Video Retrieval On Lsmdc

评估指标

text-to-video Mean Rank

text-to-video R@1

text-to-video R@10

text-to-video R@5

评测结果

各个模型在此基准测试上的表现结果

					Paper Title	Repository
InternVideo2-6B	-	46.4	-	-	InternVideo2: Scaling Foundation Models for Multimodal Video Understanding
vid-TLDR (UMT-L)	-	43.1	71.4	64.5	vid-TLDR: Training Free Token merging for Light-weight Video Transformer
UMT-L (ViT-L/16)	-	43.0	73.0	65.5	Unmasked Teacher: Towards Training-Efficient Video Foundation Models
HunYuan_tvr (huge)	3.9	40.4	92.8	80.1	Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations	-
COSA	-	39.4	-	-	COSA: Concatenated Sample Pretrained Vision-Language Foundation Model
mPLUG-2	-	34.4	65.1	55.2	mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video
VALOR	-	34.2	64.1	56.0	VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset
InternVideo	-	34.0	-	-	InternVideo: General Video Foundation Models via Generative and Discriminative Learning
CLIP-ViP	-	30.7	60.6	51.4	CLIP-ViP: Adapting Pre-trained Image-Text Model to Video-Language Representation Alignment
HunYuan_tvr	56.4	29.7	55.4	46.4	Tencent Text-Video Retrieval: Hierarchical Cross-Modal Interactions with Multi-Level Representations	-
STAN	-	29.2	58.8	49.5	Revisiting Temporal Modeling for CLIP-based Image-to-Video Knowledge Transferring
HiTeA	-	28.7	59.0	50.3	HiTeA: Hierarchical Temporal-Aware Video-Language Pre-training	-
MDMMT-2	48.0	26.9	55.9	46.7	MDMMT-2: Multidomain Multimodal Transformer for Video Retrieval, One More Step Towards Generalization	-
X-CLIP	-	26.1	-	-	X-CLIP: End-to-End Multi-grained Contrastive Learning for Video-Text Retrieval
CAMoE	54.4	25.9	53.7	46.1	Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss
EMCL-Net++	-	25.9	-	46.4	Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations
X-Pool	53.2	25.2	53.5	43.7	X-Pool: Cross-Modal Language-Video Attention for Text-Video Retrieval
Clover	-	24.8	54.5	44	Clover: Towards A Unified Video-Language Alignment and Fusion Model
DiffusionRet	40.7	24.4	54.3	43.1	DiffusionRet: Generative Text-Video Retrieval with Diffusion Model
CenterCLIP (ViT-B/16)	47.3	24.2	55.9	46.2	CenterCLIP: Token Clustering for Efficient Text-Video Retrieval

0 of 38 row(s) selected.