ML Research Wiki / Benchmarks / Video Captioning / YouCook2

YouCook2

Video Captioning Benchmark

Performance Over Time

📊 Showing 14 results | 📏 Metric: BLEU-4

Top Performing Models

Rank Model Paper BLEU-4 Date Code
1 VAST 📚 VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset 18.20 2023-05-29 📦 TXH-mercury/VALOR 📦 txh-mercury/vast
2 UniVL + MELTR MELTR: Meta Loss Transformer for Learning to Fine-tune Video Foundation Models 17.92 2023-03-23 📦 mlvlab/MELTR
3 UniVL 📚 UniVL: A Unified Video and Language Pre-Training Model for Multimodal Understanding and Generation 17.35 2020-02-15 📦 microsoft/UniVL 📦 wqliu657/UniVL
4 VideoCoCa 📚 VideoCoCa: Video-Text Modeling with Zero-Shot Transfer from Contrastive Captioners 14.20 2022-12-09 -
5 VLM 📚 VLM: Task-agnostic Video-Language Model Pre-training for Video Understanding 12.27 2021-05-20 📦 pytorch/fairseq
6 E2vidD6-MASSvid-BiD 📚 Multimodal Pretraining for Dense Video Captioning 12.04 2020-11-10 📦 google-research-datasets/Video-Timeline-Tags-ViTT
7 TextKG Text with Knowledge Graph Augmented Transformer for Video Captioning 11.70 2023-03-22 -
8 COOT 📚 COOT: Cooperative Hierarchical Transformer for Video-Text Representation Learning 11.30 2020-11-01 📦 gingsi/coot-videotext
9 COSA 📚 COSA: Concatenated Sample Pretrained Vision-Language Foundation Model 10.10 2023-06-15 📦 txh-mercury/cosa
10 HowToCaption HowToCaption: Prompting LLMs to Transform Video Annotations at Scale 8.80 2023-10-07 📦 ninatu/howtocaption

All Papers (14)

TXH-mercury/VALOR txh-mercury/vast
mlvlab/MELTR
microsoft/UniVL wqliu657/UniVL
pytorch/fairseq
google-research-datasets/Video-Timeline-Tags-ViTT
gingsi/coot-videotext
txh-mercury/cosa
ninatu/howtocaption
salesforce/densecap
ammesatyajit/VideoBERT MDSKUL/MasterProject parkervg/allrecipes-bert
boheumd/MA-LMM