '18: ACM Multimedia Conference. New York, NY, USA: ACM, 2018. http://dx.doi.org/10.1145/3240508.3243931.
Full text
10
Chien, Jen-Tzung. "Deep Bayesian Multimedia Learning." In MM '20: The 28th ACM International Conference on Multimedia. New York, NY, USA: ACM, 2020. http://dx.doi.org/10.1145/3394171.3418545.
Full text