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

arXiv:2404.10718v2 Announce Type: replace
Abstract: 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 …

abstract arxiv association components cs.cv detection detectors head image independent type