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.
The UK-India Education and Research Initiative (UKIERI) started in April 2006 with the aim of enhancing educational linkages between India and the UK. Since then UKIERI has been recognized as a key multi stakeholder programme that has strengthened the research, leadership, education and now skill sector relations between the two countries.
Established in 1958, the second of its kind, IIT Bombay is recognised worldwide as a leader in the field of engineering education and research. Reputed for the outstanding calibre of students graduating from its undergraduate and postgraduate programmes, the institute attracts the best students from the country for its bachelor's, master's and doctoral programmes. Research and academic programmes at IIT Bombay are driven by an outstanding faculty, many of whom are reputed for their research contributions internationally.