SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2202.07925 · ECCV · 2022

ActionFormer: Localizing Moments of Actions with Transformers

Yin Li, Jianxin Wu, Chen-Lin Zhang

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Self-attention based Transformer models have demonstrated impressive results for image classification and object detection, and more recently for video understanding. Inspired by this success, we investigate the application of Transformer networks for temporal action localization in videos. To this end, we present ActionFormer-a simple yet powerful model to identify actions in time and recognize their categories in a single shot, without using action proposals or relying on pre-defined anchor windows. ActionFormer combines a multiscale feature representation with local self-attention, and uses a light-weighted decoder to classify every moment in time and estimate the corresponding action boundaries. We show that this orchestrated design results in major improvements upon prior works. Without bells and whistles, Ac-tionFormer achieves 71.0% mAP at tIoU=0.5 on THUMOS14, outperforming the best prior model by 14.1 absolute percentage points. Further, ActionFormer demonstrates strong results on ActivityNet 1.3 (36.6% average mAP) and EPIC-Kitchens 100 (+13.5% average mAP over prior works). Our code is available at https://github.com/happyharrycn/ actionformer_release.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2202.07925")
get_code_for_paper("2202.07925")
have("2202.07925")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2202.07925.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2202.07925.svg)](https://syntology.ai/paper/2202.07925)

Connect an agent — have() is free.