Transform the caffe model to pytorch model for Temporal Segment Network
☆74Dec 12, 2018Updated 7 years ago
Alternatives and similar repositories for caffe2pytorch-tsn
Users that are interested in caffe2pytorch-tsn are comparing it to the libraries listed below
Sorting:
- Temporal Segment Networks (TSN) in PyTorch☆1,085Jun 21, 2019Updated 6 years ago
- ☆15Jun 17, 2018Updated 7 years ago
- This is tensorflow implementation for TSN(Temporal Segment Networks)☆21Apr 21, 2019Updated 6 years ago
- Code & Models for Temporal Segment Networks (TSN) in ECCV 2016☆1,579Oct 27, 2020Updated 5 years ago
- Weakly Supervised Action Recognition and Detection☆161Oct 16, 2018Updated 7 years ago
- Pytorch version for 3D ResNet☆15Dec 11, 2018Updated 7 years ago
- Code for paper: Optical Flow Guided Feature: A Fast and Robust Motion Representation for Video Action Recognition☆28Dec 8, 2022Updated 3 years ago
- Multilevel model for activity recognition in basketball using Optical Flow, LSTM and CNN☆20Dec 25, 2018Updated 7 years ago
- Code for "Predictive-Corrective Networks for Action Detection"☆16Nov 29, 2017Updated 8 years ago
- Temporal augmentation with two-stream ConvNet features on human action recognition☆18Apr 3, 2017Updated 8 years ago
- Code for our CVPR 2018 paper "Learning Latent Super-Events to Detect Multiple Activities in Videos"☆123Oct 4, 2018Updated 7 years ago
- PyTorch implementation of two-stream networks for video action recognition☆582Dec 22, 2020Updated 5 years ago
- This repository host the code for real-time action detection paper☆319Feb 23, 2021Updated 5 years ago
- Using two stream architecture to implement a classic action recognition method on UCF101 dataset☆876Oct 14, 2019Updated 6 years ago
- Appearance-and-Relation Networks☆202Nov 20, 2018Updated 7 years ago
- This repository is intended to host tools and demos for ActivityNet☆21Feb 7, 2017Updated 9 years ago
- This is a script which tests the speed of multiple optical flow extraction methods. support both single-thread and multi-thread☆23Sep 22, 2018Updated 7 years ago
- Code release for "Convolutional Two-Stream Network Fusion for Video Action Recognition", CVPR 2016.☆717Sep 27, 2016Updated 9 years ago
- This is my attempt at the ActivityNet Challenge 2017. Thanks to the organizers for providing the boilerplate code and annotated datasets.…☆10Jul 19, 2017Updated 8 years ago
- Caffe implementation for "Hidden Two-Stream Convolutional Networks for Action Recognition"☆191Dec 20, 2017Updated 8 years ago
- This repo is for action recognition using Kinetics dataset with pytorch☆11Aug 5, 2019Updated 6 years ago
- Deep networks with Temporal Pyramid Pooling. The official implementation for "End-to-end Video-level Representation Learning for Action R…☆74May 6, 2019Updated 6 years ago
- Extract TVL1 optical flows in python (multi-process && multi-server)☆194Jan 14, 2018Updated 8 years ago
- temporal action detection with SSN☆647Jun 21, 2019Updated 6 years ago
- Action Proposals generated by deep models☆29Mar 19, 2017Updated 8 years ago
- End to End training of Spatial Pyramid Networks☆13Apr 8, 2017Updated 8 years ago
- Recording and thinking when read the paper about PersonReID.☆10Jan 10, 2019Updated 7 years ago
- InceptionV3, InceptionV4, Inception-Resnet pretrained models for Torch7 and PyTorch☆32Dec 4, 2017Updated 8 years ago
- Video classification tools using 3D ResNet☆1,131Nov 23, 2018Updated 7 years ago
- Preprocess the activityNet dataset for detection task☆13Mar 3, 2017Updated 9 years ago
- semantic image segmentation networks implemented in tensorflow☆16Jan 21, 2017Updated 9 years ago
- Compressed Video Action Recognition☆520Jul 6, 2018Updated 7 years ago
- ☆1,041Jun 28, 2020Updated 5 years ago
- An open-source toolbox for action understanding based on PyTorch☆1,877Apr 8, 2022Updated 3 years ago
- A one stop shop for all of your activity recognition needs.☆108May 24, 2019Updated 6 years ago
- Tools to extract dense optical flow from videos, based on OpenCV☆246Jun 25, 2021Updated 4 years ago
- The source code of ECCV18 'Flow-Grounded Spatial-Temporal Video Prediction from Still Images'.☆61Feb 3, 2019Updated 7 years ago
- PyTorch implementation of the R2Plus1D convolution based ResNet architecture described in the paper "A Closer Look at Spatiotemporal Conv…☆365May 21, 2020Updated 5 years ago
- Pretrained Image & Video ConvNets and GANs for PyTorch: NASNet, ResNeXt (2D + 3D), ResNet (2D + 3D), InceptionV4, InceptionResnetV2, Xcep…☆330Jan 8, 2022Updated 4 years ago