SOTAVerified

Weakly Supervised Action Localization

In this task, the training data consists of videos with a list of activities in them without any temporal boundary annotations. However, while testing, given a video, the algorithm should recognize the activities in the video and also provide the start and end time.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–50 of 55 papers

TitleStatusHype
Is Weakly-supervised Action Segmentation Ready For Human-Robot Interaction? No, Let's Improve It With Action-union LearningCode2
HR-Pro: Point-supervised Temporal Action Localization via Hierarchical Reliability PropagationCode1
Learning Action Completeness from Points for Weakly-supervised Temporal Action LocalizationCode1
Recognition of Instrument-Tissue Interactions in Endoscopic Videos via Action TripletsCode1
Weakly-Supervised Action Localization by Generative Attention ModelingCode1
Proposal-Based Multiple Instance Learning for Weakly-Supervised Temporal Action LocalizationCode1
VideoMix: Rethinking Data Augmentation for Video ClassificationCode1
Temporal Action Segmentation from Timestamp SupervisionCode1
Adversarial Background-Aware Loss for Weakly-supervised Temporal Activity LocalizationCode1
SF-Net: Single-Frame Supervision for Temporal Action LocalizationCode1
Weakly-supervised Temporal Action Localization by Uncertainty ModelingCode1
Background Suppression Network for Weakly-supervised Temporal Action LocalizationCode1
CoLA: Weakly-Supervised Temporal Action Localization with Snippet Contrastive LearningCode1
ACM-Net: Action Context Modeling Network for Weakly-Supervised Temporal Action LocalizationCode1
Convex Combination Consistency between Neighbors for Weakly-supervised Action LocalizationCode1
Revisiting Foreground and Background Separation in Weakly-supervised Temporal Action Localization: A Clustering-based ApproachCode1
Cross-modal Consensus Network for Weakly Supervised Temporal Action LocalizationCode1
Weakly-Supervised Temporal Action Detection for Fine-Grained Videos with Hierarchical Atomic ActionsCode1
FineAction: A Fine-Grained Video Dataset for Temporal Action LocalizationCode1
Fine-grained Temporal Contrastive Learning for Weakly-supervised Temporal Action LocalizationCode1
Actionness Inconsistency-guided Contrastive Learning for Weakly-supervised Temporal Action LocalizationCode1
Weakly Supervised Action Selection Learning in VideoCode1
W-TALC: Weakly-supervised Temporal Activity Localization and ClassificationCode0
3C-Net: Category Count and Center Loss for Weakly-Supervised Action LocalizationCode0
Completeness Modeling and Context Separation for Weakly Supervised Temporal Action LocalizationCode0
D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised ActivationsCode0
Guess Where? Actor-Supervision for Spatiotemporal Action LocalizationCode0
Hide-and-Seek: Forcing a Network to be Meticulous for Weakly-supervised Object and Action LocalizationCode0
Multilevel semantic and adaptive actionness learning for weakly supervised temporal action localizationCode0
RefineLoc: Iterative Refinement for Weakly-Supervised Action LocalizationCode0
UntrimmedNets for Weakly Supervised Action Recognition and DetectionCode0
Weakly Supervised Action Localization by Sparse Temporal Pooling NetworkCode0
Weakly-Supervised Temporal Action Localization by Progressive Complementary LearningCode0
Weakly-Supervised Action Localization with Expectation-Maximization Multi-Instance LearningCode0
Weakly supervised temporal action localization with actionness-guided false positive suppressionCode0
AutoLoc: Weakly-supervised Temporal Action Localization in Untrimmed Videos—0
Spatio-Temporal Instance Learning: Action Tubes from Class Supervision—0
Adaptive Mutual Supervision for Weakly-Supervised Temporal Action Localization—0
Temporal Structure Mining for Weakly Supervised Action Detection—0
Two-Stream Consensus Network for Weakly-Supervised Temporal Action Localization—0
Two-Stream Networks for Weakly-Supervised Temporal Action Localization With Semantic-Aware Mechanisms—0
Action Graphs: Weakly-supervised Action Localization with Graph Convolution Networks—0
Action Unit Memory Network for Weakly Supervised Temporal Action Localization—0
Weakly-Supervised Action Localization and Action Recognition using Global-Local Attention of 3D CNN—0
Weakly Supervised Temporal Action Localization Through Contrast Based Evaluation Networks—0
Weakly-Supervised Action Localization by Hierarchically-structured Latent Attention Modeling—0
Action Shuffling for Weakly Supervised Temporal Localization—0
0/1 Deep Neural Networks via Block Coordinate Descent—0
Weakly-supervised Action Localization with Background Modeling—0
Point-Level Temporal Action Localization: Bridging Fully-supervised Proposals to Weakly-supervised Losses—0
Show:102550
← PrevPage 1 of 2Next →
All datasetsTHUMOS 2014THUMOS14ActivityNet-1.2ActivityNet-1.3GTEABEOIDFineActionTHUMOS' 14

