Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Code release for ActionFormer (ECCV 2022)
| Date | Stars |
|---|---|
| 2026-07-30 | 572 |
| 2026-08-11 | 571 |
| 2026-08-18 | 572 |
| 2026-08-19 | 573 |
| 2026-09-04 | 574 |
| 2026-09-05 | 575 |
| 2026-09-16 | 576 |
| 2026-09-24 | 577 |
| 2026-09-25 | 578 |
| 2026-10-05 | 579 |
| 2026-10-06 | 578 |
| 2026-11-02 | 579 |
| 2026-11-03 | 580 |
| 2026-11-04 | 580 |
Today
— stars today
This week
+2 stars this week
This month
+1 stars this month
Momentum
0.0
growth rate 0.35%/day
# ActionFormer: Localizing Moments of Actions with Transformers ## Introduction This code repo implements Actionformer, one of the first Transformer-based model for temporal action localization --- detecting the onsets and offsets of action instances and recognizing their action categories. Without bells and whistles, ActionFormer achieves 71.0% mAP at tIoU=0.5 on THUMOS14, outperforming the best prior model by 14.1 absolute percentage points and crossing the 60% mAP for the first time. Further, ActionFormer demonstrates strong results on ActivityNet 1.3 (36.56% average mAP) and the more challenging EPIC-Kitchens 100 (+13.5% average mAP over prior works). Our paper is accepted to ECCV 2022 and an arXiv version can be found at [this link](https://arxiv.org/abs/2202.07925). In addition, ActionFormer is the backbone for many winning solutions in the Ego4D Moment Queries Challenge 2022. Our submission in particular is ranked 2nd with a record 21.76% average mAP and 42.54% Recall@1x, tIoU=0.5, nearly three times higher than the official baseline. An arXiv version of our tech report can be found at [this link](https://arxiv.org/abs/2211.09074). We invite our audience to try out the code. <div align="center"> <img src="teaser.jpg" width="600px"/> </div> Specifically, we adopt a minimalist design and develop a Transformer based model for temporal action localization, inspired by the recent success of Transformers in NLP and vision. Our method, illustrated in the figure, adapts local self-attention to model temporal context in untrimmed videos, classifies every moment in an input video, and regresses their corresponding action boundaries. The result is a deep model that is trained using standard classification and regression loss, and can localize moments of actions in a single shot, without using action proposals or pre-defined anchor windows. **Related projects**: > [**SnAG: Scalable and Accurate Video Grounding**](https://arxiv.org/abs/2404.02257) <br> > Fangzhou Mu\*, Sicheng Mo\*, Yin Li <br> > *CVPR 2024* <br> [](https://github.com/fmu2/snag_release) [](https://github.com/fmu2/snag_release) [](https://arxiv.org/abs/2404.02257) <br> ## Changelog * 11/18/2022: We have released the [tech report](https://arxiv.org/abs/2211.09074) for our submission to the [Ego4D Moment Queries (MQ) Challenge](https://eval.ai/web/challenges/challenge-page/1626/overview). The code repo now includes config files, pre-trained models and results on the Ego4D MQ benchmark. * 08/29/2022: Updated arXiv version. * 08/01/2022: Updated code repo with latest results on ActivityNet. * 07/08/2022: The paper is accepted to ECCV 2022. * 05/09/2022: Pre-trained models have been updated. * 05/08/2022: We have updated the code repo based on the community feedback and our code review, leading to significantly better average mAP on THUMOS14 (>66.0%) and slightly improved results on ActivityNet and EPIC-Kitchens 100. ## Code Overview The structure of this code repo is heavily inspired by Detectron2. Some of the main components are * ./libs/core: Parameter configuration module. * ./libs/datasets: Data loader and IO module. * ./libs/modeling: Our main model with all its building blocks. * ./libs/utils: Utility functions for training, inference, and postprocessing. ## Installation * Follow INSTALL.md for installing necessary dependencies and compiling the code. ## Frequently Asked Questions * See FAQ.md. ## To Reproduce Our Results on THUMOS14 **Download Features and Annotations** * Download *thumos.tar.gz* (`md5sum 375f76ffbf7447af1035e694971ec9b2`) from [this Box link](https://uwmadison.box.com/s/glpuxadymf3gd01m1cj6g5c3bn39qbgr) or [this Google Drive link](https://drive.google.com/file/d/1zt2eoldshf99vJMDuu8jqxda55dCyhZP/view?usp=sh
Excerpt of 22,288 characters
Read on GitHub
50
12
6
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:5b5e4618dbccf64e, topic:computer-vision