AI Paper Atlas

Research map / Benchmarks / MSVD

MSVD leaderboard

54 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on MSVD. Best CIDEr: 189.4 (AdaCM2, CVPR 2025).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

MSVD · CIDEr

34 papers, each with its best reported number for its own method; higher is better.

#CIDEr ↑MethodPaperTopic
1189.4AdaCM2
InstructBLIP Q-Former, Vicuna-7B
AdaCM^2: On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction
CVPR 2025 · Table 3
Video-language understanding
2183.1HierarQ
Vicuna 7B
HierarQ: Task-Aware Hierarchical Q-Former for Enhanced Video Understanding
CVPR 2025 · Table 5
Video-language understanding
3179.1MA-LMM
Vicuna-7B
MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding
CVPR 2024 · Table 4
Video-language understanding
4171.6MAMS + mPLUG-2
mPLUG-2
MAMS: Model-Agnostic Module Selection Framework for Video Captioning
AAAI 2025 · Main results table, MSVD
Video-language understanding
5151.19Token Mixing (F)
BLIP ViT-B/16
Token Mixing: Parameter-Efficient Transfer Learning from Image-Language to Video-Language
AAAI 2023 · Table 5
Video-language understanding
6148.2S3VL
VideoSwin + BERT-base
Stitching Segments and Sentences towards Generalization in Video-Text Pre-training
AAAI 2024 · Table 2
Video-language understanding
7145.4STM
ViT-B/16
Video Language Model Pretraining with Spatio-temporal Masking
CVPR 2025 · Table 4
Video-language understanding
8130.96Ours, iterative selection
SwinBERT
Learnability Matters: Active Learning for Video Captioning
NeurIPS 2024 · Table 1
Video-language understanding
9122.5OmniViD
VideoSwin-Base
OmniViD: A Generative Framework for Universal Video Understanding
CVPR 2024 · Table 3
Video-language understanding
10121.5Ours (ViT/L14)
CLIP ViT-L/14
Accurate and Fast Compressed Video Captioning
ICCV 2023 · Table 1
Video segmentation and tracking
24 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

MSVD · METEOR

22 papers, each with its best reported number for its own method; higher is better.

12 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

MSVD · BLEU-4

21 papers, each with its best reported number for its own method; higher is better.

11 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

MSVD · R@1

12 papers, each with its best reported number for its own method; higher is better.

#R@1 ↑MethodPaperTopic
174.2BLIP + Heuristic
BLIP
Simple Baselines for Interactive Video Retrieval with Questions and Answers
ICCV 2023 · Table 2
Video-language understanding
262.7vid-TLDR
UMT-B
vid-TLDR: Training Free Token Merging for Light-weight Video Transformer
CVPR 2024 · Table 2
Video segmentation and tracking
361.6AMD-Net
CLIP ViT-B/16
Appearance-Motion Decomposed Alignment for Text-Video Retrieval
AAAI 2026 · Table 2
Video-language understanding
455.2VIDEO-COLBERT (SigLIP-B/16)
SigLIP-B/16
Video-ColBERT: Contextualized Late Interaction for Text-to-Video Retrieval
CVPR 2025 · Table 1
Video-language understanding
552.2LanguageBind
CLIP-L/14
LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment
ICLR 2024 · Table: Zero-shot Video-Text re
Cross-modal learning
651.5STAN-conv-B/16
CLIP-B/16
Revisiting Temporal Modeling for CLIP-Based Image-to-Video Knowledge Transferring
CVPR 2023 · Appendix table: Comparisons on
Video-language understanding
747.9PIG
CLIP-ViP B/32
Hybrid-Tower: Fine-grained Pseudo-query Interaction and Generation for Text-to-Video Retrieval
ICCV 2025 · Table 1
Video-language understanding
847.6CLIP2Video (+QB-Norm)
CLIP2Video
Cross Modal Retrieval With Querybank Normalisation
CVPR 2022 · Table: MSVD comparison
Cross-modal learning
947.2X-Pool
CLIP ViT-B/32
X-Pool: Cross-Modal Language-Video Attention for Text-Video Retrieval
CVPR 2022 · Table: t2v results on MSVD
Video-language understanding
1045.4LAFF-mlLightweight Attentional Feature Fusion: A New Baseline for Text-to-Video Retrieval
ECCV 2022 · Table 7
Video-language understanding
2 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.