Video Retrieval On Msr Vtt

المقاييس

text-to-video R@1

text-to-video R@10

text-to-video R@5

النتائج

نتائج أداء النماذج المختلفة على هذا المعيار القياسي

اسم النموذج	text-to-video R@1	text-to-video R@10	text-to-video R@5	Paper Title	Repository
TEFAL	52	86.1	76.6	Audio-Enhanced Text-to-Video Retrieval using Text-Conditioned Feature Alignment	-
VideoCoCa (zero-shot)	34.3	67.0	57.8	VideoCoCa: Video-Text Modeling with Zero-Shot Transfer from Contrastive Captioners	-
TACo	24.8	64.0	52.1	TACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment	-
VIOLETv2	37.2	75.8	64.8	An Empirical Study of End-to-End Video-Language Transformers with Masked Visual Modeling
COSA	57.9	-	-	COSA: Concatenated Sample Pretrained Vision-Language Foundation Model
CoCa (zero-shot)	30.0	61.6	52.4	CoCa: Contrastive Captioners are Image-Text Foundation Models
CLIP	21.4	50.4	41.1	A Straightforward Framework For Video Retrieval Using CLIP
RoME	10.7	41.2	29.6	RoME: Role-aware Mixture-of-Expert Transformer for Text-to-Video Retrieval
InternVideo2-6B	62.8	-	-	InternVideo2: Scaling Foundation Models for Multimodal Video Understanding
C+LSTM+SA+FC7	4.2	19.9	-	Learning Language-Visual Embedding for Movie Understanding with Natural-Language	-
VALOR	59.9	89.6	83.5	VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset
GRAM	64	89.3	-	Gramian Multimodal Representation Learning and Alignment
Aurora (ours, r=64)	52.4	82	73.9	-	-
Kaufman	4.7	24.1	-	Temporal Tessellation: A Unified Approach for Video Analysis
Ours	26	-	56.7	Video and Text Matching with Conditioned Embeddings
Text-Video Embedding	14.9	52.8	-	HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips
FROZEN	32.5	71.2	61.5	Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval
LAFF	29.1	65.8	54.9	Lightweight Attentional Feature Fusion: A New Baseline for Text-to-Video Retrieval
All-in-one + MELTR	38.6	84.7	74.4	MELTR: Meta Loss Transformer for Learning to Fine-tune Video Foundation Models
JSFusion	10.2	43.2	-	A Joint Sequence Fusion Model for Video Question Answering and Retrieval

0 of 40 row(s) selected.