Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/TSP

TSP

Reported on 62 benchmarks across 6 tasks · 1 paper · 51 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision48 results

VideoonActivityNet-1.3
mAP· 2020-11-23
35.81
best: 42.9 (RDFA-S6 (InternVideo2-6B))
SOTA
TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks arXiv:2011.11479
VideoonActivityNet-1.3
mAP IOU@0.75· 2020-11-23
37.12
best: 44 (RDFA-S6 (InternVideo2-6B))
SOTA
TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks arXiv:2011.11479
VideoonTHUMOS’14
Avg mAP (0.3:0.7)· 2020-11-23
50.46
best: 76.9 (AdaTAD (VideoMAEv2-giant))
SOTA
TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks arXiv:2011.11479
VideoonTHUMOS’14
mAP IOU@0.1· 2020-11-23
74.02
SOTA
TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks arXiv:2011.11479
VideoonTHUMOS’14
mAP IOU@0.2· 2020-11-23
72.29
SOTA
TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks arXiv:2011.11479
VideoonTHUMOS’14
mAP IOU@0.3· 2020-11-23
69.1
best: 89.7 (AdaTAD (VideoMAEv2-giant))
SOTA
TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks arXiv:2011.11479
VideoonTHUMOS’14
mAP IOU@0.4· 2020-11-23
63.3
best: 86.7 (AdaTAD (VideoMAEv2-giant))
SOTA
TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks arXiv:2011.11479
VideoonTHUMOS’14
mAP IOU@0.5· 2020-11-23
53.5
best: 80.9 (AdaTAD (VideoMAEv2-giant))
SOTA
TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks arXiv:2011.11479
VideoonTHUMOS’14
mAP IOU@0.6· 2020-11-23
40.4
best: 71 (AdaTAD (VideoMAEv2-giant))
SOTA
TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks arXiv:2011.11479
VideoonTHUMOS’14
mAP IOU@0.7· 2020-11-23
26
best: 56.1 (AdaTAD (VideoMAEv2-giant))
SOTA
TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks arXiv:2011.11479
VideoonActivityNet-1.3
AR@100· 2020-11-23
76.63
best: 77.67 (AOE-Net)
SOTA
TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks arXiv:2011.11479
VideoonActivityNet-1.3
AUC (val)· 2020-11-23
69.04
best: 69.71 (AOE-Net)
SOTA
TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks arXiv:2011.11479
Temporal Action LocalizationonActivityNet-1.3
mAP· 2020-11-23
35.81
best: 42.9 (RDFA-S6 (InternVideo2-6B))
SOTA
TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks arXiv:2011.11479
Temporal Action LocalizationonActivityNet-1.3
mAP IOU@0.75· 2020-11-23
37.12
best: 44 (RDFA-S6 (InternVideo2-6B))
SOTA
TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks arXiv:2011.11479
Temporal Action LocalizationonTHUMOS’14
Avg mAP (0.3:0.7)· 2020-11-23
50.46
best: 76.9 (AdaTAD (VideoMAEv2-giant))
SOTA
TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks arXiv:2011.11479
Temporal Action LocalizationonTHUMOS’14
mAP IOU@0.1· 2020-11-23
74.02
SOTA
TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks arXiv:2011.11479
Temporal Action LocalizationonTHUMOS’14
mAP IOU@0.2· 2020-11-23
72.29
SOTA
TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks arXiv:2011.11479
Temporal Action LocalizationonTHUMOS’14
mAP IOU@0.3· 2020-11-23
69.1
best: 89.7 (AdaTAD (VideoMAEv2-giant))
SOTA
TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks arXiv:2011.11479
Temporal Action LocalizationonTHUMOS’14
mAP IOU@0.4· 2020-11-23
63.3
best: 86.7 (AdaTAD (VideoMAEv2-giant))
SOTA
TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks arXiv:2011.11479
Temporal Action LocalizationonTHUMOS’14
mAP IOU@0.5· 2020-11-23
53.5
best: 80.9 (AdaTAD (VideoMAEv2-giant))
SOTA
TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks arXiv:2011.11479
Temporal Action LocalizationonTHUMOS’14
mAP IOU@0.6· 2020-11-23
40.4
best: 71 (AdaTAD (VideoMAEv2-giant))
SOTA
TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks arXiv:2011.11479
Temporal Action LocalizationonTHUMOS’14
mAP IOU@0.7· 2020-11-23
26
best: 56.1 (AdaTAD (VideoMAEv2-giant))
SOTA
TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks arXiv:2011.11479
Temporal Action LocalizationonActivityNet-1.3
AR@100· 2020-11-23
76.63
best: 77.67 (AOE-Net)
SOTA
TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks arXiv:2011.11479
Temporal Action LocalizationonActivityNet-1.3
AUC (val)· 2020-11-23
69.04
best: 69.71 (AOE-Net)
SOTA
TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks arXiv:2011.11479
