{"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/dual-modality-seq2seq-network-for-audio","title":"Dual-modality seq2seq network for audio-visual event localization","arxiv_id":"1902.07473","date":"2019-02-20","proceeding":null,"authors":["Yan-Bo Lin","Yu-Jhe Li","Yu-Chiang Frank Wang"],"abstract":"Audio-visual event localization requires one to identify theevent which is both visible and audible in a video (eitherat a frame or video level). To address this task, we pro-pose a deep neural network named Audio-Visual sequence-to-sequence dual network (AVSDN). By jointly taking bothaudio and visual features at each time segment as inputs, ourproposed model learns global and local event information ina sequence to sequence manner, which can be realized in ei-ther fully supervised or weakly supervised settings. Empiricalresults confirm that our proposed method performs favorablyagainst recent deep learning approaches in both settings.","url_abs":"https://arxiv.org/abs/1902.07473v2","url_pdf":"https://arxiv.org/pdf/1902.07473v2.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":"dual-modality-seq2seq-network-for-audio","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":"dual-modality-seq2seq-network-for-audio","repo_url":"https://github.com/jasongief/cpsp","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"audio-visual-event-localization","task_name":"audio-visual event localization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1902.07473","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.07473"}},"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/jasongief/cpsp","reach":null}],"summary":{"ran_draft_wrong":2,"ran_fixture":1,"ran_honours":1,"unverified":2},"by_repo_kind":{"listed":{"samples":2,"ran":1,"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":6,"samples":[{"code_sha256_prefix":"72739f58746f7a7a","entry":"compute_acc","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"72739f58746f7a7a"}},{"code_sha256_prefix":"2c6b1e38dd0aa68a","entry":"compute_accuracy_supervised","repo":"jasongief/cpsp","repo_kind":"listed","path":"cpsp_avel/weakly_supv_main.py","file_url":"https://github.com/jasongief/cpsp/blob/HEAD/cpsp_avel/weakly_supv_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":"2c6b1e38dd0aa68a"}},{"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":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"f604bf5b94c48316"}},{"code_sha256_prefix":"5e1f439e307cce60","entry":"get_flag_by_gt","repo":"jasongief/cpsp","repo_kind":"listed","path":"cpsp_avel/fully_supv_main.py","file_url":"https://github.com/jasongief/cpsp/blob/HEAD/cpsp_avel/fully_supv_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":"5e1f439e307cce60"}},{"code_sha256_prefix":"219c7611d3659ea1","entry":"val","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"219c7611d3659ea1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}