Multimodal Behavioral Analysis in the Wild: Advances and Challenges presents the state-of- the-art in behavioral signal processing using different data modalities, with a special focus on identifying the strengths and limitations of current technologies. The book focuses on audio and video modalities, while also emphasizing emerging modalities, such as accelerometer or proximity data. It covers tasks at different levels of complexity, from low level (speaker detection, sensorimotor links, source separation), through middle level (conversational group detection, addresser and addressee identification), and high level (personality and emotion recognition), providing insights on how to exploit inter-level and intra-level links.
This is a valuable resource on the state-of-the- art and future research challenges of multi-modal behavioral analysis in the wild. It is suitable for researchers and graduate students in the fields of computer vision, audio processing, pattern recognition, machine learning and social signal processing.
- Gives a comprehensive collection of information on the state-of-the-art, limitations, and challenges associated with extracting behavioral cues from real-world scenarios
- Presents numerous applications on how different behavioral cues have been successfully extracted from different data sources
- Provides a wide variety of methodologies used to extract behavioral cues from multi-modal data
1. Multimodal behavior analysis in the wild: an introduction 2. Auditory-motor perception in natural environments 3. An integrated audio-visual framework for assisting visually impaired users 4. Audio-visual person identification with wearable cameras 5. Understanding social relationships in egocentric vision 6. Lifelogging through egocentric vision 7. A study of speech distortion conditions in real scenarios for speech processing applications 8. Understanding the scene from a first-person perspective 9. Behavior analysis from wearable sensors 10. Wearable systems for improving museum experience 11. Animal behavior in museums 12. Separating multiple moving sound sources 13. Behaviour analysis of crowds from fixed and moving cameras 14. Detecting conversational groups in images and sequences: a game-theoretic perspective 15. Audio-visual scene understanding with robots 16. Hirability in the Wild: Analysis of Online Conversational Video Resumes 17. Multimodal open-domain conversations with robotic platforms 18. Deep multimodal fusion for persuasiveness prediction 19. Directions robot: In-the-wild experiences and lessons learned 20. Affective facial computing in the wild 21. Automatic recognition of self-reported and perceived emotions 22. Real-world automatic continuous affect recognition from audiovisual signals 23. Deep audio-visual emotion recognition 24. Deep face attributes in the wild 25. Valence and Arousal estimation in the wild 26. Capturing Order in Social Interactions 27. Human Postural Sway Estimation from Noisy Observations 28. Video Based Emotion Recognition in the Wild using Deep Transfer Learning and Score Fusion 29. Socially-aware group detection 30. Open challenges in recognizing behavior in the wild
Xavier Alameda-Pineda received his PhD from INRIA and University of Grenoble in2013. He was a post-doctoral researcher at CNRS/GIPSA-Lab and at the University of Trento, in the deep relational learning group. He is a research scientist at INRIA working on signal processing and machine learning for scene and behavior understanding using multimodal data. He is the winner of the best paper award of ACM MM 2015, the best student paper award at IEEE WASPAA 2015 and the best scientific paper award on image, speech, signal and video processing at IEEE ICPR 2016. He is member of IEEE and of ACM SIGMM.
Elisa Ricci is a researcher at FBK and an assistant professor at University of Perugia. She received her PhD from the University of Perugia in 2008. She has since been a postdoctoral researcher at Idiap and FBK, Trento and a visiting researcher at University of Bristol. Her research interests are directed along developing machine learning algorithms for video scene analysis, human behaviour understanding and multimedia content analysis. She is area chair of ACM MM 2016 and of ECCV 2016. She received the IBM Best Student Paper Award at ICPR 2014.
Nicu Sebe is a full professor at the University of Trento, Italy, where he is leading the research in the areas of multimedia information retrieval and human behavior understanding. He was a general co-chair of FG 2008 and ACM MM 2013, and a program chair of CIVR 2007 and 2010, of ACM MM 2007 and 2011, and of ECCV 2016. He is a program chair of ICCV 2017 and of ICPR 2020, and a general chair of ICMR 2017. He is a senior member of IEEE and ACM and a fellow of IAPR.