{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/sharingan-a-transformer-architecture-for","title":"Sharingan: A Transformer Architecture for Multi-Person Gaze Following","arxiv_id":null,"date":"2024-01-01","proceeding":"CVPR 2024 1","authors":["Samy Tafasca","Anshul Gupta","Jean-Marc Odobez"],"abstract":"    Gaze is a powerful form of non-verbal communication that humans develop from an early age. As such modeling this behavior is an important task that can benefit a broad set of application domains ranging from robotics to sociology. In particular the gaze following task in computer vision is defined as the prediction of the 2D pixel coordinates where a person in the image is looking. Previous attempts in this area have primarily centered on CNN-based architectures but they have been constrained by the need to process one person at a time which proves to be highly inefficient. In this paper we introduce a novel and effective multi-person transformer-based architecture for gaze prediction. While there exist prior works using transformers for multi-person gaze prediction they use a fixed set of learnable embeddings to decode both the person and its gaze target which requires a matching step afterward to link the predictions with the annotations. Thus it is difficult to quantitatively evaluate these methods reliably with the available benchmarks or integrate them into a larger human behavior understanding system. Instead we are the first to propose a multi-person transformer-based architecture that maintains the original task formulation and ensures control over the people fed as input. Our main contribution lies in encoding the person-specific information into a single controlled token to be processed alongside image tokens and using its output for prediction based on a novel multiscale decoding mechanism. Our new architecture achieves state-of-the-art results on the GazeFollow VideoAttentionTarget and ChildPlay datasets and outperforms comparable multi-person architectures with a notable margin. Our code checkpoints and data extractions will be made publicly available soon.    ","url_abs":"http://openaccess.thecvf.com//content/CVPR2024/html/Tafasca_Sharingan_A_Transformer_Architecture_for_Multi-Person_Gaze_Following_CVPR_2024_paper.html","url_pdf":"http://openaccess.thecvf.com//content/CVPR2024/papers/Tafasca_Sharingan_A_Transformer_Architecture_for_Multi-Person_Gaze_Following_CVPR_2024_paper.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"sharingan-a-transformer-architecture-for","repo_url":"https://github.com/idiap/sharingan","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"eye-tracking","task_name":"Gaze Prediction"},{"task_slug":"sociology","task_name":"Sociology"}],"methods":[{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}