HyperAI초신경

홈 뉴스 최신 연구 논문 튜토리얼 데이터셋 백과사전 SOTA LLM 모델 GPU 랭킹 컨퍼런스

한국어

HyperAI초신경

Video Captioning On Youcook2

평가 지표

BLEU-4

CIDEr

METEOR

ROUGE-L

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	BLEU-4	CIDEr	METEOR	ROUGE-L	Paper Title	Repository
HowToCaption	8.8	116.4	15.9	37.3	HowToCaption: Prompting LLMs to Transform Video Annotations at Scale
VAST	18.2	1.99	-	-	VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset
VideoBERT + S3D	4.33	0.55	11.94	28.80	VideoBERT: A Joint Model for Video and Language Representation Learning
MA-LMM	-	1.31	17.6	-	MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding
OmniVL	8.72	1.16	14.83	36.09	OmniVL:One Foundation Model for Image-Language and Video-Language Tasks	-
COSA	10.1	1.31	-	-	COSA: Concatenated Sample Pretrained Vision-Language Foundation Model
UniVL + MELTR	17.92	1.90	22.56	47.04	MELTR: Meta Loss Transformer for Learning to Fine-tune Video Foundation Models
UniVL	17.35	1.81	22.35	46.52	UniVL: A Unified Video and Language Pre-Training Model for Multimodal Understanding and Generation
E2vidD6-MASSvid-BiD	12.04	1.22	18.32	39.03	Multimodal Pretraining for Dense Video Captioning
TextKG	11.7	1.33	14.8	40.2	Text with Knowledge Graph Augmented Transformer for Video Captioning	-
VLM	12.27	1.3869	18.22	41.51	VLM: Task-agnostic Video-Language Model Pre-training for Video Understanding
VideoCoCa	14.2	1.28	-	37.7	VideoCoCa: Video-Text Modeling with Zero-Shot Transfer from Contrastive Captioners	-
Zhou	4.38	0.38	11.55	27.44	End-to-End Dense Video Captioning with Masked Transformer
COOT	11.30	0.57	19.85	37.94	COOT: Cooperative Hierarchical Transformer for Video-Text Representation Learning

0 of 14 row(s) selected.