CVAIHCAug 23, 2022

Multimodal Across Domains Gaze Target Detection

arXiv:2208.10822v131 citationsh-index: 55Has Code
Originality Highly original
AI Analysis

This work addresses gaze target detection for computer vision applications, offering a novel unsupervised approach that improves accuracy across domains.

The paper tackles gaze target detection in third-person images by proposing a multimodal deep architecture that uses head images, scene, and depth maps without requiring gaze angle supervision, head orientation, or eye location, achieving stronger performance on multiple benchmark datasets.

This paper addresses the gaze target detection problem in single images captured from the third-person perspective. We present a multimodal deep architecture to infer where a person in a scene is looking. This spatial model is trained on the head images of the person-of- interest, scene and depth maps representing rich context information. Our model, unlike several prior art, do not require supervision of the gaze angles, do not rely on head orientation information and/or location of the eyes of person-of-interest. Extensive experiments demonstrate the stronger performance of our method on multiple benchmark datasets. We also investigated several variations of our method by altering joint-learning of multimodal data. Some variations outperform a few prior art as well. First time in this paper, we inspect domain adaption for gaze target detection, and we empower our multimodal network to effectively handle the domain gap across datasets. The code of the proposed method is available at https://github.com/francescotonini/multimodal-across-domains-gaze-target-detection.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes