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/Ju et al.

Ju et al.

Reported on 55 benchmarks across 5 tasks · 1 paper · 45 SOTA

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

Computer Vision44 results

VideoonGTEA
mAP@0.1:0.7· 2020-12-15
33.7
best: 76.9 (AU-Action)
SOTA
Point-Level Temporal Action Localization: Bridging Fully-supervised Proposals to Weakly-supervised Losses arXiv:2012.08236
VideoonGTEA
mAP@0.5· 2020-12-15
21.9
best: 66.3 (AU-Action)
SOTA
Point-Level Temporal Action Localization: Bridging Fully-supervised Proposals to Weakly-supervised Losses arXiv:2012.08236
VideoonBEOID
mAP@0.1:0.7· 2020-12-15
34.9
best: 59.4 (HR-Pro)
SOTA
Point-Level Temporal Action Localization: Bridging Fully-supervised Proposals to Weakly-supervised Losses arXiv:2012.08236
VideoonBEOID
mAP@0.5· 2020-12-15
20.9
best: 55.3 (HR-Pro)
SOTA
Point-Level Temporal Action Localization: Bridging Fully-supervised Proposals to Weakly-supervised Losses arXiv:2012.08236
VideoonTHUMOS 2014
mAP@0.1:0.5· uses extra data· 2020-12-15
55.6
best: 71.6 (HR-Pro)
SOTA
Point-Level Temporal Action Localization: Bridging Fully-supervised Proposals to Weakly-supervised Losses arXiv:2012.08236
VideoonTHUMOS 2014
mAP@0.1:0.7· uses extra data· 2020-12-15
44.8
best: 60.3 (HR-Pro)
SOTA
Point-Level Temporal Action Localization: Bridging Fully-supervised Proposals to Weakly-supervised Losses arXiv:2012.08236
VideoonTHUMOS14
avg-mAP (0.1-0.5)· uses extra data· 2020-12-15
55.6
best: 71.6 (HR-Pro)
SOTA
Point-Level Temporal Action Localization: Bridging Fully-supervised Proposals to Weakly-supervised Losses arXiv:2012.08236
VideoonTHUMOS14
avg-mAP (0.1:0.7)· uses extra data· 2020-12-15
44.8
best: 60.3 (HR-Pro)
SOTA
Point-Level Temporal Action Localization: Bridging Fully-supervised Proposals to Weakly-supervised Losses arXiv:2012.08236
VideoonTHUMOS14
avg-mAP (0.3-0.7)· uses extra data· 2020-12-15
35.4
best: 51.1 (HR-Pro)
SOTA
Point-Level Temporal Action Localization: Bridging Fully-supervised Proposals to Weakly-supervised Losses arXiv:2012.08236
Temporal Action LocalizationonGTEA
mAP@0.1:0.7· 2020-12-15
33.7
best: 76.9 (AU-Action)
SOTA
Point-Level Temporal Action Localization: Bridging Fully-supervised Proposals to Weakly-supervised Losses arXiv:2012.08236
Temporal Action LocalizationonGTEA
mAP@0.5· 2020-12-15
21.9
best: 66.3 (AU-Action)
SOTA
Point-Level Temporal Action Localization: Bridging Fully-supervised Proposals to Weakly-supervised Losses arXiv:2012.08236
Temporal Action LocalizationonBEOID
mAP@0.1:0.7· 2020-12-15
34.9
best: 59.4 (HR-Pro)
SOTA
Point-Level Temporal Action Localization: Bridging Fully-supervised Proposals to Weakly-supervised Losses arXiv:2012.08236
Temporal Action LocalizationonBEOID
mAP@0.5· 2020-12-15
20.9
best: 55.3 (HR-Pro)
SOTA
Point-Level Temporal Action Localization: Bridging Fully-supervised Proposals to Weakly-supervised Losses arXiv:2012.08236
Temporal Action LocalizationonTHUMOS 2014
mAP@0.1:0.5· uses extra data· 2020-12-15
55.6
best: 71.6 (HR-Pro)
SOTA
Point-Level Temporal Action Localization: Bridging Fully-supervised Proposals to Weakly-supervised Losses arXiv:2012.08236
Temporal Action LocalizationonTHUMOS 2014
mAP@0.1:0.7· uses extra data· 2020-12-15
44.8
best: 60.3 (HR-Pro)
SOTA
