Papers with Code · CC BY-SA 4.0

MSR-VTT

아카이브 평가 24건 · 마지막 적재/변경 2026-10-30

평가 기록

과거 수집 기록이며 최신 순위가 아닙니다. 데이터셋 버전·split·실험 조건과 지표 방향이 검증되지 않은 결과는 직접 비교할 수 없습니다. 날짜는 논문 날짜이며 최신 평가일을 뜻하지 않습니다.

표가 화면보다 넓으면 좌우로 스크롤하여 논문과 구현 링크를 확인하세요.

원본 기록 순서 · 순위 미부여
모델	원본 지표·값	논문	구현
mPLUG-2	CIDEr 80.0 METEOR 34.9 ROUGE-L 70.1 BLEU-4 57.8	mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video 2023-02-01	코드 1 · 코드 2 · 코드 3 · 코드 4
VAST	CIDEr 78.0 BLEU-4 56.7	VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset 2023-05-29	코드 1 · 코드 2
GIT2	CIDEr 75.9 METEOR 33.1 ROUGE-L 68.2 BLEU-4 54.8 GS 201.6	GIT: A Generative Image-to-text Transformer for Vision and Language 2022-05-27	코드 1
VLAB	CIDEr 74.9 METEOR 33.4 ROUGE-L 68.3 BLEU-4 54.6	VLAB: Enhancing Video Language Pre-training by Feature Adapting and Blending 2023-05-22	연결 없음
COSA	CIDEr 74.7 BLEU-4 53.7	COSA: Concatenated Sample Pretrained Vision-Language Foundation Model 2023-06-15	코드 1
VALOR	CIDEr 74.0 METEOR 32.9 ROUGE-L 68.0 BLEU-4 54.4	VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset 2023-04-17	코드 1
MaMMUT (ours)	CIDEr 73.6	MaMMUT: A Simple Architecture for Joint Learning for MultiModal Tasks 2023-03-29	코드 1
VideoCoCa	CIDEr 73.2 ROUGE-L 68.0 BLEU-4 53.8	VideoCoCa: Video-Text Modeling with Zero-Shot Transfer from Contrastive Captioners 2022-12-09	연결 없음
RTQ	CIDEr 69.3 ROUGE-L 66.1 BLEU-4 49.6	RTQ: Rethinking Video-language Understanding Based on Image-text Model 2023-12-01	코드 1 · 코드 2
HowToCaption	CIDEr 65.3 METEOR 32.2 ROUGE-L 66.3 BLEU-4 49.8	HowToCaption: Prompting LLMs to Transform Video Annotations at Scale 2023-10-07	코드 1
HiTeA	CIDEr 65.1 METEOR 30.7 ROUGE-L 65.0 BLEU-4 49.2	HiTeA: Hierarchical Temporal-Aware Video-Language Pre-training 2022-12-30	연결 없음
Vid2Seq	CIDEr 64.6 METEOR 30.8	Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning 2023-02-27	코드 1 · 코드 2 · 코드 3
TextKG	CIDEr 60.8 METEOR 30.5 ROUGE-L 64.8 BLEU-4 46.6	Text with Knowledge Graph Augmented Transformer for Video Captioning 2023-03-22	연결 없음
IcoCap (ViT-B/16)	CIDEr 60.2 METEOR 31.1 ROUGE-L 64.9 BLEU-4 47.0	IcoCap: Improving Video Captioning by Compounding Images 2023-10-05	연결 없음
MV-GPT	CIDEr 60.0 METEOR 38.7 ROUGE-L 64.0 BLEU-4 48.9	End-to-end Generative Pretraining for Multimodal Video Captioning 2022-01-20	연결 없음
IcoCap (ViT-B/32)	CIDEr 59.1 METEOR 30.3 ROUGE-L 64.3 BLEU-4 46.1	IcoCap: Improving Video Captioning by Compounding Images 2023-10-05	연결 없음
CLIP-DCD	CIDEr 58.7 METEOR 31.3 ROUGE-L 64.8 BLEU-4 48.2	CLIP Meets Video Captioning: Concept-Aware Representation Learning Does Matter 2021-11-30	코드 1
VIOLETv2	CIDEr 58	An Empirical Study of End-to-End Video-Language Transformers with Masked Visual Modeling 2022-09-04	코드 1
CoCap (ViT/L14)	CIDEr 57.2 METEOR 30.3 ROUGE-L 63.4 BLEU-4 44.4	Accurate and Fast Compressed Video Captioning 2023-09-22	코드 1
VASTA (Vatex-backbone)	CIDEr 56.08 METEOR 30.24 ROUGE-L 62.9 BLEU-4 44.21	Diverse Video Captioning by Adaptive Spatio-temporal Attention 2022-08-19	코드 1
VASTA (Kinetics-backbone)	CIDEr 55 METEOR 30.2 ROUGE-L 62.5 BLEU-4 43.4	Diverse Video Captioning by Adaptive Spatio-temporal Attention 2022-08-19	코드 1
EMCL-Net	CIDEr 54.6 METEOR 30.2 ROUGE-L 63.2 BLEU-4 45.3	Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations 2022-11-21	코드 1 · 코드 2 · 코드 3 · 코드 4
SEM-POS	CIDEr 53.1 METEOR 30.7 ROUGE-L 64.1 BLEU-4 45.2 GS 192.6	SEM-POS: Grammatically and Semantically Correct Video Captioning 2023-03-26	연결 없음
UniVL + MELTR	CIDEr 52.77 METEOR 29.26 ROUGE-L 62.35 BLEU-4 44.17	MELTR: Meta Loss Transformer for Learning to Fine-tune Video Foundation Models 2023-03-23	코드 1