PyTorch implementation for "ECO: Efficient Convolutional Network for Online Video Understanding", ECCV 2018 https://github.com/zhang-can/ECO-pytorch
- Frame-Recurrent Video Super-Resolution https://github.com/msmsajjadi/frvsr https://ei.is.tuebingen.mpg.de/~msajjadi
用AI分析足球视频，AI在体育这块的应用还有很大的前景 https://www.bilibili.com/video/BV1A64y1M78H/
R-C3D: Region Convolutional 3D Network for Temporal Activity Detection https://github.com/VisionLearningGroup/R-C3D
PyTorch 行为识别模型库 https://github.com/coderSkyChen/Action_Recognition_Zoo
Optical Flow Guided Feature: A Fast and Robust Motion Representation for Video Action Recognition https://github.com/kevin-ssy/Optical-Flow-Guided-Feature
Multi-Fiber Networks for Video Recognition https://github.com/cypw/PyTorch-MFNet
Code and models of paper " ECO: Efficient Convolutional Network for Online Video Understanding", ECCV 2018 https://github.com/mzolfaghari/ECO-efficient-video-understanding
SlowFast-Networks Reproduce slowfast networks in pytorch(unofficial) https://github.com/Guocode/SlowFast-Networks
This repo holds the codes of paper: "BSN: Boundary Sensitive Network for Temporal Action Proposal Generation", which is accepted in ECCV 2018. You can also find pytorch-version implementation in [BSN.pytorch]. https://github.com/wzmsltw/BSN-boundary-sensitive-network
Unofficial example code for using a pre-trained Distilled 3D Network (D3D) for video classification. https://github.com/princeton-vl/d3dhelper
X-Temporal：开源视频分类/理解代码包 https://github.com/Sense-X/X-Temporal
PyTorch implementation of "SlowFast Networks for Video Recognition". https://github.com/r1ch88/SlowFastNetworks
Stochastic Adversarial Video Prediction 预测生成视频下面的内容，可以做视频插值 https://github.com/alexlee-gk/video_prediction
Deep Video Analytics是个视频分析平台，能够从视频和图像中抽取并索引信息。可以用于视频搜索、视频识别检测、OCR等。 https://github.com/AKSHAYUBHAT/DeepVideoAnalytics
深度学习NBA球员行为识别/统计 https://github.com/neeilan/DeepPlayByPlay
ECO: Efficient Convolutional Network for Online Video Understanding https://github.com/mzolfaghari/ECO-pytorch
视频研究常用方法、数据集和任务汇总 https://github.com/gsig/PyVideoResearch
Tutorial for video classification/ action recognition using 3D CNN/ CNN+RNN on UCF101 https://github.com/HHTseng/video-classification
深度学习视频高效加载器 https://github.com/zhreshold/decord
Decoupling Localization and Classification in Single Shot Temporal Action Detection https://github.com/HYPJUDY/Decouple-SSAD
R-C3D pytorch implementation https://github.com/sunnyxiaohu/R-C3D.pytorch
Python/OpenCV实现的视频场景检测与分析 https://github.com/Breakthrough/PySceneDetect
MMAction：PyTorch开源视频行为识别工具包 https://github.com/open-mmlab/mmaction
视频分析/多模态学习论文、代码、数据集大列表 https://github.com/HuaizhengZhang/Awsome-Deep-Learning-for-Video-Analysis
VideoGraph: Recognizing Minutes-Long Human Activities in Videos, ICCV 2019 Workshop https://github.com/noureldien/videograph
STCN: Stochastic Temporal Convolutional Networks https://github.com/emreaksan/stcn
PyTorch实现的C3D, R3D, R2Plus1D视频行为识别 https://github.com/jfzhang95/pytorch-video-recognition
Resources about activity recognition-行为识别资料汇总’ https://github.com/jindongwang/activityrecognition
【视频架构搜索】《Video Architecture Search | Google AI Blog》 https://github.com/google-research/google-research/tree/master/evanet
Facebook 开源 SlowFast：双帧率分析视频识别 https://github.com/facebookresearch/SlowFast
This is the official repo for "S3D: Single Shot multi-Span Detector via Fully 3D Convolutional Network" https://github.com/dazhang-cv/S3D
