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

Showing 110 of 55 papers

TitleStatusHype
Multilevel semantic and adaptive actionness learning for weakly supervised temporal action localizationCode0
Weakly supervised temporal action localization with actionness-guided false positive suppressionCode0
Revisiting Foreground and Background Separation in Weakly-supervised Temporal Action Localization: A Clustering-based ApproachCode1
Is Weakly-supervised Action Segmentation Ready For Human-Robot Interaction? No, Let's Improve It With Action-union LearningCode2
POTLoc: Pseudo-Label Oriented Transformer for Point-Supervised Temporal Action Localization0
HR-Pro: Point-supervised Temporal Action Localization via Hierarchical Reliability PropagationCode1
Weakly-Supervised Action Localization by Hierarchically-structured Latent Attention Modeling0
Actionness Inconsistency-guided Contrastive Learning for Weakly-supervised Temporal Action LocalizationCode1
Proposal-Based Multiple Instance Learning for Weakly-Supervised Temporal Action LocalizationCode1
Two-Stream Networks for Weakly-Supervised Temporal Action Localization With Semantic-Aware Mechanisms0
Show:102550
← PrevPage 1 of 6Next →

Benchmark Results

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