{"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/multimodal-across-domains-gaze-target","title":"Multimodal Across Domains Gaze Target Detection","arxiv_id":"2208.10822","date":"2022-08-23","proceeding":null,"authors":["Francesco Tonini","Cigdem Beyan","Elisa Ricci"],"abstract":"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.","url_abs":"https://arxiv.org/abs/2208.10822v1","url_pdf":"https://arxiv.org/pdf/2208.10822v1.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":"multimodal-across-domains-gaze-target","repo_url":"https://github.com/francescotonini/multimodal-across-domains-gaze-target-detection","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"gaze-estimation","task_name":"Gaze Estimation"},{"task_slug":"gaze-target-estimation","task_name":"Gaze Target Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2208.10822","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.10822"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/francescotonini/multimodal-across-domains-gaze-target-detection","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_honours":2,"unverified":4},"by_repo_kind":{"official":{"samples":6,"ran":2,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"b476623700945834","entry":"to_numpy","repo":"francescotonini/multimodal-across-domains-gaze-target-detection","repo_kind":"official","path":"utils.py","file_url":"https://github.com/francescotonini/multimodal-across-domains-gaze-target-detection/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b476623700945834"}},{"code_sha256_prefix":"7aac4c51e0ceee97","entry":"to_torch","repo":"francescotonini/multimodal-across-domains-gaze-target-detection","repo_kind":"official","path":"utils.py","file_url":"https://github.com/francescotonini/multimodal-across-domains-gaze-target-detection/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7aac4c51e0ceee97"}},{"code_sha256_prefix":"5c31b33dd2dcd201","entry":"get_dataset","repo":"francescotonini/multimodal-across-domains-gaze-target-detection","repo_kind":"official","path":"datasets/build.py","file_url":"https://github.com/francescotonini/multimodal-across-domains-gaze-target-detection/blob/HEAD/datasets/build.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5c31b33dd2dcd201"}},{"code_sha256_prefix":"3bfc64307589269f","entry":"get_head_mask","repo":"francescotonini/multimodal-across-domains-gaze-target-detection","repo_kind":"official","path":"utils.py","file_url":"https://github.com/francescotonini/multimodal-across-domains-gaze-target-detection/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3bfc64307589269f"}},{"code_sha256_prefix":"7635341f21c816ca","entry":"get_loader","repo":"francescotonini/multimodal-across-domains-gaze-target-detection","repo_kind":"official","path":"datasets/build.py","file_url":"https://github.com/francescotonini/multimodal-across-domains-gaze-target-detection/blob/HEAD/datasets/build.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7635341f21c816ca"}},{"code_sha256_prefix":"a28f44966f22381e","entry":"load_pretrained","repo":"francescotonini/multimodal-across-domains-gaze-target-detection","repo_kind":"official","path":"models/build.py","file_url":"https://github.com/francescotonini/multimodal-across-domains-gaze-target-detection/blob/HEAD/models/build.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a28f44966f22381e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}