OpenCodePapers

zero-shot-action-recognition-on-kinetics

Zero-Shot Action Recognition
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
PaperCodeTop-1 AccuracyTop-5 AccuracyModelNameReleaseDate
Leveraging Temporal Contextualization for Video Action Recognition✓ Link78.195.7TC-CLIP2024-04-15
Alternating Gradient Descent and Mixture-of-Experts for Integrated Multimodal Perception76.8IMP-MoE-L2023-05-10
OST: Refining Text Knowledge with Optimal Spatio-Temporal Descriptor for General Video Recognition✓ Link75.194.6OST2023-11-30
MAtch, eXpand and Improve: Unsupervised Finetuning for Zero-Shot Action Recognition with Language Knowledge✓ Link71.6MAXI2023-03-15
Orthogonal Temporal Interpolation for Zero-Shot Video Recognition✓ Link70.6OTI(ViT-L/14)2023-08-14
VideoCoCa: Video-Text Modeling with Zero-Shot Transfer from Contrastive Captioners70.188.9VideoCoCa2022-12-09
Revisiting Classifier: Transferring Vision-Language Models for Video Recognition✓ Link68.990.3Text4Vis2022-07-04
Bidirectional Cross-Modal Knowledge Exploration for Video Recognition with Pre-trained Vision-Language Models✓ Link68.591.1BIKE2022-12-31
Expanding Language-Image Pretrained Models for General Video Recognition✓ Link65.286.1X-CLIP2022-08-04
LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment✓ Link64.185.7LanguageBind2023-10-03
LoCATe-GAT: Modeling Multi-Scale Local Context and Action Relationships for Zero-Shot Action Recognition✓ Link58.7LoCATe-GAT2024-11-27
Rethinking Zero-shot Action Recognition: Learning from Latent Atomic Actions✓ Link45.978.8JigsawNet2022-03-28
Elaborative Rehearsal for Zero-shot Action Recognition✓ Link42.173.1ER-ZSAR (ST+Obj)2021-08-05
Elaborative Rehearsal for Zero-shot Action Recognition✓ Link37.169.3ER-ZSAR (ST)2021-08-05
DeViSE: A Deep Visual-Semantic Embedding Model23.851.0DEVISE2013-12-01
Learning a Deep Embedding Model for Zero-Shot Learning✓ Link23.649.5DEM2016-11-15
Label-Embedding for Image Classification✓ Link23.450.3ALE2015-03-30
An embarrassingly simple approach to zero-shot learning✓ Link22.948.3ESZSL2015-07-06
All About Knowledge Graphs for Actions22.349.7GCN2020-08-28
Evaluation of Output Embeddings for Fine-Grained Image Classification✓ Link22.348.2SJE(Word Embedding)2014-09-30