zzzzjw

action-recognition-compressed-domain

Code for submission of Neurips 2019 paper entitled "Accelerating Action Recognition In The Compressed Domain"

BIKE

【CVPR'2023】Bidirectional Cross-Modal Knowledge Exploration for Video Recognition with Pre-trained Vision-Language Models

PyTorch-tSNE

SHMetro

Shanghai Metro Visualization

st-gcn

Spatial Temporal Graph Convolutional Networks (ST-GCN) for Skeleton-Based Action Recognition in PyTorch

T2T-ViT

ICCV2021, Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet

Visualizing-Filters-and-Feature-Maps-in-Convolutional-Neural-Networks-using-PyTorch

vit-explain

Explainability for Vision Transformers

vit-visualization

Vita-CLIP

Official repository for "Vita-CLIP: Video and text adaptive CLIP via Multimodal Prompting" [CVPR 2023]

zzzzjw/action-recognition-compressed-domain

Code for submission of Neurips 2019 paper entitled "Accelerating Action Recognition In The Compressed Domain"

zzzzjw/BIKE

【CVPR'2023】Bidirectional Cross-Modal Knowledge Exploration for Video Recognition with Pre-trained Vision-Language Models

zzzzjw/PyTorch-tSNE

zzzzjw/SHMetro

Shanghai Metro Visualization

zzzzjw/st-gcn

Spatial Temporal Graph Convolutional Networks (ST-GCN) for Skeleton-Based Action Recognition in PyTorch

zzzzjw/T2T-ViT

ICCV2021, Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet

zzzzjw/Visualizing-Filters-and-Feature-Maps-in-Convolutional-Neural-Networks-using-PyTorch

zzzzjw/vit-explain

Explainability for Vision Transformers

zzzzjw/vit-visualization

zzzzjw/Vita-CLIP

Official repository for "Vita-CLIP: Video and text adaptive CLIP via Multimodal Prompting" [CVPR 2023]