End-to-end Learning of Action Detection from Frame Glimpses in Videos

Benchmark Model Rank Results
action-recognition-in-videos-on-thumos14Yeung et. al.#6mAP@0.5: 17.1mAP@0.1: 48.9mAP@0.2: 44.0mAP@0.3: 36.0
temporal-action-localization-on-thumos14Yeung et al.#31mAP IOU@0.1: 48.9mAP IOU@0.2: 44.0mAP IOU@0.3: 36.0