{"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":"/task/audio-visual-learning","name":"audio-visual learning","slug":"audio-visual-learning","description_markdown":null,"categories":[],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":38,"papers_with_code":24,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":4,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/glips","name":"GLips","full_name":"German Lips","num_papers_in_archive":6},{"url":"/dataset/acappella","name":"Acappella","full_name":"","num_papers_in_archive":5},{"url":"/dataset/avmit","name":"AVMIT","full_name":"Audiovisual Moments in Time","num_papers_in_archive":2},{"url":"/dataset/is3-interactive-synthetic-sound-source","name":"IS3 (Interactive-Synthetic Sound Source) Dataset","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":1,"rows_per_page":100,"shown":38,"of":38,"of_with_code":24,"tagged_in_all":38,"counts":{"archive_papers_tagged":38,"with_a_code_link":24,"where_syntology_ran_a_sample":11,"not_listed_spam_title":0,"listed":38,"listed_where_code_ran":11,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":10,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":10,"listed_every_run_a_failure_of_syntologys_instrument":1,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/audiotoken-adaptation-of-text-conditioned-1","slug":"audiotoken-adaptation-of-text-conditioned-1","title":"AudioToken: Adaptation of Text-Conditioned Diffusion Models for Audio-to-Image Generation","date":"2023-05-22","arxiv_id":"2305.13050","repositories_listed":2,"syntology":{"n":11,"n_ran":5,"n_constructed":0,"n_ran_checked":0,"n_instrument":5,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":6,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/audiotoken-adaptation-of-text-conditioned-1#ran","syntology_url":"https://syntology.ai/paper/2305.13050","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.13050"}},"official":{"repos":["guyyariv/AudioToken"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/cav-mae-sync-improving-contrastive-audio","slug":"cav-mae-sync-improving-contrastive-audio","title":"CAV-MAE Sync: Improving Contrastive Audio-Visual Mask Autoencoders via Fine-Grained Alignment","date":"2025-05-02","arxiv_id":"2505.01237","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/cav-mae-sync-improving-contrastive-audio#ran","syntology_url":"https://syntology.ai/paper/2505.01237","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.01237"}},"official":{"repos":["edsonroteia/cav-mae-sync"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/language-guided-audio-visual-learning-for","slug":"language-guided-audio-visual-learning-for","title":"Language-Guided Audio-Visual Learning for Long-Term Sports Assessment","date":"2025-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/dense-audio-visual-event-localization-under","slug":"dense-audio-visual-event-localization-under","title":"Dense Audio-Visual Event Localization under Cross-Modal Consistency and Multi-Temporal Granularity Collaboration","date":"2024-12-17","arxiv_id":"2412.12628","repositories_listed":1,"syntology":{"n":14,"n_ran":13,"n_constructed":0,"n_ran_checked":3,"n_instrument":10,"n_unverified":1,"n_honours":2,"n_violates":0,"n_no_contract":1,"n_pointer_only":14,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 10 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/dense-audio-visual-event-localization-under#ran","syntology_url":"https://syntology.ai/paper/2412.12628","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.12628"}},"official":{"repos":["zzhhfut/ccnet-aaai2025"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/enhancing-sound-source-localization-via-false","slug":"enhancing-sound-source-localization-via-false","title":"Enhancing Sound Source Localization via False Negative Elimination","date":"2024-08-29","arxiv_id":"2408.16448","repositories_listed":1,"syntology":null},{"url":"/paper/ma-avt-modality-alignment-for-parameter","slug":"ma-avt-modality-alignment-for-parameter","title":"MA-AVT: Modality Alignment for Parameter-Efficient Audio-Visual Transformers","date":"2024-06-07","arxiv_id":"2406.04930","repositories_listed":1,"syntology":null},{"url":"/paper/equiav-leveraging-equivariance-for-audio","slug":"equiav-leveraging-equivariance-for-audio","title":"EquiAV: Leveraging Equivariance for Audio-Visual Contrastive Learning","date":"2024-03-14","arxiv_id":"2403.09502","repositories_listed":1,"syntology":{"n":13,"n_ran":6,"n_constructed":4,"n_ran_checked":5,"n_instrument":1,"n_unverified":7,"n_honours":1,"n_violates":0,"n_no_contract":4,"n_pointer_only":2,"phrase":"6 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/equiav-leveraging-equivariance-for-audio#ran","syntology_url":"https://syntology.ai/paper/2403.09502","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.09502"}},"official":{"repos":["jongsuk1/equiav"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":4,"n_ran_no_instrument_failure":5,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/emotions-a-large-scale-dataset-for-emotion","slug":"emotions-a-large-scale-dataset-for-emotion","title":"Towards Emotion Analysis in Short-form Videos: A Large-Scale Dataset and Baseline","date":"2023-11-29","arxiv_id":"2311.17335","repositories_listed":1,"syntology":null},{"url":"/paper/boosting-audio-visual-zero-shot-learning-with","slug":"boosting-audio-visual-zero-shot-learning-with","title":"Boosting Audio-visual Zero-shot Learning with Large Language