Point-Level Temporal Action Localization: Bridging Fully-supervised Proposals to Weakly-supervised Losses arXiv:2012.08236
Temporal Action LocalizationonTHUMOS14
avg-mAP (0.1-0.5)· uses extra data· 2020-12-15
55.6
best: 71.6 (HR-Pro)
SOTA
Point-Level Temporal Action Localization: Bridging Fully-supervised Proposals to Weakly-supervised Losses arXiv:2012.08236
Temporal Action LocalizationonTHUMOS14
avg-mAP (0.1:0.7)· uses extra data· 2020-12-15
44.8
best: 60.3 (HR-Pro)
SOTA
Point-Level Temporal Action Localization: Bridging Fully-supervised Proposals to Weakly-supervised Losses arXiv:2012.08236
Temporal Action LocalizationonTHUMOS14
avg-mAP (0.3-0.7)· uses extra data· 2020-12-15
35.4
best: 51.1 (HR-Pro)
SOTA
Point-Level Temporal Action Localization: Bridging Fully-supervised Proposals to Weakly-supervised Losses arXiv:2012.08236
Action LocalizationonGTEA
mAP@0.1:0.7· 2020-12-15
33.7
best: 76.9 (AU-Action)
SOTA
Point-Level Temporal Action Localization: Bridging Fully-supervised Proposals to Weakly-supervised Losses arXiv:2012.08236
Action LocalizationonGTEA
mAP@0.5· 2020-12-15
21.9
best: 66.3 (AU-Action)
SOTA
Point-Level Temporal Action Localization: Bridging Fully-supervised Proposals to Weakly-supervised Losses arXiv:2012.08236
Action LocalizationonBEOID
mAP@0.1:0.7· 2020-12-15
34.9
best: 59.4 (HR-Pro)
SOTA
Point-Level Temporal Action Localization: Bridging Fully-supervised Proposals to Weakly-supervised Losses arXiv:2012.08236
Action LocalizationonBEOID
mAP@0.5· 2020-12-15
20.9
best: 55.3 (HR-Pro)
SOTA
Point-Level Temporal Action Localization: Bridging Fully-supervised Proposals to Weakly-supervised Losses arXiv:2012.08236
Action LocalizationonTHUMOS 2014
mAP@0.1:0.5· uses extra data· 2020-12-15
55.6
best: 71.6 (HR-Pro)
SOTA
Point-Level Temporal Action Localization: Bridging Fully-supervised Proposals to Weakly-supervised Losses arXiv:2012.08236
Action LocalizationonTHUMOS 2014
mAP@0.1:0.7· uses extra data· 2020-12-15
44.8
best: 60.3 (HR-Pro)
SOTA
Point-Level Temporal Action Localization: Bridging Fully-supervised Proposals to Weakly-supervised Losses arXiv:2012.08236
Action LocalizationonTHUMOS14
avg-mAP (0.1-0.5)· uses extra data· 2020-12-15
55.6
best: 71.6 (HR-Pro)
SOTA
Point-Level Temporal Action Localization: Bridging Fully-supervised Proposals to Weakly-supervised Losses arXiv:2012.08236
Action LocalizationonTHUMOS14
avg-mAP (0.1:0.7)· uses extra data· 2020-12-15
44.8
best: 60.3 (HR-Pro)
SOTA
Point-Level Temporal Action Localization: Bridging Fully-supervised Proposals to Weakly-supervised Losses arXiv:2012.08236
Action LocalizationonTHUMOS14
avg-mAP (0.3-0.7)· uses extra data· 2020-12-15
35.4
best: 51.1 (HR-Pro)
SOTA
Point-Level Temporal Action Localization: Bridging Fully-supervised Proposals to Weakly-supervised Losses arXiv:2012.08236
Weakly Supervised Action LocalizationonGTEA
mAP@0.1:0.7· 2020-12-15
33.7
best: 76.9 (AU-Action)
SOTA
Point-Level Temporal Action Localization: Bridging Fully-supervised Proposals to Weakly-supervised Losses arXiv:2012.08236
Weakly Supervised Action LocalizationonGTEA
mAP@0.5· 2020-12-15
21.9
best: 66.3 (AU-Action)
SOTA
Point-Level Temporal Action Localization: Bridging Fully-supervised Proposals to Weakly-supervised Losses arXiv:2012.08236
Weakly Supervised Action LocalizationonBEOID
mAP@0.1:0.7· 2020-12-15
34.9
