136 Open source projects that are alternatives of or similar to Tdn

Paper list of activity prediction and related area

Temporal Segment Networks (TSN) in PyTorch

What and How Well You Performed? A Multitask Learning Approach to Action Quality Assessment [CVPR 2019]

A collection of recent video understanding datasets, under construction!

[ICCV 2021 Oral] Deep Evidential Action Recognition

A curated list of action recognition and related area resources

ActionVLAD for video action classification (CVPR 2017)

OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark

TensorFlow code for finetuning I3D model on UCF101.

Code & Models for Temporal Segment Networks (TSN) in ECCV 2016

An open-source toolbox for action understanding based on PyTorch

A new codebase for Group Activity Recognition. It contains codes for ICCV 2021 paper: Spatio-Temporal Dynamic Inference Network for Group Activity Recognition and some other methods.

STEP: Spatio-Temporal Progressive Learning for Video Action Detection. CVPR'19 (Oral)

Tools for movie and video research

Comprehensive, latest, and deployable video deep learning algorithm, including video recognition, action localization, and temporal action detection tasks. It's a high-performance, light-weight codebase provides practical models for video understanding research and application

temporal action detection with SSN

Identifying Visible Actions in Lifestyle Vlogs

Gluon CV Toolkit

ICCV 19 Grouped Spatial-Temporal Aggretation for Efficient Action Recognition

NTU-X, which is an extended version of popular NTU dataset

Video classification tools using 3D ResNet

Apply ML to the skeletons from OpenPose; 9 actions; multiple people. (WARNING: I'm sorry that this is only good for course demo, not for real world applications !!! Those ary very difficult !!!)

Learning Video Representations from Correspondence Proposals (CVPR 2019 Oral)

End-to-end Temporal Action Detection with Transformer. [Under review for a journal publication]

[TPAMI Special Issue on ICCV 2021 Best Papers, Oral] Just Ask: Learning to Answer Questions from Millions of Narrated Videos

Deep Convolutional Bidirectional LSTM for Complex Activity Recognition with Missing Data. Human Activity Recognition Challenge. Springer SIST (2020)

CP-360-Weakly-Supervised-Saliency

Tutorial for video classification/ action recognition using 3D CNN/ CNN+RNN on UCF101

基于kinect 的人体 动作识别

Use 3D ResNet to extract features of UCF101 and HMDB51 and then classify them.

Deep Learning for Computer Vision (CommE 5052) in NTU

PyTorch implementation of two-stream networks for video action recognition

An implementation of the LRCN in Torch

Training Toolbox for Caffe

A curated list of “Temporally Language Grounding” and related area

Temporal Segments LSTM and Temporal-Inception for Activity Recognition

REPresentAtion bIas Removal (REPAIR) of datasets

ResGCN: an efficient baseline for skeleton-based human action recognition.

Hierarchical Co-occurrence Network with Prototype Loss for Few-shot Learning (PyTorch)

Action recognition using soft attention based deep recurrent neural networks

The official PyTorch implementation of "Context Matters: Self-Attention for sign Language Recognition"

No description or website provided.

Skeleton-based Action Recognition

code for CVPR-2019 paper: Self-supervised Spatio-temporal Representation Learning for Videos by Predicting Motion and Appearance Statistics

EPIC-KITCHENS-55 baselines for Action Recognition

Surveillance System Against Violence

Temporal Convolutional Feature Pyramid Network (TCFPN) & Iterative Soft Boundary Assignment (ISBA), CVPR '18

Official PyTorch code for the ICIP 2021 paper 'Syntactically Guided Generative Embeddings For Zero Shot Skeleton Action Recognition'

Action recognition.基于C3D的视频动作识别

This repository host the code for real-time action detection paper

Code for AdaScan: Adaptive Scan Pooling (CVPR 2017)

ICCV2021/2019/2017 论文/代码/解读/直播合集，极市团队整理

3D ResNets for Action Recognition (CVPR 2018)

Two Stream CNN implemented in Keras using in skeleton-based action recognition with dataset NTU RGB+D

Detects Chinese traffic police commanding poses 检测中国交警指挥手势

Using two stream architecture to implement a classic action recognition method on UCF101 dataset

A Repository for maintaining various human skeleton preprocessing steps in numpy and tensorflow along with tensorflow model to learn pose embeddings.

Count pushups from video/webcam. Tech stack: Keypoint detection, BlazePose, action recognition.

experiments on classifying actions using poses

Useful Toolbox for Anomaly Detection