Action LocalizationonActivityNet-1.3
mAP· 2020-11-23
35.81
best: 42.9 (RDFA-S6 (InternVideo2-6B))
SOTA
TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks arXiv:2011.11479
Action LocalizationonActivityNet-1.3
mAP IOU@0.75· 2020-11-23
37.12
best: 44 (RDFA-S6 (InternVideo2-6B))
SOTA
TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks arXiv:2011.11479
Action LocalizationonTHUMOS’14
Avg mAP (0.3:0.7)· 2020-11-23
50.46
best: 76.9 (AdaTAD (VideoMAEv2-giant))
SOTA
TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks arXiv:2011.11479
Action LocalizationonTHUMOS’14
mAP IOU@0.1· 2020-11-23
74.02
SOTA
TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks arXiv:2011.11479
Action LocalizationonTHUMOS’14
mAP IOU@0.2· 2020-11-23
72.29
SOTA
TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks arXiv:2011.11479
Action LocalizationonTHUMOS’14
mAP IOU@0.3· 2020-11-23
69.1
best: 89.7 (AdaTAD (VideoMAEv2-giant))
SOTA
TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks arXiv:2011.11479
Action LocalizationonTHUMOS’14
mAP IOU@0.4· 2020-11-23
63.3
best: 86.7 (AdaTAD (VideoMAEv2-giant))
SOTA
TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks arXiv:2011.11479
Action LocalizationonTHUMOS’14
mAP IOU@0.5· 2020-11-23
53.5
best: 80.9 (AdaTAD (VideoMAEv2-giant))
SOTA
TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks arXiv:2011.11479
Action LocalizationonTHUMOS’14
mAP IOU@0.6· 2020-11-23
40.4
best: 71 (AdaTAD (VideoMAEv2-giant))
SOTA
TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks arXiv:2011.11479
Action LocalizationonTHUMOS’14
mAP IOU@0.7· 2020-11-23
26
best: 56.1 (AdaTAD (VideoMAEv2-giant))
SOTA
TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks arXiv:2011.11479
Action LocalizationonActivityNet-1.3
AR@100· 2020-11-23
76.63
best: 77.67 (AOE-Net)
SOTA
TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks arXiv:2011.11479
Action LocalizationonActivityNet-1.3
AUC (val)· 2020-11-23
69.04
best: 69.71 (AOE-Net)
SOTA
TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks arXiv:2011.11479
Video CaptioningonActivityNet Captions
BLEU-4· 2020-11-23
2.02
best: 9.45 (ADV-INF + Global)
SOTA
TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks arXiv:2011.11479
Dense Video CaptioningonActivityNet Captions
BLEU-3· 2020-11-23
4.16
SOTA
TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks arXiv:2011.11479
Dense Video CaptioningonActivityNet Captions
BLEU-4· 2020-11-23
2.02
best: 9.45 (ADV-INF + Global)
SOTA
TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks arXiv:2011.11479
VideoonActivityNet-1.3
mAP IOU@0.5· 2020-11-23
51.26
best: 64.1 (RDFA-S6 (InternVideo2-6B))
TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks arXiv:2011.11479
VideoonActivityNet-1.3
mAP IOU@0.95· 2020-11-23
9.29
best: 10.85 (AdaTAD (VideoMAEv2-giant))
TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks arXiv:2011.11479
Temporal Action LocalizationonActivityNet-1.3
mAP IOU@0.5· 2020-11-23
51.26
best: 64.1 (RDFA-S6 (InternVideo2-6B))
TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks arXiv:2011.11479
Temporal Action LocalizationonActivityNet-1.3
mAP IOU@0.95· 2020-11-23
9.29
best: 10.85 (AdaTAD (VideoMAEv2-giant))
TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks arXiv:2011.11479
Action LocalizationonActivityNet-1.3
mAP IOU@0.5· 2020-11-23
51.26
best: 64.1 (RDFA-S6 (InternVideo2-6B))
TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks arXiv:2011.11479
Action LocalizationonActivityNet-1.3
mAP IOU@0.95· 2020-11-23
9.29
best: 10.85 (AdaTAD (VideoMAEv2-giant))
TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks arXiv:2011.11479
Video CaptioningonActivityNet Captions
BLEU-3· 2020-11-23
4.16
best: 17.43 (COOT (ae-test split) - Only Appearance features)
TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks arXiv:2011.11479
Video CaptioningonActivityNet Captions
METEOR· 2020-11-23
8.75
best: 17.97 (VLTinT (ae-test split) C3D/Ling)
TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks arXiv:2011.11479
Dense Video CaptioningonActivityNet Captions
METEOR· 2020-11-23
8.75
best: 17 (Vid2Seq)
TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks arXiv:2011.11479

