{"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/detecting-attended-visual-targets-in-video","title":"Detecting Attended Visual Targets in Video","arxiv_id":"2003.02501","date":"2020-03-05","proceeding":"CVPR 2020 6","authors":["Eunji Chong","Yongxin Wang","Nataniel Ruiz","James M. Rehg"],"abstract":"We address the problem of detecting attention targets in video. Our goal is to identify where each person in each frame of a video is looking, and correctly handle the case where the gaze target is out-of-frame. Our novel architecture models the dynamic interaction between the scene and head features and infers time-varying attention targets. We introduce a new annotated dataset, VideoAttentionTarget, containing complex and dynamic patterns of real-world gaze behavior. Our experiments show that our model can effectively infer dynamic attention in videos. In addition, we apply our predicted attention maps to two social gaze behavior recognition tasks, and show that the resulting classifiers significantly outperform existing methods. We achieve state-of-the-art performance on three datasets: GazeFollow (static images), VideoAttentionTarget (videos), and VideoCoAtt (videos), and obtain the first results for automatically classifying clinically-relevant gaze behavior without wearable cameras or eye trackers.","url_abs":"https://arxiv.org/abs/2003.02501v2","url_pdf":"https://arxiv.org/pdf/2003.02501v2.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":"detecting-attended-visual-targets-in-video","repo_url":"https://github.com/ejcgt/attention-target-detection","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"deep-attention","task_name":"Deep Attention"}],"methods":[],"datasets_introduced":[{"slug":"videoattentiontarget","name":"VideoAttentionTarget","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2003.02501","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.02501"}},"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/ejcgt/attention-target-detection","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_honours":2,"unverified":11},"by_repo_kind":{"named_in_paper":{"samples":13,"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":"ejcgt/attention-target-detection","repo_kind":"named_in_paper","path":"utils/misc.py","file_url":"https://github.com/ejcgt/attention-target-detection/blob/HEAD/utils/misc.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":"ejcgt/attention-target-detection","repo_kind":"named_in_paper","path":"utils/misc.py","file_url":"https://github.com/ejcgt/attention-target-detection/blob/HEAD/utils/misc.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":"73becc3e41a71a86","entry":"LSTMCell","repo":"ejcgt/attention-target-detection","repo_kind":"named_in_paper","path":"lib/pytorch_convolutional_rnn/convolutional_rnn/functional.py","file_url":"https://github.com/ejcgt/attention-target-detection/blob/HEAD/lib/pytorch_convolutional_rnn/convolutional_rnn/functional.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":"73becc3e41a71a86"}},{"code_sha256_prefix":"05467393784434c1","entry":"RNNReLUCell","repo":"ejcgt/attention-target-detection","repo_kind":"named_in_paper","path":"lib/pytorch_convolutional_rnn/convolutional_rnn/functional.py","file_url":"https://github.com/ejcgt/attention-target-detection/blob/HEAD/lib/pytorch_convolutional_rnn/convolutional_rnn/functional.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":"05467393784434c1"}},{"code_sha256_prefix":"cd1e300e333d5db3","entry":"RNNTanhCell","repo":"ejcgt/attention-target-detection","repo_kind":"named_in_paper","path":"lib/pytorch_convolutional_rnn/convolutional_rnn/functional.py","file_url":"https://github.com/ejcgt/attention-target-detection/blob/HEAD/lib/pytorch_convolutional_rnn/convolutional_rnn/functional.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":"cd1e300e333d5db3"}},{"code_sha256_prefix":"b9f23783a1dde069","entry":"ap","repo":"ejcgt/attention-target-detection","repo_kind":"named_in_paper","path":"utils/evaluation.py","file_url":"https://github.com/ejcgt/attention-target-detection/blob/HEAD/utils/evaluation.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":"b9f23783a1dde069"}},{"code_sha256_prefix":"f00c194f6adc3f25","entry":"argmax_pts","repo":"ejcgt/attention-target-detection","repo_kind":"named_in_paper","path":"utils/evaluation.py","file_url":"https://github.com/ejcgt/attention-target-detection/blob/HEAD/utils/evaluation.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":"f00c194f6adc3f25"}},{"code_sha256_prefix":"4672566e034d749b","entry":"auc","repo":"ejcgt/attention-target-detection","repo_kind":"named_in_paper","path":"utils/evaluation.py","file_url":"https://github.com/ejcgt/attention-target-detection/blob/HEAD/utils/evaluation.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":"4672566e034d749b"}},{"code_sha256_prefix":"e15e27f2915b4002","entry":"draw_labelmap","repo":"ejcgt/attention-target-detection","repo_kind":"named_in_paper","path":"utils/imutils.py","file_url":"https://github.com/ejcgt/attention-target-detection/blob/HEAD/utils/imutils.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":"e15e27f2915b4002"}},{"code_sha256_prefix":"e51e72ca0654a9a0","entry":"get_head_box_channel","repo":"ejcgt/attention-target-detection","repo_kind":"named_in_paper","path":"utils/imutils.py","file_url":"https://github.com/ejcgt/attention-target-detection/blob/HEAD/utils/imutils.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":"e51e72ca0654a9a0"}},{"code_sha256_prefix":"94dd3d9e6c6d6473","entry":"smooth_by_conv","repo":"ejcgt/attention-target-detection","repo_kind":"named_in_paper","path":"utils/myutils.py","file_url":"https://github.com/ejcgt/attention-target-detection/blob/HEAD/utils/myutils.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":"94dd3d9e6c6d6473"}},{"code_sha256_prefix":"b65c0249984c6b66","entry":"unnorm","repo":"ejcgt/attention-target-detection","repo_kind":"named_in_paper","path":"utils/imutils.py","file_url":"https://github.com/ejcgt/attention-target-detection/blob/HEAD/utils/imutils.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":"b65c0249984c6b66"}},{"code_sha256_prefix":"ebd6363b1de50a7e","entry":"video_pack_sequences","repo":"ejcgt/attention-target-detection","repo_kind":"named_in_paper","path":"eval_on_videoatttarget.py","file_url":"https://github.com/ejcgt/attention-target-detection/blob/HEAD/eval_on_videoatttarget.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":"ebd6363b1de50a7e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}