code for learning trajectory dependencies for human motion prediction https://github.com/wei-mao-2019/LearnTrajDep
Code and models for our CVPR'19 paper "Representation Flow for Action Recognition" https://github.com/piergiaj/representation-flow-cvpr19
"Attention in Convolutional LSTM for Gesture Recognition" in NIPS 2018 https://github.com/GuangmingZhu/AttentionConvLSTM
Code and models for our ICCV'19 paper "Evolving Space-Time Neural Architectures for Videos" https://github.com/piergiaj/evanet-iccv19
Unofficial PyTorch implementation of the CVPR'19 paper "Skeleton-Based Action Recognition with Directed Graph Neural Networks". https://github.com/kenziyuliu/DGNN-PyTorch
This repo contains a PyTorch S3D Text-Video model trained from scratch on HowTo100M using MIL-NCE https://github.com/antoine77340/S3D_HowTo100M
A Faster Pytorch Implementation of R-C3D https://github.com/sunnyxiaohu/R-C3D.pytorch
Pytorch code for End-to-End Audiovisual Speech Recognition https://github.com/mpc001/end-to-end-lipreading
NSD: Neural Scene Decomposition for Human Motion Capture https://github.com/hrhodin/NeuralSceneDecomposition
I3D implemetation in Keras + video preprocessing + visualization of results https://github.com/oanaignat/i3d_keras
https://github.com/NVlabs/STEP
Repository for the paper "Adversarial Framing for Image and Video Classification" https://github.com/zajaczajac/adv_framing
'IG-65M PyTorch - PyTorch 3D video classification models pre-trained on 65 million Instagram videos' https://github.com/moabitcoin/ig65m-pytorch
Keras深度学习视频分类 https://www.pyimagesearch.com/2019/07/15/video-classification-with-keras-and-deep-learning/
简易快速的视频深度特征抽取 https://github.com/antoine77340/video_feature_extractor
Code for the paper "High Speed and High Dynamic Range Video with an Event Camera" (arXiv, 2019). http://rpg.ifi.uzh.ch/E2VID.html https://github.com/uzh-rpg/rpg_e2vid
Timeception for Complex Action Recognition https://github.com/noureldien/timeception
MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentation https://github.com/yabufarha/ms-tcn
Deep Spatio-Temporal Neural Network (DSTN) https://github.com/oywtece/dstn
Learning to align and match videos with kernelized temporal layers https://github.com/facebookresearch/videoalignment
Self-supervised Spatiotemporal Learning via Video Clip Order Prediction https://github.com/xudejing/video-clip-order-prediction
Real-time Hand Gesture Recognition with PyTorch on EgoGesture, NvGesture and Jester https://arxiv.org/abs/1901.10323
https://github.com/ahmetgunduz/Real-time-GesRec
【MMAction2：下一代行为理解工具箱和基准】 https://github.com/open-mmlab/mmaction2
Temporal Pyramid Network for Action Recognition https://github.com/decisionforce/TPN
Code repository for the paper: 'Something-Else: Compositional Action Recognition with Spatial-Temporal Interaction Networks' https://github.com/joaanna/something_else
Zero-shot video classification by end-to-end training of 3D convolutional neural networks https://github.com/bbrattoli/ZeroShotVideoClassification
Spatio-Temporal Action Localization System https://github.com/MVIG-SJTU/AlphAction
Gate-Shift Networks for Video Action Recognition - CVPR 2020 https://github.com/swathikirans/GSM
Learn to cycle: Time-consistent feature discovery for action recognition https://github.com/alexandrosstergiou/Squeeze-and-Recursion-Temporal-Gates
We present a new action tubelet detection framework, termed as MovingCenter Detector (MOC-detector), by treating an action instance as a trajectory of moving points.
