- [2016 CVPR] Dynamic Image Networks for Action Recognition, [paper], [bibtex], sources: [hbilen/dynamic-image-nets].
- [2016 CVPR] End-to-end Learning of Action Detection from Frame Glimpses in Videos, [paper], [bibtex], sources: [syyeung/frameglimpses].
- [2017 ICCV] TURN TAP: Temporal Unit Regression Network for Temporal Action Proposals, [paper], [supplementary], [bibtex], sources: [jiyanggao/TURN-TAP].
- [2017 ICCV] Action Tubelet Detector for Spatio-Temporal Action Localization, [paper], [bibtex], [homepage], sources: [vkalogeiton/act-detector].
- [2017 CVPR] Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset, [paper], [bibtex], sources: [deepmind/kinetics-i3d], [piergiaj/pytorch-i3d], [hassony2/kinetics_i3d_pytorch], [LossNAN/I3D-Tensorflow], [tomrunia/PyTorchConv3D], [dlpbc/keras-kinetics-i3d].
- [2017 PAMI] Action Recognition with Dynamic Image Networks, [paper], [bibtex], sources: [hbilen/dynamic-image-nets].
- [2017 CVPR] SST: Single-Stream Temporal Action Proposals, [paper], [bibtex], sources: [shyamal-b/sst].
- [2018 CVPR] Non-local Neural Networks, [paper], [bibtex], sources: [facebookresearch/video-nonlocal-net].
- [2018 ECCV] BSN: Boundary Sensitive Network for Temporal Action Proposal Generation, [paper], [bibtex], sources: [wzmsltw/BSN-boundary-sensitive-network].
- [2019 ICCV] SlowFast Networks for Video Recognition, [paper], [bibtex], sources: [facebookresearch/SlowFast].
- [2019 ICCV] Weakly-supervised Action Localization with Background Modeling, [paper], [bibtex].
- [2019 ICCV] TSM: Temporal Shift Module for Efficient Video Understanding, [paper], [bibtex], sources: [mit-han-lab/temporal-shift-module].
- [2019 CVPR] Self-supervised Spatiotemporal Learning via Video Clip Order Prediction, [paper], [bibtex], sources: [xudejing/video-clip-order-prediction].
- [2020 CVPR] G-TAD: Sub-Graph Localization for Temporal Action Detection, [paper], [bibtex], [homepage], sources: [frostinassiky/gtad].
- [2021 CVPR] The Blessings of Unlabeled Background in Untrimmed Videos, [paper], [bibtex], sources: [liuyuancv/WTAL_blessing].
- [2022 ArXiv] ActionFormer: Localizing Moments of Actions with Transformers, [paper], [bibtex], sources: [happyharrycn/actionformer_release].