{"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/discriminative-sounding-objects-localization","title":"Discriminative Sounding Objects Localization via Self-supervised Audiovisual Matching","arxiv_id":"2010.05466","date":"2020-10-12","proceeding":"NeurIPS 2020 12","authors":["Di Hu","Rui Qian","Minyue Jiang","Xiao Tan","Shilei Wen","Errui Ding","Weiyao Lin","Dejing Dou"],"abstract":"Discriminatively localizing sounding objects in cocktail-party, i.e., mixed sound scenes, is commonplace for humans, but still challenging for machines. In this paper, we propose a two-stage learning framework to perform self-supervised class-aware sounding object localization. First, we propose to learn robust object representations by aggregating the candidate sound localization results in the single source scenes. Then, class-aware object localization maps are generated in the cocktail-party scenarios by referring the pre-learned object knowledge, and the sounding objects are accordingly selected by matching audio and visual object category distributions, where the audiovisual consistency is viewed as the self-supervised signal. Experimental results in both realistic and synthesized cocktail-party videos demonstrate that our model is superior in filtering out silent objects and pointing out the location of sounding objects of different classes. Code is available at https://github.com/DTaoo/Discriminative-Sounding-Objects-Localization.","url_abs":"https://arxiv.org/abs/2010.05466v1","url_pdf":"https://arxiv.org/pdf/2010.05466v1.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":"discriminative-sounding-objects-localization","repo_url":"https://github.com/DTaoo/Discriminative-Sounding-Objects-Localization","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"object","task_name":"Object"},{"task_slug":"object-localization","task_name":"Object Localization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2010.05466","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.05466"}},"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/DTaoo/Discriminative-Sounding-Objects-Localization","reach":null}],"summary":{"ran":1,"ran_fixture":2,"ran_honours":1},"by_repo_kind":{"official":{"samples":4,"ran":4,"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":"f36436df524b530d","entry":"Location_Net_stage_one","repo":"DTaoo/Discriminative-Sounding-Objects-Localization","repo_kind":"official","path":"audioset-instrument/model/location_model.py","file_url":"https://github.com/DTaoo/Discriminative-Sounding-Objects-Localization/blob/HEAD/audioset-instrument/model/location_model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f36436df524b530d"}},{"code_sha256_prefix":"305858167dad390a","entry":"batch_organize","repo":"dtaoo/discriminative-sounding-objects-localization","repo_kind":"official","path":"music-exp/training_stage_one.py","file_url":"https://github.com/dtaoo/discriminative-sounding-objects-localization/blob/HEAD/music-exp/training_stage_one.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"305858167dad390a"}},{"code_sha256_prefix":"1b255d3d05a68d2d","entry":"eva_metric","repo":"dtaoo/discriminative-sounding-objects-localization","repo_kind":"official","path":"music-exp/training_stage_one.py","file_url":"https://github.com/dtaoo/discriminative-sounding-objects-localization/blob/HEAD/music-exp/training_stage_one.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1b255d3d05a68d2d"}},{"code_sha256_prefix":"898dfd8d38003e43","entry":"location_dilation","repo":"dtaoo/discriminative-sounding-objects-localization","repo_kind":"official","path":"music-exp/training_stage_one.py","file_url":"https://github.com/dtaoo/discriminative-sounding-objects-localization/blob/HEAD/music-exp/training_stage_one.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"898dfd8d38003e43"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}