Statistics for topic action-recognition

RepositoryStats tracks 635,088 Github repositories, of these 110 are tagged with the action-recognition topic. The most common primary language for repositories using this topic is Python (85).

Stargazers over time for topic action-recognition

8080707060605050404030302020101000202020202021202120222022202320232024202420252025

Most starred repositories for topic action-recognition (view more)

dmlc
gluon-cv dmlc
1.2k
5.9k
apache-2.0
152
Gluon CV Toolkit
gan gluon mxnet person-reid deep-learning neural-network computer-vision pose-estimation machine-learning object-detection action-recognition image-classification semantic-segmentation
Created 2018-02-26
900 commits to master branch, last one 2 years ago
open-mmlab
mmaction2 open-mmlab
1.3k
4.5k
apache-2.0
40
OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark
ava i3d tsm tsn x3d posec3d pytorch slowfast benchmark non-local openmmlab uniformerv2 deep-learning action-recognition video-understanding video-classification temporal-action-localization spatial-temporal-action-detection
Created 2020-07-11
2,061 commits to main branch, last one about a year ago
kenshohara
3D-ResNets-PyTorch kenshohara
930
4.0k
mit
57
3D ResNets for Action Recognition (CVPR 2018)
python pytorch deep-learning computer-vision video-recognition action-recognition
Created 2017-09-14
432 commits to master branch, last one 4 years ago
jinwchoi
awesome-action-recognition jinwchoi
726
3.9k
unknown
207
A curated list of action recognition and related area resources
awesome awesome-list pose-estimation action-detection video-processing video-recognition action-recognition object-recognition video-understanding activity-recognition action-classification activity-understanding
Created 2016-09-22
296 commits to master branch, last one about a year ago
open-mmlab
mmskeleton open-mmlab
1.0k
3.0k
apache-2.0
70
A OpenMMLAB toolbox for human pose estimation, skeleton-based action recognition, and action synthesis.
pytorch deep-learning action-recognition graph-convolutional-network skeleton-based-action-recognition
Created 2017-11-21
663 commits to master branch, last one 4 years ago
extreme-assistant
ICCV2023-Paper-Code-Interpretation extreme-assistant
1.4k
2.3k
unknown
64
ICCV2021/2019/2017 论文/代码/解读/直播合集，极市团队整理
iccv2017 iccv2019 iccv2021 deep-learning computer-vision machine-learning object-detection image-recognition action-recognition image-segmentation image-classification
Created 2019-04-01
98 commits to master branch, last one about a year ago

Trending repositories for topic action-recognition (view more)

Last 3 days (new repositories)
no newly created repositories trending in the last 3 days
Last 3 days (absolute gain)
open-mmlab
open-mmlab/mmaction2

OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark

4,537 (+9)
apache-2.0
OpenGVLab
OpenGVLab/VideoMAEv2

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

613 (+6)
mit
AdaptiveMotorControlLab
AdaptiveMotorControlLab/LLaVAction

No description

28 (+2)
PaddlePaddle
PaddlePaddle/PaddleVideo

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...

1,603 (+2)
apache-2.0
open-mmlab
open-mmlab/mmskeleton

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

2,981 (+2)
apache-2.0
Last 3 days (relative gain)
AdaptiveMotorControlLab
AdaptiveMotorControlLab/LLaVAction

No description

28 (+8%)
OpenGVLab
OpenGVLab/VideoMAEv2

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

613 (+1.0%)
mit
shukkkur
shukkkur/VolleyVision

Applying Deep Learning Approaches to Volleyball Data

209 (+1.0%)
agpl-3.0
sutdcv
sutdcv/Animal-Kingdom

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

138 (+0.7%)
open-mmlab
open-mmlab/mmaction2

OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark

4,537 (+0.2%)
apache-2.0
Last week (new repositories)
no newly created repositories trending in the last week
Last week (absolute gain)
OpenGVLab
OpenGVLab/InternVideo

