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/Computer Vision/Video/ActivityNet

Video on ActivityNet

Metric: video-to-text R@5 (higher is better)

LeaderboardDataset
Loading chart...

Results

Submit a result
#Model↕video-to-text R@5▼Extra DataPaperDate↕Code
1UMT-L (ViT-L/16)89.1YesUnmasked Teacher: Towards Training-Efficient Vid...2023-03-28Code
2vid-TLDR (UMT-L)88.7Yesvid-TLDR: Training Free Token merging for Light-...2024-03-20Code
3HunYuan_tvr85.7YesTencent Text-Video Retrieval: Hierarchical Cross...2022-04-07-
4EMCL-Net++78.9NoExpectation-Maximization Contrastive Learning fo...2022-11-21Code
5CenterCLIP (ViT-B/16)77.1YesCenterCLIP: Token Clustering for Efficient Text-...2022-05-02Code
6DiffusionRet+QB-Norm76.3NoDiffusionRet: Generative Text-Video Retrieval wi...2023-03-17Code
7X-CLIP75.9NoX-CLIP: End-to-End Multi-grained Contrastive Lea...2022-07-15Code
8DiffusionRet75.3NoDiffusionRet: Generative Text-Video Retrieval wi...2023-03-17Code
9EMCL-Net74NoExpectation-Maximization Contrastive Learning fo...2022-11-21Code
10HBI73NoVideo-Text as Game Players: Hierarchical Banzhaf...2023-03-25Code
11Ours60NoVideo and Text Matching with Conditioned Embeddi...2021-10-21Code