THUMOS'14, ActivityNet v1.3

Temporal action detection in untrimmed videos via multi-stage cnns, Cdc: convolutional-de-convolutional networks for precise temporal action localization, Temporal action detection with structured segment networks, Cascaded boundary regression for temporal action detection, Temporal convolution based action proposal, Turn tap: Temporal unit regression network for temporal action proposals, Rethinking the faster r-cnn architecture for temporal action localization, ActivityNet: A large-scale video benchmark for human activity understanding, Two-stream convolutional networks for action recognition in videos, Learning spatiotemporal features with 3d convolutional networks, Quo vadis, action recognition? A new model and the kinetics dataset, Compressed video action recognition