ML Research Wiki / Benchmarks / Video Captioning / MSVD

MSVD

Video Captioning Benchmark

Performance Over Time

📊 Showing 14 results | 📏 Metric: CIDEr

Top Performing Models

Rank Model Paper CIDEr Date Code
1 MaMMUT MaMMUT: A Simple Architecture for Joint Learning for MultiModal Tasks 195.60 2023-03-29 📦 lucidrains/mammut-pytorch
2 Vid2Seq 📚 Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning 146.20 2023-02-27 📦 google-research/scenic 📦 antoyang/VidChapters 📦 KastanDay/video-pretrained-transformer
3 VIOLETv2 An Empirical Study of End-to-End Video-Language Transformers with Masked Visual Modeling 139.20 2022-09-04 📦 tsujuifu/pytorch_empirical-mvm
4 VALOR 📚 VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset 80.70 2023-04-17 📦 TXH-mercury/VALOR
5 VLAB 📚 VLAB: Enhancing Video Language Pre-training by Feature Adapting and Blending 79.30 2023-05-22 -
6 COSA 📚 COSA: Concatenated Sample Pretrained Vision-Language Foundation Model 76.50 2023-06-15 📦 txh-mercury/cosa
7 HiTeA 📚 HiTeA: Hierarchical Temporal-Aware Video-Language Pre-training 71.00 2022-12-30 -
8 mPLUG-2 mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video 70.50 2023-02-01 📦 modelscope/modelscope 📦 x-plug/mplug-owl 📦 alibaba/AliceMind 📦 X-PLUG/mPLUG-2
9 HowToCaption HowToCaption: Prompting LLMs to Transform Video Annotations at Scale 70.40 2023-10-07 📦 ninatu/howtocaption
10 RTQ RTQ: Rethinking Video-language Understanding Based on Image-text Model 66.90 2023-12-01 📦 SCZwangxiao/RTQ-MM2023 📦 sczwangxiao/tsgvs-mm2023

All Papers (14)

lucidrains/mammut-pytorch
google-research/scenic antoyang/VidChapters KastanDay/video-pretrained-transformer
tsujuifu/pytorch_empirical-mvm
TXH-mercury/VALOR
txh-mercury/cosa
modelscope/modelscope x-plug/mplug-owl
ninatu/howtocaption
SCZwangxiao/RTQ-MM2023 sczwangxiao/tsgvs-mm2023
acherstyx/CoCap
zohrehghaderi/vasta
zohrehghaderi/vasta