Overview

  • Number of papers: 14

    • DATASET: 14

For supported action algorithms, see modelzoo overview.

Supported Datasets

  • Number of papers: 14

    • [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] 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 ⇨)