We propose a unified global entropy reduction maximization (GERM) framework for active learning and semi-supervised learning for speech recognition. Active learning aims to select...
Dong Yu, Balakrishnan Varadarajan, Li Deng, Alex A...
We propose a novel general framework with a boosting algorithm to achieve active object classification by view selection. The proposed framework actively decides the next best vie...
Many dramatizations have depicted a fully automated home living environment, where actions and events are understood or even anticipated. While the realization of such environment...
Complex human activities occurring in videos can be defined in terms of temporal configurations of primitive actions. Prior work typically hand-picks the primitives, their total...
QMUL junction dataset is for research on activity analysis and crowded scenes.
Video length: 1 hour (90000 frames)
Frame size: 360x288
Frame rate: 25 Hz
Compression codec: ff...