best: 59.4 (HR-Pro)
SOTA
Point-Level Temporal Action Localization: Bridging Fully-supervised Proposals to Weakly-supervised Losses arXiv:2012.08236
Weakly Supervised Action LocalizationonBEOID
mAP@0.5· 2020-12-15
20.9
best: 55.3 (HR-Pro)
SOTA
Point-Level Temporal Action Localization: Bridging Fully-supervised Proposals to Weakly-supervised Losses arXiv:2012.08236
Weakly Supervised Action LocalizationonTHUMOS 2014
mAP@0.1:0.5· uses extra data· 2020-12-15
55.6
best: 71.6 (HR-Pro)
SOTA
Point-Level Temporal Action Localization: Bridging Fully-supervised Proposals to Weakly-supervised Losses arXiv:2012.08236
Weakly Supervised Action LocalizationonTHUMOS 2014
mAP@0.1:0.7· uses extra data· 2020-12-15
44.8
best: 60.3 (HR-Pro)
SOTA
Point-Level Temporal Action Localization: Bridging Fully-supervised Proposals to Weakly-supervised Losses arXiv:2012.08236
Weakly Supervised Action LocalizationonTHUMOS14
avg-mAP (0.1-0.5)· uses extra data· 2020-12-15
55.6
best: 71.6 (HR-Pro)
SOTA
Point-Level Temporal Action Localization: Bridging Fully-supervised Proposals to Weakly-supervised Losses arXiv:2012.08236
Weakly Supervised Action LocalizationonTHUMOS14
avg-mAP (0.1:0.7)· uses extra data· 2020-12-15
44.8
best: 60.3 (HR-Pro)
SOTA
Point-Level Temporal Action Localization: Bridging Fully-supervised Proposals to Weakly-supervised Losses arXiv:2012.08236
Weakly Supervised Action LocalizationonTHUMOS14
avg-mAP (0.3-0.7)· uses extra data· 2020-12-15
35.4
best: 51.1 (HR-Pro)
SOTA
Point-Level Temporal Action Localization: Bridging Fully-supervised Proposals to Weakly-supervised Losses arXiv:2012.08236
VideoonTHUMOS 2014
mAP@0.5· uses extra data· 2020-12-15
35.9
best: 52.2 (HR-Pro)
Point-Level Temporal Action Localization: Bridging Fully-supervised Proposals to Weakly-supervised Losses arXiv:2012.08236
VideoonTHUMOS’14
mAP@0.5· 2020-12-15
35.9
best: 45.3 (LACP)
Point-Level Temporal Action Localization: Bridging Fully-supervised Proposals to Weakly-supervised Losses arXiv:2012.08236
Temporal Action LocalizationonTHUMOS 2014
mAP@0.5· uses extra data· 2020-12-15
35.9
best: 52.2 (HR-Pro)
Point-Level Temporal Action Localization: Bridging Fully-supervised Proposals to Weakly-supervised Losses arXiv:2012.08236
Temporal Action LocalizationonTHUMOS’14
mAP@0.5· 2020-12-15
35.9
best: 45.3 (LACP)
Point-Level Temporal Action Localization: Bridging Fully-supervised Proposals to Weakly-supervised Losses arXiv:2012.08236
Action LocalizationonTHUMOS 2014
mAP@0.5· uses extra data· 2020-12-15
35.9
best: 52.2 (HR-Pro)
Point-Level Temporal Action Localization: Bridging Fully-supervised Proposals to Weakly-supervised Losses arXiv:2012.08236
Action LocalizationonTHUMOS’14
mAP@0.5· 2020-12-15
35.9
best: 45.3 (LACP)
Point-Level Temporal Action Localization: Bridging Fully-supervised Proposals to Weakly-supervised Losses arXiv:2012.08236
Weakly Supervised Action LocalizationonTHUMOS 2014
mAP@0.5· uses extra data· 2020-12-15
35.9
best: 52.2 (HR-Pro)
Point-Level Temporal Action Localization: Bridging Fully-supervised Proposals to Weakly-supervised Losses arXiv:2012.08236
Weakly Supervised Action LocalizationonTHUMOS’14
mAP@0.5· 2020-12-15
35.9
best: 45.3 (LACP)
Point-Level Temporal Action Localization: Bridging Fully-supervised Proposals to Weakly-supervised Losses arXiv:2012.08236