https://github.com/MCG-NJU/MOC-Detector
Repository for PREDICT & CLUSTER: Unsupervised Skeleton Based Action Recognition https://github.com/shlizee/Predict-Cluster
The code for our paper 《Self-Supervised Temporal-Discriminative Representation Learning for Video Action Recognition》
The Pytorch code of the TEA module (Temporal Excitation and Aggregation for Action Recognition) https://github.com/Phoenix1327/tea-action-recognition
Official repo for ECCV 2020 paper - RubiksNet: Learnable 3D-Shift for Efficient Video Action Recognition https://github.com/StanfordVL/RubiksNet
基于PyTorch的电影/视频研究工具集 https://github.com/movienet/movienet-tools
Kubric：数据生成管道，用于创建带有丰富标注的半真实合成多目标视频，如实例分割掩码、深度图和光流等 https://github.com/google-research/kubric
PaddleVideo：飞桨视频模型开发套件 https://github.com/PaddlePaddle/PaddleVideo
https://github.com/tobyperrett/trx
An Efficient PointLSTM for Point Clouds Based Gesture Recognition https://github.com/Blueprintf/pointlstm-gesture-recognition-pytorch
Boundary-Aware Cascade Networks for Temporal Action Segmentation https://github.com/MCG-NJU/BCN
Official repo for ECCV 2020 paper - RubiksNet: Learnable 3D-Shift for Efficient Video Action Recognition https://github.com/StanfordVL/RubiksNet
This repository contains the code implementation used in the paper Temporally Coherent Embeddings for Self-Supervised Video Representation Learning (TCE). https://github.com/csiro-robotics/TCE
MotionSqueeze: Neural Motion Feature Learning for Video Understanding https://github.com/arunos728/MotionSqueeze
Pytorch implementation of [Late Temporal Modeling in 3D CNN Architectures with BERT for Action Recognition] https://github.com/artest08/LateTemporalModeling3DCNN
This repository contains a PyTorch implementation for "X3D: Expanding Architectures for Efficient Video Recognition models" https://github.com/kkahatapitiya/X3D-Multigrid
Efficient 3D Backbone Network for Temporal Modeling https://github.com/youngwanLEE/VoV3D
MS-TCN++: Multi-Stage Temporal Convolutional Network for Action Segmentation (TPAMI 2020) https://github.com/sj-li/MS-TCN2
Motion capture from internet videos https://github.com/zju3dv/EasyMocap
A Closer Look at Temporal Sentence Grounding in Videos: Datasets and Metrics https://github.com/yytzsy/grounding_changing_distribution
TimeSformer：视频理解新架构 TimeSformer: A new architecture for video understanding https://ai.facebook.com/blog/timesformer-a-new-architecture-for-video-understanding
TimeSformer：视频理解新架构 https://arxiv.org/abs/2102.05095
github.com/MCG-NJU/TDN
《Monocular Real-time Hand Shape and Motion Capture using Multi-modal Data》(2021) github.com/MengHao666/Minimal-Hand-pytorch
DeepLabCut: 用于执行多种任务的动物无标记姿态估计工具箱 github.com/DeepLabCut/DeepLabCut
MVFNet: Multi-View Fusion Network for Efficient Video Recognition (AAAI 2021) github.com/whwu95/MVFNet
《TransNet V2: Shot Boundary Detection Neural Network》(2020) github.com/soCzech/TransNetV2
PyTorchVideo：深度学习视频理解库 github.com/facebookresearch/pytorchvideo
外科视频分析相关文献集 github.com/Finspire13/Awesome-Surgical-Video-Analysis
github.com/vt-vl-lab/video-data-aug
github.com/ShangHua-Gao/G2L-search
《Learning Salient Boundary Feature for Anchor-free Temporal Action Localization》(CVPR 2021) github.com/TencentYoutuResearch/ActionDetection-AFSD
《Vid2Doppler: Synthesizing Doppler Radar Data from Videos for Training Privacy-Preserving Activity Recognition》(2021) github.com/FIGLAB/Vid2Doppler
Keras实例：CNN-RNN架构实现视频分类 https://keras.io/examples/vision/video_classification/
《Beyond Self-attention: External Attention using Two Linear Layers for Visual Tasks》(2021) github.com/MenghaoGuo/EANet
DMVR: DeepMind视频数据读取模块 github.com/deepmind/dmvr
Video Contrastive Learning with Global Context github.com/amazon-research/ video-contrastive-learning
Token Shift Transformer for Video Classification github.com/VideoNetworks/TokShift-Transformer
github.com/datamllab/autovideo
Revisiting 3D ResNets for Video Recognition github.com/tensorflow/models/tree/master/official
EssentialMC2：视频理解系统 github.com/alibaba/EssentialMC2
https://ai.googleblog.com/2022/03/co-training-transformer-with-videos-and.html
'video-transformers - Easiest way of fine-tuning HuggingFace video classification models' by fatih GitHub: github.com/fcakyon/video-transformers
提出一种新的流视频模型，用于统一处理基于帧和序列的视频理解任务。 https://arxiv.org/abs/2303.17228 [CV]《Streaming Video Model》Y Zhao, C Luo, C Tang, D Chen, N Codella, Z Zha [Microsoft Research Asia] (2023)