cvdfoundation / ava-dataset
The AVA dataset densely annotates 80 atomic visual actions in 351k movie clips with actions localized in space and time, resulting in 1.65M action labels with multiple labels per human occurring frequently.
☆311Updated 2 years ago
Related projects: ⓘ
- MARS: Motion-Augmented RGB Stream for Action Recognition☆161Updated last year
- Gate-Shift Networks for Video Action Recognition - CVPR 2020☆151Updated 4 years ago
- PyTorch implementation of "SlowFast Networks for Video Recognition".☆337Updated 5 years ago
- A pytorch-version implementation codes of paper: "BMN: Boundary-Matching Network for Temporal Action Proposal Generation", which is ac…☆289Updated 2 years ago
- [CVPR 2020] Temporal Pyramid Network for Action Recognition☆392Updated 3 years ago
- Graph Convolutional Networks for Temporal Action Localization (ICCV2019)☆319Updated 4 years ago
- [Codes of paper]: PAN: Towards Fast Action Recognition via Learning Persistence of Appearance☆102Updated 4 years ago
- A repository of common methods, datasets, and tasks for video research☆532Updated 5 years ago
- STEP: Spatio-Temporal Progressive Learning for Video Action Detection. CVPR'19 (Oral)☆246Updated 4 years ago
- Inflated i3d network with inception backbone, weights transfered from tensorflow☆522Updated 3 months ago
- Download DeepMind's Kinetics dataset.☆262Updated 2 years ago
- ☆159Updated 3 years ago
- Long-Term Feature Banks for Detailed Video Understanding☆372Updated 3 years ago
- Tools to extract dense optical flow from videos, based on OpenCV☆246Updated 3 years ago
- Transforms for video datasets in pytorch☆268Updated 3 years ago
- PyTorch 3D video classification models pre-trained on 65 million Instagram videos☆265Updated 4 years ago
- HACS: Human Action Clips and Segments Dataset☆187Updated 4 years ago
- PyTorch implementation of two-stream networks for video action recognition☆567Updated 3 years ago
- ☆253Updated 5 years ago
- Code and models for our CVPR'19 paper "Representation Flow for Action Recognition"☆254Updated 2 years ago
- PyTorch implementation for "ECO: Efficient Convolutional Network for Online Video Understanding", ECCV 2018☆293Updated 4 years ago
- [CVPR 2021] Actor-Context-Actor Relation Network for Spatio-temporal Action Localization☆202Updated 2 years ago
- Implementation of the paper Video Action Transformer Network☆135Updated 3 years ago
- Scripts for downloading the AVA (Atomic Visual Actions) dataset https://research.google.com/ava/ and do postprocessing of it.☆29Updated 5 years ago
- Codes of our paper: "BSN: Boundary Sensitive Network for Temporal Action Proposal Generation"☆246Updated 5 years ago
- Code and models of paper " ECO: Efficient Convolutional Network for Online Video Understanding", ECCV 2018☆436Updated 5 years ago
- Official implementation of "An Image is Worth 16x16 Words, What is a Video Worth?" (2021 paper)☆219Updated 2 years ago
- I3D Nonlocal ResNets in Pytorch☆245Updated 2 years ago
- temporal action detection with SSN☆641Updated 5 years ago
- Listen to Look: Action Recognition by Previewing Audio (CVPR 2020)☆126Updated 3 years ago