The two-volume set LNCS 9516 and LNCS 9517 constitutes the refereed proceedings of the 22nd International Conference on Multimedia Modeling, MMM 2016, held in Miami, FL, USA, in January 2016. The 32 revised full papers and 52 poster papers presented were carefully reviewed and selected from 117 submissions. In addition 20 papers were accepted for five special sessions out of 38 submissions as well as 7 demonstrations (from 11 submissions) and 9 video showcase papers. The papers are organized in topical sections on video content analysis, social media analysis, object recognition and system, multimedia retrieval and ranking, multimedia representation, machine learning in multimedia, and interaction and mobile. The special sessions are: good practices in multimedia modeling; semantics discovery from multimedia big data; perception, aesthetics, and emotion in multimedia quality modeling; multimodal learning and computing for human activity understanding; and perspectives on multimedia analytics.

The two-volume set LNCS 9516 and 9517 constitutes the thoroughly refereed proceedings of the 22nd International Conference on Multimedia Modeling, MMM 2016, held in Miami, FL, USA, in January 2016. The 32 revised full papers and 52 poster papers were carefully reviewed and selected from 117 submissions. In addition 20 papers were accepted for five special sessions out of 38 submissions as well as 7 demonstrations (from 11 submissions) and 9 video showcase papers. The papers are organized in topical sections on video content analysis, social media analysis, object recognition and system, multimedia retrieval and ranking, multimedia representation, machine learning in multimedia, and interaction and mobile. The special sessions are: good practices in multimedia modeling; semantics discovery from multimedia big data; perception, aesthetics, and emotion in multimedia quality modeling; multimodal learning and computing for human activity understanding; and perspectives on multimedia analytics.

The 16th international conference on Multimedia Modeling (MMM2010) was held in the famous mountain city Chongqing, China, January 6-8, 2010, and hosted by Southwest University. MMM is a leading international conference for researchersand industry practitioners to share their new ideas, original research results and practicaldevelopment experiences from all multimedia related areas. MMM2010attractedmorethan160regular, specialsession, anddemosession submissions from 21 countries/regions around the world. All submitted papers were reviewed by at least two PC members or external reviewers, and most of them were reviewed by three reviewers. The review process was very selective. From the total of 133 submissions to the main track, 43 (32. 3%) were accepted as regular papers, 22 (16. 5%) as short papers. In all, 15 papers were received for three special sessions, which is by invitation only, and 14 submissions were received for a demo session, with 9 being selected. Authors of accepted papers come from 16 countries/regions. This volume of the proceedings contains the abstracts of three invited talks and all the regular, short, special session and demo papers. The regular papers were categorized into nine sections: 3D mod- ing;advancedvideocodingandadaptation;face, gestureandapplications;image processing;imageretrieval;learningsemanticconcepts;mediaanalysisandm- eling; semantic video concepts; and tracking and motion analysis. Three special sessions were video analysis and event recognition, cross-X multimedia mining in large scale, and mobile computing and applications. The technical programfeatured three invited talks, paralleloral presentation of all the accepted regular and special session papers, and poster sessions for short and demo pape