Methodology14 results

Zero-Shot LearningonActivityNet-1.3
mAP· 2020-11-23
35.81
best: 42.9 (RDFA-S6 (InternVideo2-6B))
SOTA
TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks arXiv:2011.11479
Zero-Shot LearningonActivityNet-1.3
mAP IOU@0.75· 2020-11-23
37.12
best: 44 (RDFA-S6 (InternVideo2-6B))
SOTA
TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks arXiv:2011.11479
Zero-Shot LearningonTHUMOS’14
Avg mAP (0.3:0.7)· 2020-11-23
50.46
best: 76.9 (AdaTAD (VideoMAEv2-giant))
SOTA
TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks arXiv:2011.11479
Zero-Shot LearningonTHUMOS’14
mAP IOU@0.1· 2020-11-23
74.02
SOTA
TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks arXiv:2011.11479
Zero-Shot LearningonTHUMOS’14
mAP IOU@0.2· 2020-11-23
72.29
SOTA
TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks arXiv:2011.11479
Zero-Shot LearningonTHUMOS’14
mAP IOU@0.3· 2020-11-23
69.1
best: 89.7 (AdaTAD (VideoMAEv2-giant))
SOTA
TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks arXiv:2011.11479
Zero-Shot LearningonTHUMOS’14
mAP IOU@0.4· 2020-11-23
63.3
best: 86.7 (AdaTAD (VideoMAEv2-giant))
SOTA
TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks arXiv:2011.11479
Zero-Shot LearningonTHUMOS’14
mAP IOU@0.5· 2020-11-23
53.5
best: 80.9 (AdaTAD (VideoMAEv2-giant))
SOTA
TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks arXiv:2011.11479
Zero-Shot LearningonTHUMOS’14
mAP IOU@0.6· 2020-11-23
40.4
best: 71 (AdaTAD (VideoMAEv2-giant))
SOTA
TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks arXiv:2011.11479
Zero-Shot LearningonTHUMOS’14
mAP IOU@0.7· 2020-11-23
26
best: 56.1 (AdaTAD (VideoMAEv2-giant))
SOTA
TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks arXiv:2011.11479
Zero-Shot LearningonActivityNet-1.3
AR@100· 2020-11-23
76.63
best: 77.67 (AOE-Net)
SOTA
TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks arXiv:2011.11479
Zero-Shot LearningonActivityNet-1.3
AUC (val)· 2020-11-23
69.04
best: 69.71 (AOE-Net)
SOTA
TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks arXiv:2011.11479
Zero-Shot LearningonActivityNet-1.3
mAP IOU@0.5· 2020-11-23
51.26
best: 64.1 (RDFA-S6 (InternVideo2-6B))
TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks arXiv:2011.11479
Zero-Shot LearningonActivityNet-1.3
mAP IOU@0.95· 2020-11-23
9.29
best: 10.85 (AdaTAD (VideoMAEv2-giant))
TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks arXiv:2011.11479