TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

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

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

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

SotA/Methodology/Zero-Shot Learning/THUMOS14

Zero-Shot Learning on THUMOS14

Metric: avg-mAP (0.3-0.7) (higher is better)

LeaderboardDataset
Loading chart...

Results

Submit a result
#Model↕avg-mAP (0.3-0.7)▼AugmentationsPaperDate↕Code
1HR-Pro51.1YesHR-Pro: Point-supervised Temporal Action Localiz...2023-08-24Code
2LACP44.5YesLearning Action Completeness from Points for Wea...2021-08-11Code
3P-MIL38NoProposal-Based Multiple Instance Learning for We...2023-05-29Code
4Ju et al.35.4YesPoint-Level Temporal Action Localization: Bridgi...2020-12-15-
5ACM-Net33.4NoACM-Net: Action Context Modeling Network for Wea...2021-04-07Code
6Lee et al.32.9NoWeakly-supervised Temporal Action Localization b...2020-06-12Code
7AMS32.4NoAdaptive Mutual Supervision for Weakly-Supervise...2021-04-06-
8AUMN32.4NoAction Unit Memory Network for Weakly Supervised...2021-04-29-
9CoLA32.1NoCoLA: Weakly-Supervised Temporal Action Localiza...2021-03-30Code
10A2CL-PT30.6NoAdversarial Background-Aware Loss for Weakly-sup...2020-07-13Code
11EM-ML30.4NoWeakly-Supervised Action Localization with Expec...2020-03-31Code
12TSCN28.8NoTwo-Stream Consensus Network for Weakly-Supervis...2020-10-22-