miracleyoo / Trainable-i3d-pytorch
A re-trainable version version of i3d. It is a superset of kinetics_i3d_pytorch repo from hassony2. You can train on your own dataset, and this repo also provide a complete tool which can generate RGB and Flow npy file from your video or a sets of images.
☆8Updated 5 years ago
Alternatives and similar repositories for Trainable-i3d-pytorch:
Users that are interested in Trainable-i3d-pytorch are comparing it to the libraries listed below
- [ICCV 2019] TSM: Temporal Shift Module for Efficient Video Understanding☆21Updated 4 years ago
- The Pytorch code of the TEA module (Temporal Excitation and Aggregation for Action Recognition)☆193Updated 2 years ago
- An implementation of Video Transformer Network (VTN) approach for Action Recognition in TensorFlow.☆55Updated 4 years ago
- This is a Pytorch implement of StNet:Local and Global Spatial-Temporal Modeling for Action Recognition.☆8Updated 5 years ago
- A implementation of "SlowFast Networks for Video Recognition" with tf.keras☆50Updated 5 years ago
- SmallBigNet: Integrating Core and Contextual Views for Video Classification (CVPR2020)☆41Updated 2 years ago
- Code for CVPR2021 paper "Learning Salient Boundary Feature for Anchor-free Temporal Action Localization"☆174Updated 3 years ago
- [Codes of paper]: PAN: Towards Fast Action Recognition via Learning Persistence of Appearance☆102Updated 4 years ago
- TAM: Temporal Adaptive Module for Video Recognition☆198Updated 2 years ago
- A PyTorch implementation of R2Plus1D and C3D based on CVPR 2017 paper "A Closer Look at Spatiotemporal Convolutions for Action Recognitio…☆60Updated 5 years ago
- Decoupling Localization and Classification in Single Shot Temporal Action Detection☆93Updated 5 years ago
- Pytorch 3DNet attention feature map Visualization by [Cam](https://arxiv.org/abs/1512.04150); C3D, R3D, I3D, MF Net is support now!☆66Updated 4 years ago
- I3D Models in PyTorch☆17Updated 4 years ago
- A public Python implementation for generating Dynamic Images introduced in 'Dynamic Image Networks for Action Recognition' by Bilen et a…☆39Updated 4 years ago
- using GPU to extract videos' dense optical flow fields☆38Updated 7 years ago
- Official PyTorch implementation of ACTION-Net: Multipath Excitation for Action Recognition (CVPR'21)☆201Updated 3 years ago
- Train I3D model on ucf101 or hmdb51 by tensorflow☆112Updated 6 years ago
- This Pytorch repo uses BiConvLSTM in a Spatiotemporal Encoder to detect violence in Videos. Three benchmark datasets namely Hockey, Movie…☆37Updated 6 years ago
- UCFCrime Annotation☆14Updated 5 years ago
- AVSS violence recognition in pytorch☆70Updated 6 years ago
- implementation of the paper 'SlowFast Networks for Video Recognition ' with Pytorch☆27Updated 5 years ago
- Context-aware RCNN: a Baseline for Action Detection in Videos☆52Updated 4 years ago
- ☆44Updated 4 years ago
- I3D feature extractor☆43Updated 5 years ago
- pytorch☆59Updated 3 years ago
- Pytorch impelementation for Temporal Segment Networks (TSN) in ECCV 2016☆43Updated 5 years ago
- CVPR2021: Temporal Context Aggregation Network for Temporal Action Proposal Refinement☆71Updated 3 years ago
- ☆90Updated 6 years ago
- Optical Flow Guided Feature for Action Recognition-Pytorch☆18Updated 5 years ago
- fourierer / Video_Classification_ResNet3D_R2plus1D_ip-CSN_train-UCF101-HMDB51-Kinetics400-from-scratchUsing ResNet3D-50,R(2+1)D-50, and ip_CSN-50 to train UCD-101,HMDB-51 and Kinetics-400 from scratch.☆27Updated 4 years ago