Methodology11 results

Zero-Shot LearningonGTEA
mAP@0.1:0.7· 2020-12-15
33.7
best: 76.9 (AU-Action)
SOTA
Point-Level Temporal Action Localization: Bridging Fully-supervised Proposals to Weakly-supervised Losses arXiv:2012.08236
Zero-Shot LearningonGTEA
mAP@0.5· 2020-12-15
21.9
best: 66.3 (AU-Action)
SOTA
Point-Level Temporal Action Localization: Bridging Fully-supervised Proposals to Weakly-supervised Losses arXiv:2012.08236
Zero-Shot LearningonBEOID
mAP@0.1:0.7· 2020-12-15
34.9
best: 59.4 (HR-Pro)
SOTA
Point-Level Temporal Action Localization: Bridging Fully-supervised Proposals to Weakly-supervised Losses arXiv:2012.08236
Zero-Shot LearningonBEOID
mAP@0.5· 2020-12-15
20.9
best: 55.3 (HR-Pro)
SOTA
Point-Level Temporal Action Localization: Bridging Fully-supervised Proposals to Weakly-supervised Losses arXiv:2012.08236
Zero-Shot LearningonTHUMOS 2014
mAP@0.1:0.5· uses extra data· 2020-12-15
55.6
best: 71.6 (HR-Pro)
SOTA
Point-Level Temporal Action Localization: Bridging Fully-supervised Proposals to Weakly-supervised Losses arXiv:2012.08236
Zero-Shot LearningonTHUMOS 2014
mAP@0.1:0.7· uses extra data· 2020-12-15
44.8
best: 60.3 (HR-Pro)
SOTA
Point-Level Temporal Action Localization: Bridging Fully-supervised Proposals to Weakly-supervised Losses arXiv:2012.08236
Zero-Shot LearningonTHUMOS14
avg-mAP (0.1-0.5)· uses extra data· 2020-12-15
55.6
best: 71.6 (HR-Pro)
SOTA
Point-Level Temporal Action Localization: Bridging Fully-supervised Proposals to Weakly-supervised Losses arXiv:2012.08236
Zero-Shot LearningonTHUMOS14
avg-mAP (0.1:0.7)· uses extra data· 2020-12-15
44.8
best: 60.3 (HR-Pro)
SOTA
Point-Level Temporal Action Localization: Bridging Fully-supervised Proposals to Weakly-supervised Losses arXiv:2012.08236
Zero-Shot LearningonTHUMOS14
avg-mAP (0.3-0.7)· uses extra data· 2020-12-15
35.4
best: 51.1 (HR-Pro)
SOTA
Point-Level Temporal Action Localization: Bridging Fully-supervised Proposals to Weakly-supervised Losses arXiv:2012.08236
Zero-Shot LearningonTHUMOS 2014
mAP@0.5· uses extra data· 2020-12-15
35.9
best: 52.2 (HR-Pro)
Point-Level Temporal Action Localization: Bridging Fully-supervised Proposals to Weakly-supervised Losses arXiv:2012.08236
Zero-Shot LearningonTHUMOS’14
mAP@0.5· 2020-12-15
35.9
best: 45.3 (LACP)
Point-Level Temporal Action Localization: Bridging Fully-supervised Proposals to Weakly-supervised Losses arXiv:2012.08236