List your company
ResearchFormerly WizWand

Zero-Shot Action Recognition on UCF101 (test)

88.9AccuracyTC-CLIP
6.7428.0749.470.73Nov 26, 2016Feb 18, 2018May 14, 2019Aug 5, 2020Oct 29, 2021Jan 21, 2023Apr 15, 2024
Updated 8mo ago

Evaluation results

MethodLinks
TC-CLIPBackbone=ViT-L/14, Word Embeddings (WE)=true, Evaluation protocol=Zero-shot, Training dataset=Kinetics-4002024.0488.9
ViFi-CLIP (reproduced)Backbone=ViT-L/14, Word Embeddings (WE)=true, Evaluation protocol=Zero-shot, Training dataset=Kinetics-4002024.0488.1
Open-VCLIPBackbone=ViT-L/14, Word Embeddings (WE)=true, Evaluation protocol=Zero-shot, Training dataset=Kinetics-4002024.0487.6
TC-CLIPBackbone=ViT-L/14, Word Embeddings (WE)=false, Evaluation protocol=Zero-shot, Training dataset=Kinetics-4002024.0486.9
ViFi-CLIPBackbone=ViT-L/14, Word Embeddings (WE)=false, Evaluation protocol=Zero-shot, Training dataset=Kinetics-4002024.0486.1
Vita-CLIP B/16Training Paradigm=Vision-Language Training, Evaluation Protocol=Zero-shot, Mc=8, Mv=82023.0475
X-CLIP-B/16Training Paradigm=Vision-Language Training, Evaluation Protocol=Zero-shot2023.0472
A5Training Paradigm=Vision-Language Training, Evaluation Protocol=Zero-shot2023.0469.3
ActionCLIPTraining Paradigm=Vision-Language Training, Evaluation Protocol=Zero-shot2023.0458.3
ER-ZSARTraining Paradigm=Vision Training, Evaluation Protocol=Zero-shot2023.0451.8
E2ETraining Paradigm=Vision Training, Evaluation Protocol=Zero-shot2023.0448
TS-GCNTraining Paradigm=Vision Training, Evaluation Protocol=Zero-shot2023.0434.2
ASRTraining Paradigm=Vision Training, Evaluation Protocol=Zero-shot2023.0424.4
MTE + Full KLIEP + PPLabel embedding=Word-vector, Visual feature=Fisher Vector, Transductive=true, Data augmentation=true2016.1122.9
MTE + Full KLIEPLabel embedding=Word-vector, Visual feature=Fisher Vector, Transductive=true, Data augmentation=false2016.1121.9
ESZSLLabel embedding=Word-vector, Visual feature=Fisher Vector, Transductive=false, Data augmentation=true2016.1118.7
SVELabel embedding=Word-vector, Visual feature=Bag of Words, Transductive=true, Data augmentation=true2016.1118.4
MTELabel embedding=Attribute, Visual feature=Fisher Vector, Transductive=false, Data augmentation=false2016.1118.3
URTraining Paradigm=Vision Training, Evaluation Protocol=Zero-shot2023.0417.5
ESZSLLabel embedding=Attribute, Visual feature=Fisher Vector, Transductive=false, Data augmentation=false2016.1117.1
IAPLabel embedding=Attribute, Visual feature=Fisher Vector, Transductive=false, Data augmentation=false2016.1116.7
SVELabel embedding=Word-vector, Visual feature=Bag of Words, Transductive=false, Data augmentation=true2016.1116.5
DAPLabel embedding=Attribute, Visual feature=Fisher Vector, Transductive=false, Data augmentation=false2016.1115.9
MTELabel embedding=Word-vector, Visual feature=Fisher Vector, Transductive=false, Data augmentation=false2016.1115.8
ZSECOCTraining Paradigm=Vision Training, Evaluation Protocol=Zero-shot2023.0415.1
ESZSLLabel embedding=Word-vector, Visual feature=Fisher Vector, Transductive=false, Data augmentation=false2016.1115
HAALabel embedding=Attribute, Visual feature=Fisher Vector, Transductive=false, Data augmentation=false2016.1114.9
UDALabel embedding=Attribute + Word-vector, Visual feature=Fisher Vector, Transductive=true, Data augmentation=false2016.1114
UDALabel embedding=Attribute, Visual feature=Fisher Vector, Transductive=true, Data augmentation=false2016.1113.2
SVELabel embedding=Word-vector, Visual feature=Bag of Words, Transductive=true, Data augmentation=false2016.1113.1
SVELabel embedding=Word-vector, Visual feature=Bag of Words, Transductive=false, Data augmentation=false2016.1112
SJELabel embedding=Attribute, Visual feature=Fisher Vector, Transductive=false, Data augmentation=false2016.1112
SJELabel embedding=Word-vector, Visual feature=Fisher Vector, Transductive=false, Data augmentation=false2016.119.9