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1HR-Pro[email protected]:0.760.3—Unverified
2LACP[email protected]:0.752.8—Unverified
3D2-Net[email protected]:0.551.4—Unverified
4SAL[email protected]:0.750.6—Unverified
5PivoTAL[email protected]:0.749.6—Unverified
6CASE + Zhou et al.[email protected]:0.749.2—Unverified
7AFPS[email protected]:0.748.5—Unverified
8P-MIL[email protected]:0.747—Unverified
9AICL[email protected]:0.746.4—Unverified
10TSN[email protected]:0.746.2—Unverified
#ModelMetricClaimedVerifiedStatus
1HR-Proavg-mAP (0.3-0.7)51.1—Unverified
2LACP[email protected]45.3—Unverified
3LACPavg-mAP (0.3-0.7)44.5—Unverified
4ProCL[email protected]40.5—Unverified
5P-MIL[email protected]40—Unverified
6P-MILavg-mAP (0.3-0.7)38—Unverified
7D2-Net[email protected]35.9—Unverified
8Ju et al.[email protected]35.9—Unverified
9Ju et al.avg-mAP (0.3-0.7)35.4—Unverified
10ACM-Net[email protected]34.6—Unverified
#ModelMetricClaimedVerifiedStatus
1BaS-Net[email protected]38.5—Unverified
2CleanNet[email protected]37.1—Unverified
3W-TALC[email protected]37—Unverified
4CMCS[email protected]36.8—Unverified
5SALMean mAP30.8—Unverified
6AFPSMean mAP29.9—Unverified
7AICLMean mAP29.9—Unverified
8TSM[email protected]28.3—Unverified
9CASEMean mAP27.9—Unverified
10AutoLoc[email protected]27.3—Unverified
#ModelMetricClaimedVerifiedStatus
1MAAN[email protected]33.7—Unverified
2TSM[email protected]30.3—Unverified
3STPN[email protected]29.3—Unverified
4SAL[email protected]:0.9528.8—Unverified
5PivoTAL[email protected]:0.9528.1—Unverified
6AICL[email protected]:0.9527.6—Unverified
7AFPS[email protected]:0.9527.3—Unverified
8CASE[email protected]:0.9526.8—Unverified
9TSN[email protected]:0.9526.3—Unverified
10ProCL[email protected]:0.9526.1—Unverified
#ModelMetricClaimedVerifiedStatus
1AU-Action[email protected]:0.776.9—Unverified
2HR-Pro[email protected]:0.747.3—Unverified
3LACP[email protected]:0.743.5—Unverified
4Li et al.[email protected]:0.736.4—Unverified
5Ju et al.[email protected]:0.733.7—Unverified
6SF-Net[email protected]:0.731—Unverified
#ModelMetricClaimedVerifiedStatus
1HR-Pro[email protected]:0.759.4—Unverified
2LACP[email protected]:0.751.8—Unverified
3Ju et al.[email protected]:0.734.9—Unverified
4Li et al.[email protected]:0.734.4—Unverified
5SF-Net[email protected]:0.730.1—Unverified
#ModelMetricClaimedVerifiedStatus
1HAANmAP4.1—Unverified
2W-TALCmAP3.45—Unverified
3D2-NetmAP3.35—Unverified
4ASLmAP3.3—Unverified
#ModelMetricClaimedVerifiedStatus
1ProCLavg-mAP (0.1:0.7)47.7—Unverified