A curated list of temporal action localization/detection and related area (e.g. temporal action proposal) resources.
- [PGCN] Graph Convolutional Networks for Temporal Action Localization - Runhao Zeng et al,
ICCV 2019. [code] - [RAM] Graph Convolutional Networks for Temporal Action Localization - Peihao Chen et al,
TMM 2019. - [BMN] BMN: Boundary-Matching Network for Temporal Action Proposal Generation - Tianwei Lin et al,
ICCV 2019. - [GTAN] Gaussian Temporal Awareness Networks for Action Localization - Fuchen Long et al,
CVPR 2019. - [DBS] Video Imprint Segmentation for Temporal Action Detection in Untrimmed Videos - Zhanning Gao et al,
AAAI 2019. - [C-TCN] Deep Concept-wise Temporal Convolutional Networks for Action Localization - Xin Li et al,
arXiv 2019. - [PGCN] G-TAD: Sub-Graph Localization for Temporal Action Detection - MengMeng Xu et al,
arXiv 2019.
- [TAL-Net] Rethinking the Faster R-CNN Architecture for Temporal Action Localization - Yuwei Chao et al,
CVPR 2018. - [Action-Search] Action Search: Spotting Actions in Videos and Its Application to Temporal Action Localization - Humam Alwassel et al,
ECCV 2018. [code] - [BSN] BSN: Boundary Sensitive Network for Temporal Action Proposal Generation - Tianwei Lin et al,
ECCV 2018. [code] - [TPC] Exploring Temporal Preservation Networks for Precise Temporal Action Localization - Ke Yang et al,
AAAI 2018. - [Self-Ad] A Self-Adaptive Proposal Model for Temporal Action Detection based on Reinforcement Learning - Jingjia Huang et al,
AAAI 2018.
- [CDC] CDC: Convolutional-De-Convolutional Networks for Precise Temporal Action Localization in Untrimmed Videos - Zheng Shou et al,
CVPR 2017. [code] - [SMS] Temporal Action Localization by Structured Maximal Sums - Zehuan Yuan et al,
CVPR 2017. - [SCC] SCC: Semantic Context Cascade for Efficient Action Detection - Fabian Caba Heilbron et al,
CVPR 2017. - [SSN] Temporal Action Detection with Structured Segment Networks - Yue Zhao et al,
ICCV 2017. [code] - [R-C3D] R-C3D: Region Convolutional 3D Network for Temporal Activity Detection - Huijuan Xu et al,
ICCV 2017. [code] - [TCN] Temporal Context Network for Activity Localization in Videos - Xiyang Dai et al,
ICCV 2017. - [TURN] TURN TAP: Temporal Unit Regression Network for Temporal Action Proposals - Jiyang Gao et al,
ICCV 2017. [code] - [SST] SST: Single-Stream Temporal Action Proposals - Shyamal Buch et al,
ICCV 2017.
- [FG] End-to-end Learning of Action Detection from Frame Glimpses in Videos - Serena Yeung et al,
CVPR 2016. - [PSDF] Temporal Action Localization with Pyramid of Score Distribution Features - Jun Yuan et al,
CVPR 2016. - [SLM] Temporal Action Detection Using a Statistical Language Model - Alexander Richard et al,
CVPR 2016. - [S-CNN] Temporal Action Localization in Untrimmed Videos via Multi-stage CNNs - Zheng Shou et al,
CVPR 2016. [code] - [DAPs] DAPs: Deep Action Proposals for Action Understanding - Victor Escorcia et al,
ECCV 2016.
