Command Palette

Search for a command to run...

Zero Shot Action Recognition On Ucf101

평가 지표

Top-1 Accuracy

평가 결과

이 벤치마크에서 각 모델의 성능 결과

Paper Title
OTI(ViT-L/14)92.8Orthogonal Temporal Interpolation for Zero-Shot Video Recognition
IMP-MoE-L91.5Alternating Gradient Descent and Mixture-of-Experts for Integrated Multimodal Perception
MOV (ViT-L/14)87.1Multimodal Open-Vocabulary Video Classification via Pre-Trained Vision and Language Models
BIKE86.6Bidirectional Cross-Modal Knowledge Exploration for Video Recognition with Pre-trained Vision-Language Models
VideoCoCa86.6VideoCoCa: Video-Text Modeling with Zero-Shot Transfer from Contrastive Captioners
Text4Vis85.8Revisiting Classifier: Transferring Vision-Language Models for Video Recognition
TC-CLIP85.4Leveraging Temporal Contextualization for Video Action Recognition
EVA-CLIP-E/14+83.1EVA-CLIP: Improved Training Techniques for CLIP at Scale
MOV (ViT-B/16)82.6Multimodal Open-Vocabulary Video Classification via Pre-Trained Vision and Language Models
OST79.7OST: Refining Text Knowledge with Optimal Spatio-Temporal Descriptor for General Video Recognition
EZ-CLIP79.1EZ-CLIP: Efficient Zeroshot Video Action Recognition
MAXI78.2MAtch, eXpand and Improve: Unsupervised Finetuning for Zero-Shot Action Recognition with Language Knowledge
LoCATe-GAT76.0LoCATe-GAT: Modeling Multi-Scale Local Context and Action Relationships for Zero-Shot Action Recognition
VicTR (ViT-B/16)72.4VicTR: Video-conditioned Text Representations for Activity Recognition
X-CLIP72.0Expanding Language-Image Pretrained Models for General Video Recognition
ResT58.7Cross-modal Representation Learning for Zero-shot Action Recognition
AURL58Alignment-Uniformity aware Representation Learning for Zero-shot Video Classification
JigsawNet56.0Rethinking Zero-shot Action Recognition: Learning from Latent Atomic Actions
CLASTER53.9CLASTER: Clustering with Reinforcement Learning for Zero-Shot Action Recognition
ER-ZSAR51.8Elaborative Rehearsal for Zero-shot Action Recognition
0 of 35 row(s) selected.