{"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 (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":24,"of":24,"tagged_in_all":38,"items":[{"url":"/paper/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":4,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/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_unverified":1,"n_pointer_only":0}},{"url":"/paper/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","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":0,"n_unverified":14,"n_pointer_only":14}},{"url":"/paper/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","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","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_unverified":7,"n_pointer_only":0}},{"url":"/paper/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","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","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_unverified":0,"n_pointer_only":10}},{"url":"/paper/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","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_unverified":1,"n_pointer_only":3}},{"url":"/paper/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_unverified":2,"n_pointer_only":0}},{"url":"/paper/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","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_unverified":0,"n_pointer_only":0}},{"url":"/paper/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","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","title":"UAVM: Towards Unifying Audio and Visual Models","date":"2022-07-29","arxiv_id":"2208.00061","repositories_listed":1,"syntology":{"n":14,"n_ran":6,"n_unverified":8,"n_pointer_only":0}},{"url":"/paper/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":2,"n_unverified":8,"n_pointer_only":0}},{"url":"/paper/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_unverified":4,"n_pointer_only":0}},{"url":"/paper/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","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_unverified":1,"n_pointer_only":0}},{"url":"/paper/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_unverified":0,"n_pointer_only":0}},{"url":"/paper/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}],"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"},"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":"2026-09-24T18:15:14+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; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"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"}}