Trending repositories for topic action-recognition

The collection of pre-trained, state-of-the-art AI models for ailia SDK

OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark

CVPR 2023-2024 Papers: Dive into advanced research presented at the leading computer vision conference. Keep up to date with the latest developments in computer vision and deep learning. Code included...

Applying Deep Learning Approaches to Volleyball Data

A curated paper list of awesome skeleton-based action recognition.

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

Awesome video understanding toolkits based on PaddlePaddle. It supports video data annotation tools, lightweight RGB and skeleton based action recognition model, practical applications for video taggi...

A curated list of action recognition and related area resources

Applying Deep Learning Approaches to Volleyball Data

CVPR 2023-2024 Papers: Dive into advanced research presented at the leading computer vision conference. Keep up to date with the latest developments in computer vision and deep learning. Code included...

A curated paper list of awesome skeleton-based action recognition.

The collection of pre-trained, state-of-the-art AI models for ailia SDK

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

Awesome video understanding toolkits based on PaddlePaddle. It supports video data annotation tools, lightweight RGB and skeleton based action recognition model, practical applications for video taggi...

OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark

A curated list of action recognition and related area resources

OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark

The collection of pre-trained, state-of-the-art AI models for ailia SDK

[ECCV2024] Video Foundation Models & Data for Multimodal Understanding

[NeurIPS 2022 Spotlight] VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training

Awesome video understanding toolkits based on PaddlePaddle. It supports video data annotation tools, lightweight RGB and skeleton based action recognition model, practical applications for video taggi...

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

A curated list of action recognition and related area resources

[CVPR 2023] VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking

A OpenMMLAB toolbox for human pose estimation, skeleton-based action recognition, and action synthesis.

Applying Deep Learning Approaches to Volleyball Data

A list of Human-Object Interaction Learning.

Data preparation and loader for AMASS

A toolbox for skeleton-based action recognition.

[IJCV 2021] SportsCap: Monocular 3D Human Motion Capture and Fine-grained Understanding in Challenging Sports Videos

An open-source toolbox for action understanding based on PyTorch

Applying Deep Learning Approaches to Volleyball Data

[IJCV 2021] SportsCap: Monocular 3D Human Motion Capture and Fine-grained Understanding in Challenging Sports Videos

[ECCV2024] Video Foundation Models & Data for Multimodal Understanding

[NeurIPS 2022 Spotlight] VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training

[CVPR 2023] VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking

The collection of pre-trained, state-of-the-art AI models for ailia SDK

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

Awesome video understanding toolkits based on PaddlePaddle. It supports video data annotation tools, lightweight RGB and skeleton based action recognition model, practical applications for video taggi...

A list of Human-Object Interaction Learning.

OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark

Data preparation and loader for AMASS

A toolbox for skeleton-based action recognition.

A curated list of action recognition and related area resources

A OpenMMLAB toolbox for human pose estimation, skeleton-based action recognition, and action synthesis.

An open-source toolbox for action understanding based on PyTorch

OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark

[ECCV2024] Video Foundation Models & Data for Multimodal Understanding

The collection of pre-trained, state-of-the-art AI models for ailia SDK

[NeurIPS 2022 Spotlight] VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training

Awesome video understanding toolkits based on PaddlePaddle. It supports video data annotation tools, lightweight RGB and skeleton based action recognition model, practical applications for video taggi...

A toolbox for skeleton-based action recognition.

[CVPR 2023] VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking

A curated paper list of awesome skeleton-based action recognition.

A curated list of action recognition and related area resources

Gluon CV Toolkit

CVPR 2023-2024 Papers: Dive into advanced research presented at the leading computer vision conference. Keep up to date with the latest developments in computer vision and deep learning. Code included...

A list of Human-Object Interaction Learning.

3D ResNets for Action Recognition (CVPR 2018)

Data preparation and loader for AMASS

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

A OpenMMLAB toolbox for human pose estimation, skeleton-based action recognition, and action synthesis.

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 !!!)

Implemented a CNN-LSTM Action Recognizer for dynamic motion analysis, integrating convolutional and recurrent neural networks to efficiently recognize and classify actions in video data of UCF101 data...

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

An open-source toolbox for action understanding based on PyTorch

Implemented a CNN-LSTM Action Recognizer for dynamic motion analysis, integrating convolutional and recurrent neural networks to efficiently recognize and classify actions in video data of UCF101 data...

autoupdate paper list

A systematic collection of various skeleton-based models (Datasets, Papers, Codes, Leaderboards).

