{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/learning-long-term-spatial-temporal-graphs","title":"Learning Long-Term Spatial-Temporal Graphs for Active Speaker Detection","arxiv_id":"2207.07783","date":"2022-07-15","proceeding":null,"authors":["Kyle Min","Sourya Roy","Subarna Tripathi","Tanaya Guha","Somdeb Majumdar"],"abstract":"Active speaker detection (ASD) in videos with multiple speakers is a challenging task as it requires learning effective audiovisual features and spatial-temporal correlations over long temporal windows. In this paper, we present SPELL, a novel spatial-temporal graph learning framework that can solve complex tasks such as ASD. To this end, each person in a video frame is first encoded in a unique node for that frame. Nodes corresponding to a single person across frames are connected to encode their temporal dynamics. Nodes within a frame are also connected to encode inter-person relationships. Thus, SPELL reduces ASD to a node classification task. Importantly, SPELL is able to reason over long temporal contexts for all nodes without relying on computationally expensive fully connected graph neural networks. Through extensive experiments on the AVA-ActiveSpeaker dataset, we demonstrate that learning graph-based representations can significantly improve the active speaker detection performance owing to its explicit spatial and temporal structure. SPELL outperforms all previous state-of-the-art approaches while requiring significantly lower memory and computational resources. Our code is publicly available at https://github.com/SRA2/SPELL","url_abs":"https://arxiv.org/abs/2207.07783v3","url_pdf":"https://arxiv.org/pdf/2207.07783v3.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":"learning-long-term-spatial-temporal-graphs","repo_url":"https://github.com/kylemin/SPELL","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"learning-long-term-spatial-temporal-graphs","repo_url":"https://github.com/sra2/spell","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"active-speaker-detection","task_name":"Active Speaker Detection"},{"task_slug":"audio-visual-active-speaker-detection","task_name":"Audio-Visual Active Speaker Detection"},{"task_slug":"graph-learning","task_name":"Graph Learning"},{"task_slug":"node-classification","task_name":"Node Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/audio-visual-active-speaker-detection-on-ava","task":"Audio-Visual Active Speaker Detection","dataset":"AVA-ActiveSpeaker","model":"SPELL+","rank_in_archive_order":4,"of":20,"metrics":{"validation mean average precision":"94.9%"},"uses_additional_data":false},{"leaderboard":"/sota/audio-visual-active-speaker-detection-on-ava","task":"Audio-Visual Active Speaker Detection","dataset":"AVA-ActiveSpeaker","model":"SPELL","rank_in_archive_order":6,"of":20,"metrics":{"validation mean average precision":"94.2%"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-ava","task":"Node Classification","dataset":"AVA","model":"ASDNet [ASDNet_ICCV2021]","rank_in_archive_order":1,"of":4,"metrics":{"mAP":"93.5"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-ava","task":"Node Classification","dataset":"AVA","model":"TalkNet [tao2021someone]","rank_in_archive_order":2,"of":4,"metrics":{"mAP":"92.3"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-ava","task":"Node Classification","dataset":"AVA","model":"UniCon [zhang2021unicon]","rank_in_archive_order":3,"of":4,"metrics":{"mAP":"92"},"uses_additional_data":false},{"leaderboard":"/sota/node-classification-on-ava","task":"Node Classification","dataset":"AVA","model":"MAAS-TAN [MAAS2021]","rank_in_archive_order":4,"of":4,"metrics":{"mAP":"88.8"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2207.07783","atlas_url":"https://app.syntology.ai/?focus=2207.07783","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2207.07783"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2207.07783\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2207.07783"},"call":"get_concepts_for_paper(arxiv_id=\"2207.07783\")"}],"by_repo":[{"repo":"kylemin/SPELL","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"sra2/spell","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"089bd728b943d4f15b283205a83e3c223ea54cb4d098c946d920689ffe95dd10","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}