USTC-Video-Understanding / I3D_Finetune
TensorFlow code for finetuning I3D model on UCF101.
☆145Updated 6 years ago
Alternatives and similar repositories for I3D_Finetune
Users that are interested in I3D_Finetune are comparing it to the libraries listed below
Sorting:
- Extract TVL1 optical flows in python (multi-process && multi-server)☆192Updated 7 years ago
- Train I3D model on ucf101 or hmdb51 by tensorflow☆111Updated 6 years ago
- ☆91Updated 6 years ago
- Caffe implementation for "Hidden Two-Stream Convolutional Networks for Action Recognition"☆195Updated 7 years ago
- Tools to extract dense optical flow from videos, based on OpenCV☆243Updated 3 years ago
- MARS: Motion-Augmented RGB Stream for Action Recognition☆160Updated 2 years ago
- Codes for popular action recognition models, verified on the something-something data set.☆244Updated 6 years ago
- Code and models for our CVPR'19 paper "Representation Flow for Action Recognition"☆254Updated 2 years ago
- some famous works and new content to be added☆147Updated 7 years ago
- This repository host the code for real-time action detection paper☆322Updated 4 years ago
- code for R-C3D☆257Updated 5 years ago
- This is an i3d version which can be used to finetune on other video dataset.☆41Updated 6 years ago
- R-C3D pytorch implementation☆247Updated 5 years ago
- Two-stream CNNs for video action recognition implemented in Keras☆122Updated 5 years ago
- Weakly Supervised Action Recognition and Detection☆161Updated 6 years ago
- Deep networks with Temporal Pyramid Pooling. The official implementation for "End-to-end Video-level Representation Learning for Action R…☆74Updated 6 years ago
- ☆251Updated 6 years ago
- Graph Convolutional Networks for Temporal Action Localization (ICCV2019)☆324Updated 4 years ago
- Decoupling Localization and Classification in Single Shot Temporal Action Detection☆93Updated 5 years ago
- Use 3D ResNet to extract features of UCF101 and HMDB51 and then classify them.☆42Updated 6 years ago
- Inflated 3D ConvNets for video understanding☆49Updated last year
- Spatiotemporal-separable 3D convolution network.☆117Updated 7 years ago
- Code for paper: Optical Flow Guided Feature: A Fast and Robust Motion Representation for Video Action Recognition☆28Updated 2 years ago
- Explore Action Recognition☆202Updated 5 years ago
- Timeception for Complex Action Recognition, CVPR 2019 (Oral Presentation)☆157Updated 6 years ago
- GPU based optical flow extraction in OpenCV☆435Updated 5 years ago
- A PyTorch implementation of R2Plus1D and C3D based on CVPR 2017 paper "A Closer Look at Spatiotemporal Convolutions for Action Recognitio…☆59Updated 5 years ago
- Codes of our paper: "BSN: Boundary Sensitive Network for Temporal Action Proposal Generation"☆251Updated 6 years ago
- Code and models of paper " ECO: Efficient Convolutional Network for Online Video Understanding", ECCV 2018☆438Updated 5 years ago
- A one stop shop for all of your activity recognition needs.☆107Updated 5 years ago