[ECCV2024] Video Foundation Models & Data for Multimodal Understanding

Fitness Action Quality Assessment or your AI-Fitness Coach [ECCV 2022]

A curated paper list of awesome skeleton-based action recognition.

CVPR 2023-2024 Papers: Dive into advanced research presented at the leading computer vision conference. Keep up to date with the latest developments in computer vision and deep learning. Code included...

[CVPR 2023] VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking

[CVPR2022] Animal Kingdom: A Large and Diverse Dataset for Animal Behavior Understanding

[NeurIPS 2022 Spotlight] VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training

[CVPR 2021] Multi-shot Temporal Event Localization: a Benchmark

A list of Human-Object Interaction Learning.

The collection of pre-trained, state-of-the-art AI models for ailia SDK

Gather research papers, corresponding codes (if having), reading notes and any other related materials about Hot🔥🔥🔥 fields in Computer Vision based on Deep Learning.

A toolbox for skeleton-based action recognition.

Awesome video understanding toolkits based on PaddlePaddle. It supports video data annotation tools, lightweight RGB and skeleton based action recognition model, practical applications for video taggi...

OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark

[KDD 2023] FedMultimodal

Offical implementation of paper "MSAF: Multimodal Split Attention Fusion"

[ICLR 2022] TAda! Temporally-Adaptive Convolutions for Video Understanding. This codebase provides solutions for video classification, video representation learning and temporal detection.

autoupdate paper list

Implemented a CNN-LSTM Action Recognizer for dynamic motion analysis, integrating convolutional and recurrent neural networks to efficiently recognize and classify actions in video data of UCF101 data...

[ECCV2024] Video Foundation Models & Data for Multimodal Understanding

OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark

The collection of pre-trained, state-of-the-art AI models for ailia SDK

CVPR 2023-2024 Papers: Dive into advanced research presented at the leading computer vision conference. Keep up to date with the latest developments in computer vision and deep learning. Code included...

[NeurIPS 2022 Spotlight] VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training

[CVPR 2023] VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking

A toolbox for skeleton-based action recognition.

Awesome video understanding toolkits based on PaddlePaddle. It supports video data annotation tools, lightweight RGB and skeleton based action recognition model, practical applications for video taggi...

A curated paper list of awesome skeleton-based action recognition.

A curated list of action recognition and related area resources

3D ResNets for Action Recognition (CVPR 2018)

Gluon CV Toolkit

Data preparation and loader for AMASS

A OpenMMLAB toolbox for human pose estimation, skeleton-based action recognition, and action synthesis.

A list of Human-Object Interaction Learning.

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

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 !!!)

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

Generic PyTorch dataset implementation to load and augment VIDEOS for deep learning training loops.

【AAAI'2023 & IJCV】Transferring Vision-Language Models for Visual Recognition: A Classifier Perspective

CVPR 2023-2024 Papers: Dive into advanced research presented at the leading computer vision conference. Keep up to date with the latest developments in computer vision and deep learning. Code included...

【ICCV'2023】What Can Simple Arithmetic Operations Do for Temporal Modeling?

[KDD 2023] FedMultimodal

[ECCV2024] Video Foundation Models & Data for Multimodal Understanding

Fitness Action Quality Assessment or your AI-Fitness Coach [ECCV 2022]

A curated paper list of awesome skeleton-based action recognition.

[CVPR 2023] VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking

SoccerNet@CVPR | 1st place solution for Ball Action Spotting Challenge 2023

Gather research papers, corresponding codes (if having), reading notes and any other related materials about Hot🔥🔥🔥 fields in Computer Vision based on Deep Learning.

[CVPR2023] Masked Video Distillation: Rethinking Masked Feature Modeling for Self-supervised Video Representation Learning (https://arxiv.org/abs/2212.04500)

Applying Deep Learning Approaches to Volleyball Data

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

Official code for "Action Transformer: A Self-attention Model for Short-time Pose-based Human Action Recognition", Pattern Recognition (2022).

【AAAI'2023 & IJCV】Transferring Vision-Language Models for Visual Recognition: A Classifier Perspective

[CVPR 2023] STMixer: A One-Stage Sparse Action Detector

[CVPR2022] Animal Kingdom: A Large and Diverse Dataset for Animal Behavior Understanding

deep learning sex position classifier

A systematic collection of various skeleton-based models (Datasets, Papers, Codes, Leaderboards).

CricShot10 is a video action recognition dataset consisting of 10 cricket batting shots. This dataset was developed using the videos from YouTube.

GolfDB is a video database for Golf Swing Sequencing, which involves detecting 8 golf swing events in trimmed golf swing videos. This repo demos the baseline model, SwingNet.