pose2actionexperiments on classifying actions using poses
Stars: ✭ 24 (+50%)
ailia-modelsThe collection of pre-trained, state-of-the-art AI models for ailia SDK
Stars: ✭ 1,102 (+6787.5%)
torch-lrcnAn implementation of the LRCN in Torch
Stars: ✭ 85 (+431.25%)
bLVNet-TAMThe official Codes for NeurIPS 2019 paper. Quanfu Fan, Ricarhd Chen, Hilde Kuehne, Marco Pistoia, David Cox, "More Is Less: Learning Efficient Video Representations by Temporal Aggregation Modules"
Stars: ✭ 54 (+237.5%)
tfvaegan[ECCV 2020] Official Pytorch implementation for "Latent Embedding Feedback and Discriminative Features for Zero-Shot Classification". SOTA results for ZSL and GZSL
Stars: ✭ 107 (+568.75%)
conv3d-video-action-recognitionMy experimentation around action recognition in videos. Contains Keras implementation for C3D network based on original paper "Learning Spatiotemporal Features with 3D Convolutional Networks", Tran et al. and it includes video processing pipelines coded using mPyPl package. Model is being benchmarked on popular UCF101 dataset and achieves result…
Stars: ✭ 50 (+212.5%)
synse-zslOfficial PyTorch code for the ICIP 2021 paper 'Syntactically Guided Generative Embeddings For Zero Shot Skeleton Action Recognition'
Stars: ✭ 14 (-12.5%)
auditory-slow-fastImplementation of "Slow-Fast Auditory Streams for Audio Recognition, ICASSP, 2021" in PyTorch
Stars: ✭ 46 (+187.5%)
Pose2vecA Repository for maintaining various human skeleton preprocessing steps in numpy and tensorflow along with tensorflow model to learn pose embeddings.
Stars: ✭ 25 (+56.25%)
gzsl-odOut-of-Distribution Detection for Generalized Zero-Shot Action Recognition
Stars: ✭ 47 (+193.75%)
DLCV2018SPRINGDeep Learning for Computer Vision (CommE 5052) in NTU
Stars: ✭ 38 (+137.5%)
Squeeze-and-Recursion-Temporal-GatesCode for : [Pattern Recognit. Lett. 2021] "Learn to cycle: Time-consistent feature discovery for action recognition" and [IJCNN 2021] "Multi-Temporal Convolutions for Human Action Recognition in Videos".
Stars: ✭ 62 (+287.5%)
Gluon CvGluon CV Toolkit
Stars: ✭ 5,001 (+31156.25%)
Action-LocalizationAction-Localization, Atomic Visual Actions (AVA) Dataset
Stars: ✭ 22 (+37.5%)
TadTREnd-to-end Temporal Action Detection with Transformer. [Under review for a journal publication]
Stars: ✭ 55 (+243.75%)
MUSES[CVPR 2021] Multi-shot Temporal Event Localization: a Benchmark
Stars: ✭ 51 (+218.75%)
3d Resnets Pytorch3D ResNets for Action Recognition (CVPR 2018)
Stars: ✭ 3,169 (+19706.25%)
MiCT-Net-PyTorchVideo Recognition using Mixed Convolutional Tube (MiCT) on PyTorch with a ResNet backbone
Stars: ✭ 48 (+200%)
video repres mascode for CVPR-2019 paper: Self-supervised Spatio-temporal Representation Learning for Videos by Predicting Motion and Appearance Statistics
Stars: ✭ 63 (+293.75%)
TCFPN-ISBATemporal Convolutional Feature Pyramid Network (TCFPN) & Iterative Soft Boundary Assignment (ISBA), CVPR '18
Stars: ✭ 40 (+150%)
adascan-publicCode for AdaScan: Adaptive Scan Pooling (CVPR 2017)
Stars: ✭ 43 (+168.75%)
Two-Stream-CNNTwo Stream CNN implemented in Keras using in skeleton-based action recognition with dataset NTU RGB+D
Stars: ✭ 75 (+368.75%)
pushup-counter-appCount pushups from video/webcam. Tech stack: Keypoint detection, BlazePose, action recognition.
Stars: ✭ 48 (+200%)
Video ClassificationTutorial for video classification/ action recognition using 3D CNN/ CNN+RNN on UCF101
Stars: ✭ 543 (+3293.75%)
UAV-Human[CVPR2021] UAV-Human: A Large Benchmark for Human Behavior Understanding with Unmanned Aerial Vehicles
Stars: ✭ 122 (+662.5%)
GST-videoICCV 19 Grouped Spatial-Temporal Aggretation for Efficient Action Recognition
Stars: ✭ 40 (+150%)
TCEThis repository contains the code implementation used in the paper Temporally Coherent Embeddings for Self-Supervised Video Representation Learning (TCE).
Stars: ✭ 51 (+218.75%)
dynamic-images-for-action-recognitionA public Python implementation for generating Dynamic Images introduced in 'Dynamic Image Networks for Action Recognition' by Bilen et al.
Stars: ✭ 27 (+68.75%)
ntu-xNTU-X, which is an extended version of popular NTU dataset
Stars: ✭ 55 (+243.75%)
MTL-AQAWhat and How Well You Performed? A Multitask Learning Approach to Action Quality Assessment [CVPR 2019]
Stars: ✭ 38 (+137.5%)
Mmaction2OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark
Stars: ✭ 684 (+4175%)
Openpose-based-GUI-for-Realtime-Pose-Estimate-and-Action-RecognitionGUI based on the python api of openpose in windows using cuda10 and cudnn7. Support body , hand, face keypoints estimation and data saving. Realtime gesture recognition is realized through two-layer neural network based on the skeleton collected from the gui.
Stars: ✭ 69 (+331.25%)
cpnetLearning Video Representations from Correspondence Proposals (CVPR 2019 Oral)
Stars: ✭ 93 (+481.25%)
ViCC[WACV'22] Code repository for the paper "Self-supervised Video Representation Learning with Cross-Stream Prototypical Contrasting", https://arxiv.org/abs/2106.10137.
Stars: ✭ 33 (+106.25%)
MSAFOffical implementation of paper "MSAF: Multimodal Split Attention Fusion"
Stars: ✭ 47 (+193.75%)
Robust-Deep-Learning-PipelineDeep Convolutional Bidirectional LSTM for Complex Activity Recognition with Missing Data. Human Activity Recognition Challenge. Springer SIST (2020)
Stars: ✭ 20 (+25%)
VideoTransformer-pytorchPyTorch implementation of a collections of scalable Video Transformer Benchmarks.
Stars: ✭ 159 (+893.75%)
Two Stream PytorchPyTorch implementation of two-stream networks for video action recognition
Stars: ✭ 428 (+2575%)
C3D-tensorflowAction recognition with C3D network implemented in tensorflow
Stars: ✭ 34 (+112.5%)
Dataset-REPAIRREPresentAtion bIas Removal (REPAIR) of datasets
Stars: ✭ 49 (+206.25%)
DEAR[ICCV 2021 Oral] Deep Evidential Action Recognition
Stars: ✭ 36 (+125%)
sanThe official PyTorch implementation of "Context Matters: Self-Attention for sign Language Recognition"
Stars: ✭ 17 (+6.25%)
Two Stream Action RecognitionUsing two stream architecture to implement a classic action recognition method on UCF101 dataset
Stars: ✭ 705 (+4306.25%)
Realtime Action RecognitionApply 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 !!!)
Stars: ✭ 417 (+2506.25%)
DIN-Group-Activity-Recognition-BenchmarkA 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.
Stars: ✭ 26 (+62.5%)