Some novel paradigms for analyzing human actions in complex videos

Human action detection and recognition from videos are two of the most challenging tasks in computer vision. These problems become even more severe while dealing with fine-grained action categories. An exploration of the evolution of salient bodyparts’ (local motion) is needed in this respect to better discriminate such similar-looking human activities. Dominant action detection paradigms work by locating actions of interest on a frame by frame basis, and linking them up in time to form ‘action tubes’. Moreover, given the vast category of possible actions, it is very hard to annotate labelled training videos in a cost-effective manner. We intend to explore the ‘zero-shot’  a 'few-shot' learning paradigms to enable the recognition of previously unseen human activities in a move beyond traditional supervised settings.