{"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/audio-visual-event-localization-in","title":"Audio-Visual Event Localization in Unconstrained Videos","arxiv_id":"1803.08842","date":"2018-03-23","proceeding":"ECCV 2018 9","authors":["Yapeng Tian","Jing Shi","Bochen Li","Zhiyao Duan","Chenliang Xu"],"abstract":"In this paper, we introduce a novel problem of audio-visual event\nlocalization in unconstrained videos. We define an audio-visual event as an\nevent that is both visible and audible in a video segment. We collect an\nAudio-Visual Event(AVE) dataset to systemically investigate three temporal\nlocalization tasks: supervised and weakly-supervised audio-visual event\nlocalization, and cross-modality localization. We develop an audio-guided\nvisual attention mechanism to explore audio-visual correlations, propose a dual\nmultimodal residual network (DMRN) to fuse information over the two modalities,\nand introduce an audio-visual distance learning network to handle the\ncross-modality localization. Our experiments support the following findings:\njoint modeling of auditory and visual modalities outperforms independent\nmodeling, the learned attention can capture semantics of sounding objects,\ntemporal alignment is important for audio-visual fusion, the proposed DMRN is\neffective in fusing audio-visual features, and strong correlations between the\ntwo modalities enable cross-modality localization.","url_abs":"http://arxiv.org/abs/1803.08842v1","url_pdf":"http://arxiv.org/pdf/1803.08842v1.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":"audio-visual-event-localization-in","repo_url":"https://github.com/YapengTian/AVE-ECCV18","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"audio-visual-event-localization-in","repo_url":"https://github.com/YashNita/Audio-Visual-Event-Localization-in-Unconstrained-Videos","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"temporal-localization","task_name":"Temporal Localization"},{"task_slug":"audio-visual-event-localization","task_name":"audio-visual event localization"}],"methods":[],"datasets_introduced":[{"slug":"ave","name":"AVE","full_name":"Audio-Visual Event Localization"}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1803.08842","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.08842"}},"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/YapengTian/AVE-ECCV18","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/YashNita/Audio-Visual-Event-Localization-in-Unconstrained-Videos","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":1,"ran_fixture":1,"ran_honours":1,"unverified":1},"by_repo_kind":{"listed":{"samples":3,"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":4,"samples":[{"code_sha256_prefix":"72739f58746f7a7a","entry":"compute_acc","repo":"YapengTian/AVE-ECCV18","repo_kind":"listed","path":"supervised_main.py","file_url":"https://github.com/YapengTian/AVE-ECCV18/blob/HEAD/supervised_main.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"72739f58746f7a7a"}},{"code_sha256_prefix":"cc8acac4816ccb95","entry":"eucl_dist_output_shape","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"cc8acac4816ccb95"}},{"code_sha256_prefix":"f604bf5b94c48316","entry":"step_decay","repo":"YapengTian/AVE-ECCV18","repo_kind":"listed","path":"cmm_test.py","file_url":"https://github.com/YapengTian/AVE-ECCV18/blob/HEAD/cmm_test.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f604bf5b94c48316"}},{"code_sha256_prefix":"219c7611d3659ea1","entry":"val","repo":"YapengTian/AVE-ECCV18","repo_kind":"listed","path":"supervised_main.py","file_url":"https://github.com/YapengTian/AVE-ECCV18/blob/HEAD/supervised_main.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"219c7611d3659ea1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}