google-deepmind / kinetics-i3d
Convolutional neural network model for video classification trained on the Kinetics dataset.
☆1,743Updated 5 years ago
Related projects ⓘ
Alternatives and complementary repositories for kinetics-i3d
- VMZ: Model Zoo for Video Modeling☆1,042Updated 3 years ago
- ☆980Updated 4 years ago
- Video classification tools using 3D ResNet☆1,104Updated 5 years ago
- This repository is intended to host tools and demos for ActivityNet☆942Updated 7 months ago
- Code & Models for Temporal Segment Networks (TSN) in ECCV 2016☆1,538Updated 4 years ago
- Inflated i3d network with inception backbone, weights transfered from tensorflow☆528Updated 5 months ago
- C3D is a modified version of BVLC caffe to support 3D ConvNets.☆1,165Updated 5 years ago
- An open-source toolbox for action understanding based on PyTorch☆1,863Updated 2 years ago
- temporal action detection with SSN☆641Updated 5 years ago
- Using two stream architecture to implement a classic action recognition method on UCF101 dataset☆858Updated 5 years ago
- Code release for "Convolutional Two-Stream Network Fusion for Video Action Recognition", CVPR 2016.☆716Updated 8 years ago
- PyTorch implemented C3D, R3D, R2Plus1D models for video activity recognition.☆1,191Updated 10 months ago
- Temporal Relation Networks☆786Updated 3 years ago
- Tutorial for video classification/ action recognition using 3D CNN/ CNN+RNN on UCF101☆939Updated 3 years ago
- Non-local Neural Networks for Video Classification☆1,975Updated 3 years ago
- A repository of common methods, datasets, and tasks for video research☆533Updated 5 years ago
- PyTorch implementation of two-stream networks for video action recognition☆568Updated 3 years ago
- 3D ResNets for Action Recognition (CVPR 2018)☆3,903Updated 3 years ago
- Pytorch porting of C3D network, with Sports1M weights☆348Updated 5 years ago
- C3D is a modified version of BVLC tensorflow to support 3D ConvNets.☆588Updated 5 years ago
- A curated list of action recognition and related area resources☆3,815Updated last year
- [ICCV 2019] TSM: Temporal Shift Module for Efficient Video Understanding☆2,068Updated 4 months ago
- pytorch version of pseudo-3d-residual-networks(P-3D), pretrained model is supported☆451Updated 5 years ago
- Temporal Segment Networks (TSN) in PyTorch☆1,066Updated 5 years ago
- A collection of recent video understanding datasets, under construction!☆459Updated 6 years ago
- You Only Watch Once: A Unified CNN Architecture for Real-Time Spatiotemporal Action Localization☆847Updated 3 weeks ago
- The pretrained models trained on Moments in Time Dataset☆355Updated 4 years ago
- GPU based optical flow extraction in OpenCV☆431Updated 5 years ago
- Download DeepMind's Kinetics dataset.☆262Updated 2 years ago
- PyTorch implementation of the R2Plus1D convolution based ResNet architecture described in the paper "A Closer Look at Spatiotemporal Conv…☆363Updated 4 years ago