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 Captioning/MSVD

Video Captioning on MSVD

Metric: BLEU-4 (higher is better)

LeaderboardDataset
Loading chart...

Results

Submit a result
#Model↕BLEU-4▼Extra DataPaperDate↕Code
1VALOR80.7YesVALOR: Vision-Audio-Language Omni-Perception Pre...2023-04-17Code
2VLAB79.3YesVLAB: Enhancing Video Language Pre-training by F...2023-05-22-
3COSA76.5YesCOSA: Concatenated Sample Pretrained Vision-Lang...2023-06-15Code
4HiTeA71YesHiTeA: Hierarchical Temporal-Aware Video-Languag...2022-12-30-
5mPLUG-270.5NomPLUG-2: A Modularized Multi-modal Foundation Mo...2023-02-01Code
6HowToCaption70.4NoHowToCaption: Prompting LLMs to Transform Video ...2023-10-07Code
7RTQ66.9NoRTQ: Rethinking Video-language Understanding Bas...2023-12-01Code
8CoCap (ViT/L14)60.1NoAccurate and Fast Compressed Video Captioning2023-09-22Code
9SEM-POS60.1NoSEM-POS: Grammatically and Semantically Correct ...2023-03-26-
10VASTA (Vatex-backbone)59.2NoDiverse Video Captioning by Adaptive Spatio-temp...2022-08-19Code
11IcoCap (ViT-B/16)59.1Yes---
12IcoCap (ViT-B/32)56.3Yes---
13VASTA (Kinetics-backbone)56.1NoDiverse Video Captioning by Adaptive Spatio-temp...2022-08-19Code