Weakly-Supervised Action Recognition
3 papers with code • 0 benchmarks • 0 datasets
Action recognition with single-point annotations in time (there are no action start/stop time annotations)
Benchmarks
These leaderboards are used to track progress in Weakly-Supervised Action Recognition
Most implemented papers
UntrimmedNets for Weakly Supervised Action Recognition and Detection
We exploit the learned models for action recognition (WSR) and detection (WSD) on the untrimmed video datasets of THUMOS14 and ActivityNet.
Learning from Video and Text via Large-Scale Discriminative Clustering
Discriminative clustering has been successfully applied to a number of weakly-supervised learning tasks.
Re-ID-AR: Improved Person Re-identification in Video via Joint Weakly Supervised Action Recognition
Our consideration of Re-ID and action recognition as a multi-task problem results in a multi-branch 2D CNN architecture that outperforms prior work in the field (rank-1 (mAP) – MARS: 93. 21%(87. 23%), LPW: 79. 60%) without any reliance 3D convolutions or multi-stream networks architectures as found in other contemporary work.