Part I. Multimedia content analysis -- 1. Deep learning for video classification and captioning / Zuxuan Wu, Ting Yao, Yanwei Fu, Yu-gang Jiang -- 1.1 Introduction -- 1.2 Basic deep learning modules -- 1.3 Video classification -- 1.4 Video captioning -- 1.5 Benchmarks and challenges -- 1.6 Conclusion -- 2. Audition for multimedia computing / Gerald Friedland, Paris Smaragdis, Josh McDermott, Bhiksha Raj -- 2.1 A new field -- 2.2 Background -- 2.3 Data for computer audition -- 2.4 The nature of audio data -- 2.5 Dealing with the peculiarities of sound -- 2.6 Potential applications -- 2.7 Conclusion -- Acknowledgments -- 3. Multimodal analysis of free-standing conversational groups / Xavier Alameda-Pineda, Elisa Ricci, Nicu Sebe -- 3.1 Introduction -- 3.2 Related work -- 3.3 The SALSA dataset -- 3.4 Matrix completion for multimodal pose estimation -- 3.5 Experiments -- 3.6 Conclusion -- 4. Encrypted domain multimedia content analysis / Pradeep K. Atrey, Ankita Lathey, Abukari M. Yakubu -- 4.1 Introduction -- 4.2 SPED: an overview -- 4.3 Image processing in encrypted domain -- 4.4 Video processing in encrypted domain -- 4.5 Audio processing in encrypted domain -- 4.6 Further discussion -- 4.7 Conclusion -- 5. Efficient similarity search / Herve Jegou -- 5.1 Background -- 5.2 Cell-probe algorithms -- 5.3 Sketches and binary embeddings -- 5.4 Searching and similarity estimation with quantization -- 5.5 Hybrid approaches: the best of probing and sketching -- 5.6 Searching for non-Euclidean metrics and graph-based approaches -- 5.7 Conclusion --

Part II. Human-centered multimedia computing -- 6. Social-sensed multimedia computing / Peng Cui -- 6.1 Semantic gap vs. need gap -- 6.2 Social-sensed multimedia computing -- 6.3 Basic problems and key technologies -- 6.4 Recent advances -- 6.5 Exemplary applications -- 6.6 Discussions on future directions -- 6.7 Conclusion -- 7.Situation recognition using multimodal data / Vivek Singh -- 7.1 The emerging eco-system and a motivating application -- 7.2 Defining situation -- 7.3 A framework for situation recognition -- 7.4 EventShop: a toolkit for situation recognition -- 7.5 Building situation-aware applications using EventShop: -- 7.6 Open challenges and opportunities -- 7.7 Conclusion -- Acknowledgments -- 8. Hawkes processes for events in social media / Marian-Andrei Rizoiu, Young Lee, Swapnil Mishra, Lexing Xie -- 8.1 Introduction -- 8.2 Preliminary: Poisson processes -- 8.3 Hawkes processes -- 8.4 Simulating events from Hawkes processes -- 8.5 Estimation of Hawkes processes parameters -- 8.6 Constructing a Hawkes model for social media -- 8.7 Conclusion -- 9. Utilizing implicit user cues for multimedia analytics / Subramanian Ramanathan, Syed Omer Gilani, Nicu Sebe -- 9.1 Introduction -- 9.2 Inferring scene semantics from eye movements -- 9.3 Eye fixations as implicit annotations for object recognition -- 9.4 Emotion and personality type recognition via physiological signals -- 9.5 Conclusion --

Part III. Multimedia communication and systems -- 10. Multimedia fog computing: minions in the cloud and crowd / Cheng-Hsin Hsu, Hua-Jun Hong, Tarek Elgamal, Klara Nahrstedt, Nalini Venkatasubramanian -- 10.1 Introduction -- 10.2 Related work -- 10.3 Challenges -- 10.4 Distributed multimedia applications: what we can learn from prior studies -- 10.5 Deployment: open-source platforms -- 10.6 Conclusion -- 11. Cloud gaming / Kuan-Ta Chen, Wei Cai, Ryan Shea, Chun-Ying Huang, Jiangchuan Liu, -- Victor C. M. Leung, Cheng-Hsin Hsu -- 11.1 Overview on cloud gaming research -- 11.2 GamingAnywhere: an open-source cloud gaming platform -- 11.3 Cloud deployment -- 11.4 Thin client design -- 11.5 Communication -- 11.6 Future paradigm of cloud gaming -- 11.7 Conclusion -- Bibliography -- Index -- Editor biography.