Models","date":"2023-11-21","arxiv_id":"2311.12268","repositories_listed":1,"syntology":null},{"url":"/paper/can-clip-help-sound-source-localization","slug":"can-clip-help-sound-source-localization","title":"Can CLIP Help Sound Source Localization?","date":"2023-11-07","arxiv_id":"2311.04066","repositories_listed":1,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":10,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/can-clip-help-sound-source-localization#ran","syntology_url":"https://syntology.ai/paper/2311.04066","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.04066"}},"official":{"repos":["swimmiing/ACL-SSL"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/deep-video-inpainting-guided-by-audio-visual","slug":"deep-video-inpainting-guided-by-audio-visual","title":"Deep Video Inpainting Guided by Audio-Visual Self-Supervision","date":"2023-10-11","arxiv_id":"2310.07663","repositories_listed":1,"syntology":null},{"url":"/paper/av-superb-a-multi-task-evaluation-benchmark","slug":"av-superb-a-multi-task-evaluation-benchmark","title":"AV-SUPERB: A Multi-Task Evaluation Benchmark for Audio-Visual Representation Models","date":"2023-09-19","arxiv_id":"2309.10787","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/av-superb-a-multi-task-evaluation-benchmark#ran","syntology_url":"https://syntology.ai/paper/2309.10787","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.10787"}},"official":{"repos":["roger-tseng/av-superb"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/class-incremental-grouping-network-for","slug":"class-incremental-grouping-network-for","title":"Class-Incremental Grouping Network for Continual Audio-Visual Learning","date":"2023-09-11","arxiv_id":"2309.05281","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/class-incremental-grouping-network-for#ran","syntology_url":"https://syntology.ai/paper/2309.05281","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.05281"}},"official":{"repos":["stonemo/cign"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/a-unified-audio-visual-learning-framework-for","slug":"a-unified-audio-visual-learning-framework-for","title":"A Unified Audio-Visual Learning Framework for Localization, Separation, and Recognition","date":"2023-05-30","arxiv_id":"2305.19458","repositories_listed":1,"syntology":null},{"url":"/paper/modality-independent-teachers-meet-weakly-1","slug":"modality-independent-teachers-meet-weakly-1","title":"Modality-Independent Teachers Meet Weakly-Supervised Audio-Visual Event Parser","date":"2023-05-27","arxiv_id":"2305.17343","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":2,"n_ran_checked":4,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"6 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/modality-independent-teachers-meet-weakly-1#ran","syntology_url":"https://syntology.ai/paper/2305.17343","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.17343"}},"official":{"repos":["franklin905/valor"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":2,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/a-closer-look-at-audio-visual-semantic","slug":"a-closer-look-at-audio-visual-semantic","title":"Unraveling Instance Associations: A Closer Look for Audio-Visual Segmentation","date":"2023-04-06","arxiv_id":"2304.02970","repositories_listed":1,"syntology":null},{"url":"/paper/revisiting-pre-training-in-audio-visual","slug":"revisiting-pre-training-in-audio-visual","title":"Revisiting Pre-training in Audio-Visual Learning","date":"2023-02-07","arxiv_id":"2302.03533","repositories_listed":1,"syntology":null},{"url":"/paper/uavm-a-unified-model-for-audio-visual","slug":"uavm-a-unified-model-for-audio-visual","title":"UAVM: Towards Unifying Audio and Visual Models","date":"2022-07-29","arxiv_id":"2208.00061","repositories_listed":1,"syntology":{"n":14,"n_ran":10,"n_constructed":0,"n_ran_checked":6,"n_instrument":4,"n_unverified":4,"n_honours":1,"n_violates":1,"n_no_contract":4,"n_pointer_only":3,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 1 violated, 4 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/uavm-a-unified-model-for-audio-visual#ran","syntology_url":"https://syntology.ai/paper/2208.00061","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.00061"}},"official":{"repos":["YuanGongND/uavm"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/modality-aware-contrastive-instance-learning","slug":"modality-aware-contrastive-instance-learning","title":"Modality-Aware Contrastive Instance Learning with Self-Distillation for Weakly-Supervised Audio-Visual Violence Detection","date":"2022-07-12","arxiv_id":"2207.05500","repositories_listed":1,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":7,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":6,"n_pointer_only":1,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/modality-aware-contrastive-instance-learning#ran","syntology_url":"https://syntology.ai/paper/2207.05500","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.05500"}},"official":{"repos":["JustinYuu/MACIL_SD"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/learning-to-answer-questions-in-dynamic-audio","slug":"learning-to-answer-questions-in-dynamic-audio","title":"Learning to Answer Questions in Dynamic Audio-Visual Scenarios","date":"2022-03-26","arxiv_id":"2203.14072","repositories_listed":1,"syntology":{"n":4,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 4 