Middle-level representation for human activities recognition : the role of spatio-temporal relationships

• المؤلفون الرئيسيون: Yuan, Fei, Prinet, V´eronique, Yuan, Junsong
• مؤلفون آخرون: Kutulakos, Kiriakos N.
• التنسيق: فصل الكتاب
• اللغة: English
• منشور في: Springer Berlin Heidelberg 2014
• الموضوعات: DRNTU::Engineering::Electrical and electronic engineering
• الوصول للمادة أونلاين: https://hdl.handle.net/10356/103853; http://hdl.handle.net/10220/19350
• المؤسسة: Nanyang Technological University

We tackle the challenging problem of human activity recognition in realistic video sequences. Unlike local features-based methods or global template-based methods, we propose to represent a video sequence by a set of middle-level parts. A part, or component, has consistent spatial structure and cons...