List your company
ResearchFormerly WizWand

Zero-Shot Action Recognition on HMDB51 (test)

59AccuracyOpen-VCLIP
11.47223.81136.1548.489Nov 26, 2016Feb 18, 2018May 14, 2019Aug 5, 2020Oct 29, 2021Jan 21, 2023Apr 15, 2024
Updated 8mo ago

Evaluation results

MethodLinks
Open-VCLIPBackbone=ViT-L/14, Word Embeddings (WE)=true, Evaluation protocol=Zero-shot, Training dataset=Kinetics-4002024.0459
TC-CLIPBackbone=ViT-L/14, Word Embeddings (WE)=true, Evaluation protocol=Zero-shot, Training dataset=Kinetics-4002024.0457.1
TC-CLIPBackbone=ViT-L/14, Word Embeddings (WE)=false, Evaluation protocol=Zero-shot, Training dataset=Kinetics-4002024.0456.1
ViFi-CLIP (reproduced)Backbone=ViT-L/14, Word Embeddings (WE)=true, Evaluation protocol=Zero-shot, Training dataset=Kinetics-4002024.0455.8
ViFi-CLIPBackbone=ViT-L/14, Word Embeddings (WE)=false, Evaluation protocol=Zero-shot, Training dataset=Kinetics-4002024.0455.6
Vita-CLIP B/16Training Paradigm=Vision-Language Training, Evaluation Protocol=Zero-shot, Mc=8, Mv=82023.0448.6
X-CLIP-B/16Training Paradigm=Vision-Language Training, Evaluation Protocol=Zero-shot2023.0444.6
A5Training Paradigm=Vision-Language Training, Evaluation Protocol=Zero-shot2023.0444.3
ActionCLIPTraining Paradigm=Vision-Language Training, Evaluation Protocol=Zero-shot2023.0440.8
ER-ZSARTraining Paradigm=Vision Training, Evaluation Protocol=Zero-shot2023.0435.3
E2ETraining Paradigm=Vision Training, Evaluation Protocol=Zero-shot2023.0432.7
MTE + Full KLIEP + PPLabel embedding=Word-vector, Visual feature=Fisher Vector, Transductive=true, Data augmentation=true2016.1124.8
URTraining Paradigm=Vision Training, Evaluation Protocol=Zero-shot2023.0424.4
MTE + Full KLIEPLabel embedding=Word-vector, Visual feature=Fisher Vector, Transductive=true, Data augmentation=false2016.1123.9
TS-GCNTraining Paradigm=Vision Training, Evaluation Protocol=Zero-shot2023.0423.2
SVELabel embedding=Word-vector, Visual feature=Bag of Words, Transductive=true, Data augmentation=true2016.1122.8
ESZSLLabel embedding=Word-vector, Visual feature=Fisher Vector, Transductive=false, Data augmentation=true2016.1122.7
ZSECOCTraining Paradigm=Vision Training, Evaluation Protocol=Zero-shot2023.0422.6
ASRTraining Paradigm=Vision Training, Evaluation Protocol=Zero-shot2023.0421.8
MTELabel embedding=Word-vector, Visual feature=Fisher Vector, Transductive=false, Data augmentation=false2016.1119.7
SVELabel embedding=Word-vector, Visual feature=Bag of Words, Transductive=true, Data augmentation=false2016.1119.3
ESZSLLabel embedding=Word-vector, Visual feature=Fisher Vector, Transductive=false, Data augmentation=false2016.1118.5
SVELabel embedding=Word-vector, Visual feature=Bag of Words, Transductive=false, Data augmentation=true2016.1115.6
SVELabel embedding=Word-vector, Visual feature=Bag of Words, Transductive=false, Data augmentation=false2016.1114.9
SJELabel embedding=Word-vector, Visual feature=Fisher Vector, Transductive=false, Data augmentation=false2016.1113.3