paper-with-me

홈 › Papers

End-to-End Shared Attention Estimation via Group Detection with Feedback Refinement

2026-04-02 · Chihiro Nakatani, Norimichi Ukita, Jean-Marc Odobez arxiv

This paper proposes an end-to-end shared attention estimation method via group detection. Most previous methods estimate shared attention (SA) without detecting the actual group of people focusing on it, or assume that there is a single SA point in a given image. These issues limit the applicability of SA detection in practice and impact performance. To address them, we propose to simultaneously achieve group detection and shared attention estimation using a two step process: (i) the generation of SA heatmaps relying on individual gaze attention heatmaps and group membership scalars estimated in a group inference; (ii) a refinement of the initial group memberships allowing to account for the initial SA heatmaps, and the final prediction of the SA heatmap. Experiments demonstrate that our method outperforms other methods in group detection and shared attention estimation. Additional analyses validate the effectiveness of the proposed components. Code: https://github.com/chihina/sagd-CVPRW2026.

📄 PDF Abstract BibTeX arXiv:2604.01714

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

GroupEnsemble: Efficient Uncertainty Estimation for DETR-based Object Detection

2026-03-02 · Yutong Yang, Katarina Popović, Julian Wiederer, Markus Braun 외 arxiv

Detection Transformer (DETR) and its variants show strong performance on object detection, a key task for autonomous systems. However, a critical limitation of these models is that their confidence scores only reflect se…

Autonomous DrivingObject Detection

TGA: Two-level Group Attention for Assembly State Detection

2020-10-12 · Hangfan Liu, Yongzhi Su, Jason Rambach, Alain Pagani

Assembly state detection, i.e., object state detection, has a critical meaning in computer vision tasks, especially in AR assisted assembly. Unlike other object detection problems, the visual difference between different…

Objectobject-detectionObject DetectionState Estimation+1

SharedRep-RLHF: A Shared Representation Approach to RLHF with Diverse Preferences

2025-09-03 · Arpan Mukherjee, Marcello Bullo, Deniz Gündüz arxiv

Uniform-reward reinforcement learning from human feedback (RLHF), which trains a single reward model to represent the preferences of all annotators, fails to capture the diversity of opinions across sub-populations, inad…

Reinforcement Learning

Group Pose: A Simple Baseline for End-to-End Multi-person Pose Estimation

2023-08-14 · ICCV 2023 1 · Huan Liu, Qiang Chen, Zichang Tan, Jiang-Jiang Liu 외

In this paper, we study the problem of end-to-end multi-person pose estimation. State-of-the-art solutions adopt the DETR-like framework, and mainly develop the complex decoder, e.g., regarding pose estimation as keypoin…

DecoderHuman DetectionMulti-Person Pose EstimationPose Estimation

Self-attention in Vision Transformers Performs Perceptual Grouping, Not Attention

2023-03-02 · Paria Mehrani, John K. Tsotsos

Recently, a considerable number of studies in computer vision involves deep neural architectures called vision transformers. Visual processing in these models incorporates computational models that are claimed to impleme…

Saliency Detection