srijandas07

VPN

Pose driven attention mechanism

vpnplusplus

This is a repo of extension of VPN for Recognition of Activities of Daily Living

LSTM_action_recognition

Compute action classification accuracy from skeleton joints using LSTM

clip_baseline_LTA_Ego4d

Video + CLIP Baseline for Ego4D Long Term Action Anticipation Challenge (CVPR 2022)

i3d

Train I3D on NTU-RGB+D dataset in keras

i3d_smarthome

Pytorch I3D implmentation on Toyota Smarthome Dataset

P-I3D

Where to focus on for Human Action Recognition?

temporal_model

Temporal Model for Action Recognition (WACV 2020)

i3d_test

Test pre-trained NTU i3d model for action recognition

improved_P-CNN

NTURGB-D

Info and sample codes for "NTU RGB+D Action Recognition Dataset"

Pyvideoresearch_new

The master PyVideoresearch is committed with few changes in this repository in order to make use of the pre-trained models.

st-gcn

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

tokenlearner

Charades_i3d

CoCLR

[NeurIPS'20] Self-supervised Co-Training for Video Representation Learning. Tengda Han, Weidi Xie, Andrew Zisserman.

mae-1

PyTorch implementation of MAE https//arxiv.org/abs/2111.06377

srijandas07.github.io

video_convolution

Simplest video representation using frame-level convolutional feature extraction followed by max-min pooling.