unverified","sample_list":"/paper/learning-to-answer-questions-in-dynamic-audio#ran","syntology_url":"https://syntology.ai/paper/2203.14072","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.14072"}},"official":{"repos":["GeWu-Lab/MUSIC-AVQA"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":4,"ran_from_kinds":[]}}},{"url":"/paper/cascaded-multilingual-audio-visual-learning","slug":"cascaded-multilingual-audio-visual-learning","title":"Cascaded Multilingual Audio-Visual Learning from Videos","date":"2021-11-08","arxiv_id":"2111.04823","repositories_listed":1,"syntology":null},{"url":"/paper/distilling-audio-visual-knowledge-by","slug":"distilling-audio-visual-knowledge-by","title":"Distilling Audio-Visual Knowledge by Compositional Contrastive Learning","date":"2021-04-22","arxiv_id":"2104.10955","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/distilling-audio-visual-knowledge-by#ran","syntology_url":"https://syntology.ai/paper/2104.10955","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.10955"}},"official":{"repos":["yanbeic/CCL"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/can-audio-visual-integration-strengthen","slug":"can-audio-visual-integration-strengthen","title":"Can audio-visual integration strengthen robustness under multimodal attacks?","date":"2021-04-05","arxiv_id":"2104.02000","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/can-audio-visual-integration-strengthen#ran","syntology_url":"https://syntology.ai/paper/2104.02000","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.02000"}},"official":{"repos":["YapengTian/AV-Robustness-CVPR21"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/adversarial-metric-learning-for-audio-visual","slug":"adversarial-metric-learning-for-audio-visual","title":"Adversarial-Metric Learning for Audio-Visual Cross-Modal Matching","date":"2021-01-12","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":null,"slug":"lightweight-joint-audio-visual-deepfake","title":"Lightweight Joint Audio-Visual Deepfake Detection via Single-Stream Multi-Modal Learning Framework","date":"2025-06-09","arxiv_id":"2506.07358","repositories_listed":0,"syntology":null},{"url":null,"slug":"rethinking-audio-visual-adversarial","title":"Rethinking Audio-Visual Adversarial Vulnerability from Temporal and Modality Perspectives","date":"2025-02-17","arxiv_id":"2502.11858","repositories_listed":0,"syntology":null},{"url":null,"slug":"unveiling-visual-biases-in-audio-visual","title":"Unveiling Visual Biases in Audio-Visual Localization Benchmarks","date":"2024-08-25","arxiv_id":"2409.06709","repositories_listed":0,"syntology":null},{"url":null,"slug":"sequential-contrastive-audio-visual-learning","title":"Sequential Contrastive Audio-Visual Learning","date":"2024-07-08","arxiv_id":"2407.05782","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-input-multi-output-target-speaker-voice","title":"Multi-Input Multi-Output Target-Speaker Voice Activity Detection For Unified, Flexible, and Robust Audio-Visual Speaker Diarization","date":"2024-01-16","arxiv_id":"2401.08052","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-pretrained-image-text-models-for","title":"Leveraging Pretrained Image-text Models for Improving Audio-Visual Learning","date":"2023-09-08","arxiv_id":"2309.04628","repositories_listed":0,"syntology":null},{"url":null,"slug":"realimpact-a-dataset-of-impact-sound-fields-1","title":"RealImpact: A Dataset of Impact Sound Fields for Real Objects","date":"2023-06-16","arxiv_id":"2306.09944","repositories_listed":0,"syntology":null},{"url":"/paper/versatile-audio-visual-learning-for-handling","slug":"versatile-audio-visual-learning-for-handling","title":"Versatile audio-visual learning for emotion recognition","date":"2023-05-12","arxiv_id":"2305.07216","repositories_listed":0,"syntology":null},{"url":null,"slug":"object-segmentation-with-audio-context","title":"Object Segmentation with Audio Context","date":"2023-01-04","arxiv_id":"2301.10295","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-in-audio-visual-context-a-review","title":"Learning in Audio-visual Context: A Review, Analysis, and New Perspective","date":"2022-08-20","arxiv_id":"2208.09579","repositories_listed":0,"syntology":null},{"url":null,"slug":"few-shot-audio-visual-learning-of-environment","title":"Few-Shot Audio-Visual Learning of Environment Acoustics","date":"2022-06-08","arxiv_id":"2206.04006","repositories_listed":0,"syntology":null},{"url":null,"slug":"telling-left-from-right-learning-spatial-1","title":"Telling Left from Right: Learning Spatial Correspondence of Sight and Sound","date":"2020-06-11","arxiv_id":"2006.06175","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-audio-visual-learning-a-survey","title":"Deep Audio-Visual Learning: A Survey","date":"2020-01-14","arxiv_id":"2001.04758","repositories_listed":0,"syntology":null},{"url":null,"slug":"audio-visual-embedding-for-cross-modal","title":"Audio-Visual Embedding for Cross-Modal MusicVideo Retrieval through Supervised Deep CCA","date":"2019-08-10","arxiv_id":"1908.03744","repositories_listed":0,"syntology":null}],"syntology_records":13,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":11,"papers_where_code_ran_first_page":"/task/audio-visual-learning/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/task/audio-visual-learning/papers/ran/1","json":"/task/audio-visual-learning/papers/ran/1.json","rows":11}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"51b5854ad7504a274a67f1e58f60c11c0bd5696923ee1faa35d4e29a225964ff","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}