| Method | Conference | IoU@0.1 | IoU@0.2 | IoU@0.3 | IoU@0.4 | IoU@0.5 | IoU@0.6 | IoU@0.7 |
|---|---|---|---|---|---|---|---|---|
| FG | CVPR-2016 | 48.9 | 44.0 | 36.0 | 26.4 | 17.1 | - | - |
| PSDF | CVPR-2016 | 51.4 | 42.6 | 33.6 | 26.1 | 18.8 | - | - |
| SLM | CVPR-2016 | 39.7 | 35.7 | 30.0 | 23.2 | 15.2 | - | - |
| S-CNN | CVPR-2016 | 47.7 | 43.5 | 36.3 | 28.7 | 19.0 | 10.3 | 5.3 |
| DAPs | ECCV-2016 | - | - | - | - | 13.9 | - | - |
| CDC | CVPR-2017 | - | - | 40.1 | 29.4 | 23.3 | 13.1 | 7.9 |
| SMS | CVPR-2017 | 51.0 | 45.2 | 36.5 | 27.8 | 17.8 | - | - |
| SSN | ICCV-2017 | 66.0 | 59.4 | 51.9 | 41.0 | 29.8 | - | - |
| R-C3D | ICCV-2017 | 54.5 | 51.5 | 44.8 | 35.6 | 28.9 | - | - |
| TCN | ICCV-2017 | - | - | - | 33.3 | 25.6 | 15.9 | 9.0 |
| TURN | ICCV-2017 | 54.0 | 50.9 | 44.1 | 34.9 | 25.6 | - | - |
| SST | ICCV-2017 | - | - | - | - | 23.0 | - | - |
| Action-Search | ECCV-2018 | - | - | 51.8 | 42.4 | 30.8 | 20.2 | 11.1 |
| BSN | ECCV-2018 | - | - | 53.5 | 45.0 | 36.9 | 28.4 | 20.0 |
| TPC | AAAI-2018 | - | - | 44.1 | 37.1 | 28.2 | 20.6 | 12.7 |
| Self-Ad | AAAI-2018 | - | - | - | - | 27.7 | - | - |
| DBS | AAAI-2019 | 56.7 | 54.7 | 50.6 | 43.1 | 34.3 | 24.4 | 14.7 |
| GTAN | CVPR-2019 | 69.1 | 63.7 | 57.8 | 47.2 | 38.8 | - | - |
| BMN | ICCV-2019 | - | - | 56.0 | 47.4 | 38.8 | 29.7 | 20.5 |
| TAL-Net | CVPR-2018 | 59.8 | 57.1 | 53.2 | 48.5 | 42.8 | 33.8 | 20.8 |
| RAM | TMM-2019 | 65.4 | 63.1 | 58.8 | 52.7 | 43.7 | - | - |
| PGCN | ICCV-2019 | 69.5 | 67.8 | 63.6 | 57.8 | 49.1 | - | - |
| Method | Conference | IoU@0.1 | IoU@0.2 | IoU@0.3 | IoU@0.4 | IoU@0.5 | IoU@0.6 | IoU@0.7 |
|---|---|---|---|---|---|---|---|---|
| C-TCN | arXiv | 72.2 | 71.4 | 68.0 | 62.3 | 52.1 | - | - |
| G-TAD | arXiv | - | - | 54.5 | 47.6 | 40.2 | 30.8 | 23.4 |
| Method | Conference | IoU@0.5 | IoU@0.75 | IoU@0.95 | IoU@Avg |
|---|---|---|---|---|---|
| CDC | CVPR-2017 | 45.3 | 26.0 | 0.2 | 23.8 |
| SCC | CVPR-2017 | 39.9 | 18.7 | 4.7 | 19.3 |
| SSN | ICCV-2017 | 43.26 | 28.70 | 5.63 | 28.28 |
| R-C3D | ICCV-2017 | 26.8 | - | - | - |
| TCN | ICCV-2017 | 37.49 | 23.47 | 4.47 | 23.58 |
| TAL-Net | CVPR-2018 | 38.23 | 18.30 | 1.30 | 20.22 |
| BSN | ECCV-2018 | 46.45 | 29.96 | 8.02 | 30.03 |
| DBS | CVPR-2019 | 43.2 | 25.8 | 6.1 | 26.1 |
| RAM | TMM-2019 | 36.99 | 23.10 | 3.34 | 23.03 |
| PGCN | ICCV-2019 | 42.90 | 28.14 | 2.47 | 26.99 |
| BMN | ICCV-2019 | 50.07 | 34.78 | 8.29 | 33.85 |
| GTAN | CVPR-2019 | 52.61 | 34.14 | 8.91 | 34.31 |
| Method | Conference | IoU@0.5 | IoU@0.75 | IoU@0.95 | IoU@Avg |
|---|---|---|---|---|---|
| C-TCN | arXiv | 47.6 | 31.9 | 6.2 | 31.1 |
| G-TAD | arXiv | 50.36 | 34.60 | 9.02 | 34.09 |
- [IWO-Net] Breaking Winner-Takes-All: Iterative-Winners-Out Networks for Weakly Supervised Temporal Action Localization - Runhao Zeng et al,
TIP 2019. - [BM] Weakly-supervised Action Localization with Background Modeling - Phuc Xuan Nguyen et al,
ICCV 2019. - [TSM] Temporal Structure Mining for Weakly Supervised Action Detection - Tan Yu et al,
ICCV 2019. - [CleanNet] Weakly Supervised Temporal Action Localization through Contrast based Evaluation Networks - Ziyi Liu et al,
ICCV 2019. - [CMCS] Completeness Modeling and Context Separation for Weakly Supervised Temporal Action Localization - Daochang Liu et al,
CVPR 2019. - [STAR] Segregated Temporal Assembly Recurrent Networks for Weakly Supervised Multiple Action Detection - Yunlu Xu et al,
AAAI 2019.
