Panos Sourtzinos, Sergio A. Velastin, Miguel Jara, Pablo Zegers, Dimitrios Makris. People Counting in Videos by Fusing Temporal Cues from Spatial Context-Aware Convolutional Neural Networks. In Gang Hua, Hervé Jégou, editors, Computer Vision - ECCV 2016 Workshops - Amsterdam, The Netherlands, October 8-10 and 15-16, 2016, Proceedings, Part II. Volume 9914 of Lecture Notes in Computer Science, pages 655-667, 2016. [doi]
Abstract is missing.