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/CASE

CASE

Reported on 35 benchmarks across 6 tasks · 2 papers · 18 SOTA

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

Computer Vision29 results

VideoonActivityNet-1.3
mAP@0.5· 2023-12-21
43.2
best: 45.1 (PivoTAL)
SOTA
Revisiting Foreground and Background Separation in Weakly-supervised Temporal Action Localization: A Clustering-based Approach arXiv:2312.14138
VideoonActivityNet-1.3
mAP@0.5:0.95· 2023-12-21
26.8
best: 28.8 (SAL)
SOTA
Revisiting Foreground and Background Separation in Weakly-supervised Temporal Action Localization: A Clustering-based Approach arXiv:2312.14138
VideoonActivityNet-1.2
Mean mAP· 2023-12-21
27.9
best: 30.8 (SAL)
SOTA
Revisiting Foreground and Background Separation in Weakly-supervised Temporal Action Localization: A Clustering-based Approach arXiv:2312.14138
Temporal Action LocalizationonActivityNet-1.3
mAP@0.5· 2023-12-21
43.2
best: 45.1 (PivoTAL)
SOTA
Revisiting Foreground and Background Separation in Weakly-supervised Temporal Action Localization: A Clustering-based Approach arXiv:2312.14138
Temporal Action LocalizationonActivityNet-1.3
mAP@0.5:0.95· 2023-12-21
26.8
best: 28.8 (SAL)
SOTA
Revisiting Foreground and Background Separation in Weakly-supervised Temporal Action Localization: A Clustering-based Approach arXiv:2312.14138
Temporal Action LocalizationonActivityNet-1.2
Mean mAP· 2023-12-21
27.9
best: 30.8 (SAL)
SOTA
Revisiting Foreground and Background Separation in Weakly-supervised Temporal Action Localization: A Clustering-based Approach arXiv:2312.14138
Action LocalizationonActivityNet-1.3
mAP@0.5· 2023-12-21
43.2
best: 45.1 (PivoTAL)
SOTA
Revisiting Foreground and Background Separation in Weakly-supervised Temporal Action Localization: A Clustering-based Approach arXiv:2312.14138
Action LocalizationonActivityNet-1.3
mAP@0.5:0.95· 2023-12-21
26.8
best: 28.8 (SAL)
SOTA
Revisiting Foreground and Background Separation in Weakly-supervised Temporal Action Localization: A Clustering-based Approach arXiv:2312.14138
Action LocalizationonActivityNet-1.2
Mean mAP· 2023-12-21
27.9
best: 30.8 (SAL)
SOTA
Revisiting Foreground and Background Separation in Weakly-supervised Temporal Action Localization: A Clustering-based Approach arXiv:2312.14138
Weakly Supervised Action LocalizationonActivityNet-1.3
mAP@0.5· 2023-12-21
43.2
best: 45.1 (PivoTAL)
SOTA
Revisiting Foreground and Background Separation in Weakly-supervised Temporal Action Localization: A Clustering-based Approach arXiv:2312.14138
Weakly Supervised Action LocalizationonActivityNet-1.3
mAP@0.5:0.95· 2023-12-21
26.8
best: 28.8 (SAL)
SOTA
Revisiting Foreground and Background Separation in Weakly-supervised Temporal Action Localization: A Clustering-based Approach arXiv:2312.14138
Weakly Supervised Action LocalizationonActivityNet-1.2
Mean mAP· 2023-12-21
27.9
best: 30.8 (SAL)
SOTA
Revisiting Foreground and Background Separation in Weakly-supervised Temporal Action Localization: A Clustering-based Approach arXiv:2312.14138
Image RetrievalonLaSCo
Recall@1 (%)· 2023-03-16
7.08
SOTA
Data Roaming and Quality Assessment for Composed Image Retrieval arXiv:2303.09429
Image RetrievalonFashion IQ
(Recall@10+Recall@50)/2· 2023-03-16
59.73
best: 71.77 (DQU-CIR)
SOTA
Data Roaming and Quality Assessment for Composed Image Retrieval arXiv:2303.09429
Image RetrievalonFashion IQ
Recall@10· 2023-03-16
48.79
best: 61.97 (DQU-CIR)
SOTA
Data Roaming and Quality Assessment for Composed Image Retrieval arXiv:2303.09429
VideoonTHUMOS 2014
mAP@0.1:0.5· 2023-12-21
57.1
best: 71.6 (HR-Pro)
Revisiting Foreground and Background Separation in Weakly-supervised Temporal Action Localization: A Clustering-based Approach arXiv:2312.14138
VideoonTHUMOS 2014
mAP@0.1:0.7· 2023-12-21
46.2
best: 60.3 (HR-Pro)
Revisiting Foreground and Background Separation in Weakly-supervised Temporal Action Localization: A Clustering-based Approach arXiv:2312.14138
VideoonActivityNet-1.2
mAP@0.5· 2023-12-21
43.8
best: 49.6 (AICL)
Revisiting Foreground and Background Separation in Weakly-supervised Temporal Action Localization: A Clustering-based Approach arXiv:2312.14138
Temporal Action LocalizationonTHUMOS 2014
mAP@0.1:0.5· 2023-12-21
57.1
best: 71.6 (HR-Pro)
Revisiting Foreground and Background Separation in Weakly-supervised Temporal Action Localization: A Clustering-based Approach arXiv:2312.14138
Temporal Action LocalizationonTHUMOS 2014
mAP@0.1:0.7· 2023-12-21
46.2
best: 60.3 (HR-Pro)
Revisiting Foreground and Background Separation in Weakly-supervised Temporal Action Localization: A Clustering-based Approach arXiv:2312.14138
Temporal Action LocalizationonActivityNet-1.2
mAP@0.5· 2023-12-21
43.8
best: 49.6 (AICL)
Revisiting Foreground and Background Separation in Weakly-supervised Temporal Action Localization: A Clustering-based Approach arXiv:2312.14138
Action LocalizationonTHUMOS 2014
mAP@0.1:0.5· 2023-12-21
57.1
best: 71.6 (HR-Pro)
Revisiting Foreground and Background Separation in Weakly-supervised Temporal Action Localization: A Clustering-based Approach arXiv:2312.14138
Action LocalizationonTHUMOS 2014
mAP@0.1:0.7· 2023-12-21
46.2
best: 60.3 (HR-Pro)
Revisiting Foreground and Background Separation in Weakly-supervised Temporal Action Localization: A Clustering-based Approach arXiv:2312.14138
Action LocalizationonActivityNet-1.2
mAP@0.5· 2023-12-21
43.8
best: 49.6 (AICL)
Revisiting Foreground and Background Separation in Weakly-supervised Temporal Action Localization: A Clustering-based Approach arXiv:2312.14138
Weakly Supervised Action LocalizationonTHUMOS 2014
mAP@0.1:0.5· 2023-12-21
57.1
best: 71.6 (HR-Pro)
Revisiting Foreground and Background Separation in Weakly-supervised Temporal Action Localization: A Clustering-based Approach arXiv:2312.14138
Weakly Supervised Action LocalizationonTHUMOS 2014
mAP@0.1:0.7· 2023-12-21
46.2
best: 60.3 (HR-Pro)
Revisiting Foreground and Background Separation in Weakly-supervised Temporal Action Localization: A Clustering-based Approach arXiv:2312.14138
Weakly Supervised Action LocalizationonActivityNet-1.2
mAP@0.5· 2023-12-21
43.8
best: 49.6 (AICL)
Revisiting Foreground and Background Separation in Weakly-supervised Temporal Action Localization: A Clustering-based Approach arXiv:2312.14138
Image RetrievalonCIRR
(Recall@5+Recall_subset@1)/2· 2023-03-16
77.5
best: 83.46 (TMCIR)
Data Roaming and Quality Assessment for Composed Image Retrieval arXiv:2303.09429
Image RetrievalonCIRR
Recall@10· 2023-03-16
87.25
best: 91.06 (TMCIR)
Data Roaming and Quality Assessment for Composed Image Retrieval arXiv:2303.09429

