Overview

• Number of papers: 16

  • DATASET: 16

For supported action algorithms, see modelzoo overview.

Supported Datasets

• Number of papers: 16

  • [DATASET] Activitynet: A Large-Scale Video Benchmark for Human Activity Understanding (ActivityNet ->)

  • [DATASET] Ava: A Video Dataset of Spatio-Temporally Localized Atomic Visual Actions (AVA ->)

  • [DATASET] Finegym: A Hierarchical Video Dataset for Fine-Grained Action Understanding (GYM ->)

  • [DATASET] Hmdb: A Large Video Database for Human Motion Recognition (HMDB51 ->)

  • [DATASET] Large Scale Holistic Video Understanding (HVU ->)

  • [DATASET] Moments in Time Dataset: One Million Videos for Event Understanding (Moments in Time ->)

  • [DATASET] Multi-Moments in Time: Learning and Interpreting Models for Multi-Action Video Understanding (Multi-Moments in Time ->)

  • [DATASET] Omni-Sourced Webly-Supervised Learning for Video Recognition (OmniSource ->)

  • [DATASET] Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset (Kinetics-[400/600/700] ->)

  • [DATASET] Resound: Towards Action Recognition Without Representation Bias (Diving48 ->)

  • [DATASET] Revisiting Skeleton-Based Action Recognition (Skeleton Dataset ->)

  • [DATASET] The “Something Something” Video Database for Learning and Evaluating Visual Common Sense (Something-Something V2 ->, Something-Something V1 ->)

  • [DATASET] The Jester Dataset: A Large-Scale Video Dataset of Human Gestures (Jester ->)

  • [DATASET] Towards Understanding Action Recognition (JHMDB ->)

  • [DATASET] Ucf101: A Dataset of 101 Human Actions Classes From Videos in the Wild (UCF101-24 ->, UCF-101 ->)

  • [DATASET] {Thumos (THUMOS’14 ->)