[ECCV2024] Video Foundation Models & Data for Multimodal Understanding

1,778 (+17)
apache-2.0
OpenGVLab
OpenGVLab/VideoMAEv2

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

613 (+11)
mit
open-mmlab
open-mmlab/mmaction2

OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark

4,537 (+11)
apache-2.0
AdaptiveMotorControlLab
AdaptiveMotorControlLab/LLaVAction

No description

28 (+4)
MCG-NJU
MCG-NJU/VideoMAE

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

1,464 (+4)
Last week (relative gain)
AdaptiveMotorControlLab
AdaptiveMotorControlLab/LLaVAction

No description

28 (+17%)
shukkkur
shukkkur/VolleyVision

Applying Deep Learning Approaches to Volleyball Data

209 (+2%)
agpl-3.0
OpenGVLab
OpenGVLab/VideoMAEv2

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

613 (+2%)
mit
isLinXu
isLinXu/paper-list

autoupdate paper list

79 (+1%)
apache-2.0
OpenGVLab
OpenGVLab/InternVideo

[ECCV2024] Video Foundation Models & Data for Multimodal Understanding

1,778 (+1.0%)
apache-2.0
Last month (new repositories)
AdaptiveMotorControlLab
AdaptiveMotorControlLab/LLaVAction

No description

28
Last month (absolute gain)
open-mmlab
open-mmlab/mmaction2

OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark

4,537 (+64)
apache-2.0
OpenGVLab
OpenGVLab/InternVideo

[ECCV2024] Video Foundation Models & Data for Multimodal Understanding

1,778 (+59)
apache-2.0
AdaptiveMotorControlLab
AdaptiveMotorControlLab/LLaVAction

No description

28 (+25)
PaddlePaddle
PaddlePaddle/PaddleVideo

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...

1,603 (+25)
apache-2.0
MCG-NJU
MCG-NJU/VideoMAE

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

1,464 (+23)
Last month (relative gain)
usc-sail
usc-sail/fed-multimodal

[KDD 2023] FedMultimodal

104 (+6%)
apache-2.0
isLinXu
isLinXu/paper-list

autoupdate paper list

79 (+5%)
apache-2.0
ruiwang2021
ruiwang2021/mvd

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

124 (+5%)
shukkkur
shukkkur/VolleyVision

Applying Deep Learning Approaches to Volleyball Data

209 (+5%)
agpl-3.0
firework8
firework8/Awesome-Skeleton-based-Action-Recognition

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

503 (+3%)
mit
Last 12-months (new repositories)
AdaptiveMotorControlLab
AdaptiveMotorControlLab/LLaVAction

No description

28
pha123661
pha123661/SA-DVAE

[ECCV 2024] The official repo for "SA-DVAE: Improving Zero-Shot Skeleton-Based Action Recognition by Disentangled Variational Autoencoders"

26
mit
masashi-hatano
masashi-hatano/MM-CDFSL

[ECCV 2024] Official code release for "Multimodal Cross-Domain Few-Shot Learning for Egocentric Action Recognition"

26
mit
Last 12-months (absolute gain)
OpenGVLab
OpenGVLab/InternVideo

[ECCV2024] Video Foundation Models & Data for Multimodal Understanding

1,778 (+921)
apache-2.0
open-mmlab
open-mmlab/mmaction2

OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark

4,537 (+687)
apache-2.0
axinc-ai
axinc-ai/ailia-models

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

2,168 (+385)
MCG-NJU
MCG-NJU/VideoMAE

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

1,464 (+271)
OpenGVLab
OpenGVLab/VideoMAEv2

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

613 (+235)
mit
Last 12-months (relative gain)
isLinXu
isLinXu/paper-list

autoupdate paper list

79 (+778%)
apache-2.0
S1mpleyang
S1mpleyang/ConstructionActionRecognition

This github project aims to recongnize unsafe actions of workers on the construction site.

64 (+146%)
mit
OpenGVLab
OpenGVLab/InternVideo

[ECCV2024] Video Foundation Models & Data for Multimodal Understanding

1,778 (+107%)
apache-2.0
usc-sail
usc-sail/fed-multimodal

[KDD 2023] FedMultimodal

104 (+96%)
apache-2.0
ParitoshParmar
ParitoshParmar/Fitness-AQA

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

69 (+92%)