Zero Shot Action Recognition On Hmdb51

Metrics

Top-1 Accuracy

Results

Performance results of various models on this benchmark

Model Name	Top-1 Accuracy	Paper Title	Repository
AURL	39	Alignment-Uniformity aware Representation Learning for Zero-shot Video Classification	-
VicTR (ViT-B/16)	51.0	VicTR: Video-conditioned Text Representations for Activity Recognition	-
SPOT	35.9	Synthetic Sample Selection for Generalized Zero-Shot Learning	-
JigsawNet	38.7	Rethinking Zero-shot Action Recognition: Learning from Latent Atomic Actions
LoCATe-GAT	50.7	LoCATe-GAT: Modeling Multi-Scale Local Context and Action Relationships for Zero-Shot Action Recognition
X-CLIP	44.6	Expanding Language-Image Pretrained Models for General Video Recognition
SJE(word embedding)	13.3	Evaluation of Output Embeddings for Fine-Grained Image Classification
TC-CLIP	56.0	Leveraging Temporal Contextualization for Video Action Recognition
Text4Vis	58.4	Revisiting Classifier: Transferring Vision-Language Models for Video Recognition
MTE	19.7	Multi-Task Zero-Shot Action Recognition with Prioritised Data Augmentation	-
MOV (ViT-B/16)	60.8	Multimodal Open-Vocabulary Video Classification via Pre-Trained Vision and Language Models	-
O2A	15.6	Objects2action: Classifying and localizing actions without any video example	-
VideoCoCa	58.7	VideoCoCa: Video-Text Modeling with Zero-Shot Transfer from Contrastive Captioners	-
TS-GCN	23.2	I Know the Relationships: Zero-Shot Action Recognition via Two-Stream Graph Convolutional Networks and Knowledge Graphs
MSQNet	-	Actor-agnostic Multi-label Action Recognition with Multi-modal Query
BIKE	61.4	Bidirectional Cross-Modal Knowledge Exploration for Video Recognition with Pre-trained Vision-Language Models
OTI(ViT-L/14)	64	Orthogonal Temporal Interpolation for Zero-Shot Video Recognition
IMP-MoE-L	59.1	Alternating Gradient Descent and Mixture-of-Experts for Integrated Multimodal Perception	-
ESZSL	18.5	-	-
ER-ZSAR	35.3	Elaborative Rehearsal for Zero-shot Action Recognition

0 of 29 row(s) selected.