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/Zero-Shot Video Retrieval/MSR-VTT

Zero-Shot Video Retrieval on MSR-VTT

Metric: video-to-text R@10 (higher is better)

LeaderboardDataset
Loading chart...

Results

Submit a result
#Model↕video-to-text R@10▼Extra DataPaperDate↕Code
1InternVideo2-6B84.1YesInternVideo2: Scaling Foundation Models for Mult...2024-03-22Code
2GRAM82.9YesGramian Multimodal Representation Learning and A...2024-12-16Code
3FluxViT-B82.4YesMake Your Training Flexible: Towards Deployment-...2025-03-18Code
4InternVideo2-1B81.8YesInternVideo2: Scaling Foundation Models for Mult...2024-03-22Code
5LanguageBind(ViT-L/14)77.8YesLanguageBind: Extending Video-Language Pretraini...2023-10-03Code
6FluxViT-S76.5YesMake Your Training Flexible: Towards Deployment-...2025-03-18Code
7LanguageBind(ViT-H/14)75.7YesLanguageBind: Extending Video-Language Pretraini...2023-10-03Code
8UMT-L (ViT-L/16)69.6YesUnmasked Teacher: Towards Training-Efficient Vid...2023-03-28Code
9vid-TLDR (UMT-L)69.4Yesvid-TLDR: Training Free Token merging for Light-...2024-03-20Code
10LaT47.9NoLaT: Latent Translation with Cycle-Consistency f...2022-07-11-