HyperAIHyperAI

Command Palette

Search for a command to run...

Plateforme

Zero Shot Action Recognition On Hmdb51

Métriques

Top-1 Accuracy

Résultats

Résultats de performance de divers modèles sur ce benchmark

Paper Title
MOV (ViT-L/14)64.7Multimodal Open-Vocabulary Video Classification via Pre-Trained Vision and Language Models
OTI(ViT-L/14)64Orthogonal Temporal Interpolation for Zero-Shot Video Recognition
BIKE61.4Bidirectional Cross-Modal Knowledge Exploration for Video Recognition with Pre-trained Vision-Language Models
MOV (ViT-B/16)60.8Multimodal Open-Vocabulary Video Classification via Pre-Trained Vision and Language Models
IMP-MoE-L59.1Alternating Gradient Descent and Mixture-of-Experts for Integrated Multimodal Perception
VideoCoCa58.7VideoCoCa: Video-Text Modeling with Zero-Shot Transfer from Contrastive Captioners
Text4Vis58.4Revisiting Classifier: Transferring Vision-Language Models for Video Recognition
TC-CLIP56.0Leveraging Temporal Contextualization for Video Action Recognition
OST55.9OST: Refining Text Knowledge with Optimal Spatio-Temporal Descriptor for General Video Recognition
MAXI52.3MAtch, eXpand and Improve: Unsupervised Finetuning for Zero-Shot Action Recognition with Language Knowledge
VicTR (ViT-B/16)51.0VicTR: Video-conditioned Text Representations for Activity Recognition
LoCATe-GAT50.7LoCATe-GAT: Modeling Multi-Scale Local Context and Action Relationships for Zero-Shot Action Recognition
X-CLIP44.6Expanding Language-Image Pretrained Models for General Video Recognition
CLASTER43.2CLASTER: Clustering with Reinforcement Learning for Zero-Shot Action Recognition
ResT41.1Cross-modal Representation Learning for Zero-shot Action Recognition
AURL39Alignment-Uniformity aware Representation Learning for Zero-shot Video Classification
JigsawNet38.7Rethinking Zero-shot Action Recognition: Learning from Latent Atomic Actions
SPOT35.9Synthetic Sample Selection for Generalized Zero-Shot Learning
ER-ZSAR35.3Elaborative Rehearsal for Zero-shot Action Recognition
E2E32.7Rethinking Zero-shot Video Classification: End-to-end Training for Realistic Applications
0 of 29 row(s) selected.
Zero Shot Action Recognition On Hmdb51 | SOTA | HyperAI