Methodology6 results

Zero-Shot LearningonActivityNet-1.3
mAP@0.5· 2023-12-21
43.2
best: 45.1 (PivoTAL)
SOTA
Revisiting Foreground and Background Separation in Weakly-supervised Temporal Action Localization: A Clustering-based Approach arXiv:2312.14138
Zero-Shot LearningonActivityNet-1.3
mAP@0.5:0.95· 2023-12-21
26.8
best: 28.8 (SAL)
SOTA
Revisiting Foreground and Background Separation in Weakly-supervised Temporal Action Localization: A Clustering-based Approach arXiv:2312.14138
Zero-Shot LearningonActivityNet-1.2
Mean mAP· 2023-12-21
27.9
best: 30.8 (SAL)
SOTA
Revisiting Foreground and Background Separation in Weakly-supervised Temporal Action Localization: A Clustering-based Approach arXiv:2312.14138
Zero-Shot LearningonTHUMOS 2014
mAP@0.1:0.5· 2023-12-21
57.1
best: 71.6 (HR-Pro)
Revisiting Foreground and Background Separation in Weakly-supervised Temporal Action Localization: A Clustering-based Approach arXiv:2312.14138
Zero-Shot LearningonTHUMOS 2014
mAP@0.1:0.7· 2023-12-21
46.2
best: 60.3 (HR-Pro)
Revisiting Foreground and Background Separation in Weakly-supervised Temporal Action Localization: A Clustering-based Approach arXiv:2312.14138
Zero-Shot LearningonActivityNet-1.2
mAP@0.5· 2023-12-21
43.8
best: 49.6 (AICL)
Revisiting Foreground and Background Separation in Weakly-supervised Temporal Action Localization: A Clustering-based Approach arXiv:2312.14138