GazeHTA: End-to-end Gaze Target Detection with Head-Target Association

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Lin, Zhi-Yi, Chew, Jouh Yeong, van Gemert, Jan, Zhang, Xucong
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917912895291392
author Lin, Zhi-Yi
Chew, Jouh Yeong
van Gemert, Jan
Zhang, Xucong
author_facet Lin, Zhi-Yi
Chew, Jouh Yeong
van Gemert, Jan
Zhang, Xucong
contents Precisely detecting which object a person is paying attention to is critical for human-robot interaction since it provides important cues for the next action from the human user. We propose an end-to-end approach for gaze target detection: predicting a head-target connection between individuals and the target image regions they are looking at. Most of the existing methods use independent components such as off-the-shelf head detectors or have problems in establishing associations between heads and gaze targets. In contrast, we investigate an end-to-end multi-person Gaze target detection framework with Heads and Targets Association (GazeHTA), which predicts multiple head-target instances based solely on input scene image. GazeHTA addresses challenges in gaze target detection by (1) leveraging a pre-trained diffusion model to extract scene features for rich semantic understanding, (2) re-injecting a head feature to enhance the head priors for improved head understanding, and (3) learning a connection map as the explicit visual associations between heads and gaze targets. Our extensive experimental results demonstrate that GazeHTA outperforms state-of-the-art gaze target detection methods and two adapted diffusion-based baselines on two standard datasets.
format Preprint
id arxiv_https___arxiv_org_abs_2404_10718
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle GazeHTA: End-to-end Gaze Target Detection with Head-Target Association
Lin, Zhi-Yi
Chew, Jouh Yeong
van Gemert, Jan
Zhang, Xucong
Computer Vision and Pattern Recognition
Precisely detecting which object a person is paying attention to is critical for human-robot interaction since it provides important cues for the next action from the human user. We propose an end-to-end approach for gaze target detection: predicting a head-target connection between individuals and the target image regions they are looking at. Most of the existing methods use independent components such as off-the-shelf head detectors or have problems in establishing associations between heads and gaze targets. In contrast, we investigate an end-to-end multi-person Gaze target detection framework with Heads and Targets Association (GazeHTA), which predicts multiple head-target instances based solely on input scene image. GazeHTA addresses challenges in gaze target detection by (1) leveraging a pre-trained diffusion model to extract scene features for rich semantic understanding, (2) re-injecting a head feature to enhance the head priors for improved head understanding, and (3) learning a connection map as the explicit visual associations between heads and gaze targets. Our extensive experimental results demonstrate that GazeHTA outperforms state-of-the-art gaze target detection methods and two adapted diffusion-based baselines on two standard datasets.
title GazeHTA: End-to-end Gaze Target Detection with Head-Target Association
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2404.10718