- [One-Shot] One-Shot Action Localization by Learning Sequence Matching Network - Hongtao Yang et al,
CVPR 2018. - [STPN] Weakly Supervised Action Localization by Sparse Temporal Pooling Network - Phuc Nguyen et al,
CVPR 2018. - [AutoLoc] AutoLoc: Weakly-supervised Temporal Action Localization in Untrimmed Videos - Zheng Shou et al,
ECCV 2018. [code] - [W-TALC] W-TALC: Weakly-supervised Temporal Activity Localization and Classification - Sujoy Paul et al,
ECCV 2018. [code]
- [UNet] UntrimmedNets for Weakly Supervised Action Recognition and Detection - Limin Wang et al,
CVPR 2017. [code] - [H&S] Hide-and-Seek: Forcing a Network to be Meticulous for Weakly-supervised Object and Action Localization - Krishna Kumar Singh et al,
CVPR 2017.
| Method | Conference | IoU@0.1 | IoU@0.2 | IoU@0.3 | IoU@0.4 | IoU@0.5 | IoU@0.6 | IoU@0.7 |
|---|---|---|---|---|---|---|---|---|
| UNet | CVPR-2017 | 44.4 | 37.7 | 28.2 | 21.1 | 13.7 | - | - |
| H&S | ICCV-2017 | 36.44 | 27.84 | 19.49 | 12.66 | 6.84 | - | - |
| One-Shot | CVPR-2018 | - | - | - | - | 14.7 | - | - |
| STPN | CVPR-2018 | 52.0 | 44.7 | 35.5 | 25.8 | 16.9 | 9.9 | 4.3 |
| AutoLoc | ECCV-2018 | - | - | 35.8 | 29.0 | 21.2 | 13.4 | 5.8 |
| W-TAL | ECCV-2018 | 55.2 | 49.6 | 40.1 | 31.1 | 22.8 | - | 7.6 |
| CMCS | CVPR-2019 | 57.4 | 50.8 | 41.2 | 32.1 | 23.1 | 15.0 | 7.0 |
| STAR | AAAI-2019 | 68.8 | 60.0 | 48.7 | 34.7 | 23.0 | - | - |
| CleanNet | ICCV-2019 | 68.8 | 60.0 | 37.0 | 30.9 | 23.9 | 13.9 | 7.1 |
| TSM | ICCV-2019 | - | - | 39.5 | - | 24.5 | - | 7.1 |
| IWO-Net | TIP-2019 | 57.6 | 48.9 | 38.9 | 29.3 | 20.5 | - | - |
| BM | ICCV-2019 | 60.4 | 56.0 | 46.6 | 37.5 | 26.8 | 17.6 | 9.0 |
| Method | Conference | IoU@0.5 | IoU@0.75 | IoU@0.95 | IoU@Avg |
|---|---|---|---|---|---|
| STPN | CVPR-2018 | 29.3 | 16.9 | 2.6 | 20.07 |
| CMCS | CVPR-2019 | 34.0 | 20.9 | 5.7 | 21.2 |
| STAR | AAAI-2019 | 31.1 | 18.8 | 4.7 | - |
| BM | ICCV-2019 | 36.4 | 19.2 | 2.9 | - |
| TSM | ICCV-2019 | 30.3 | 19.0 | 4.5 | - |
| IWO-Net | TIP-2019 | 29.8 | 17.6 | 4.7 | - |
| Method | Conference | IoU@0.5 | IoU@0.75 | IoU@0.95 | IoU@Avg |
|---|---|---|---|---|---|
| UNet | CVPR-2017 | 7.4 | 3.2 | 0.7 | - |
| AutoLoc | ECCV-2018 | 27.3 | 15.1 | 3.3 | - |
| W-TALC | ECCV-2018 | 37.0 | - | - | 18.0 |
| CMCS | CVPR-2019 | 36.8 | 22.0 | 5.6 | 22.4 |
| STAR | AAAI-2019 | 31.1 | 18.8 | 4.7 | - |
| TSM | ICCV-2019 | 28.3 | 17.0 | 3.5 | - |
| CleanNet | ICCV-2019 | 37.1 | 20.3 | 5.0 | 21.6 |