# E^2TAD: An Energy-Efficient Tracking-based Action Detector

Source: [E^2TAD: An Energy-Efficient Tracking-based Action Detector](<https://www.sota2.com/research/paper/68fa6dc81e209131cea3c2b8>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T00:44:11.594Z

Authors: Xin Hu, Zhenyu Wu, Hao-Yu Miao, Siqi Fan, Taiyu Long, Zhenyu Hu, Pengcheng Pi, Yi Wu, Zhou Ren, Zhangyang Wang, Gang Hua

Published: 2022-04-09T07:52:11.000Z

## Abstract

Video action detection (spatio-temporal action localization) is usually the starting point for human-centric intelligent analysis of videos nowadays. It has high practical impacts for many applications across robotics, security, healthcare, etc. The two-stage paradigm of Faster R-CNN inspires a standard paradigm of video action detection in object detection, i.e., firstly generating person proposals and then classifying their actions. However, none of the existing solutions could provide fine-grained action detection to the "who-when-where-what" level. This paper presents a tracking-based solution to accurately and efficiently localize predefined key actions spatially (by predicting the associated target IDs and locations) and temporally (by predicting the time in exact frame indices). This solution won first place in the UAV-Video Track of 2021 Low-Power Computer Vision Challenge (LPCVC).

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2204.04416>)

[PDF](<https://arxiv.org/pdf/2204.04416.pdf>)
