{"total":107,"rows":[{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556,"area":null},{"id":"2207.05042","title":"Audio-Visual Segmentation","created":"2022-07-11","cited_by_count":151,"area":null},{"id":"2101.03149","title":"VisualVoice: Audio-Visual Speech Separation with Cross-Modal Consistency","created":"2021-01-08","cited_by_count":114,"area":null},{"id":"2203.09324","title":"Localizing Visual Sounds the Easy Way","created":"2022-03-17","cited_by_count":82,"area":null},{"id":"2103.15916","title":"Robust Audio-Visual Instance Discrimination","created":"2021-03-29","cited_by_count":80,"area":null},{"id":"2204.02389","title":"ObjectFolder 2.0: A Multisensory Object Dataset for Sim2Real Transfer","created":"2022-04-05","cited_by_count":75,"area":null},{"id":"2301.13190","title":"Audio-Visual Segmentation with Semantics","created":"2023-01-30","cited_by_count":75,"area":null},{"id":"2209.09634","title":"A Closer Look at Weakly-Supervised Audio-Visual Source Localization","created":"2022-08-30","cited_by_count":73,"area":null},{"id":"2212.07983","title":"Vision Transformers are Parameter-Efficient Audio-Visual Learners","created":"2022-12-15","cited_by_count":72,"area":null},{"id":"2104.02026","title":"Cyclic Co-Learning of Sounding Object Visual Grounding and Sound Separation","created":"2021-04-05","cited_by_count":59,"area":null},{"id":"2104.10955","title":"Distilling Audio-Visual Knowledge by Compositional Contrastive Learning","created":"2021-04-22","cited_by_count":53,"area":null},{"id":"2211.09980","title":"Contrastive Positive Sample Propagation along the Audio-Visual Event Line","created":"2022-11-18","cited_by_count":50,"area":null},{"id":"2104.06162","title":"Visually Informed Binaural Audio Generation without Binaural Audios","created":"2021-04-13","cited_by_count":46,"area":null},{"id":"2206.12772","title":"Exploiting Transformation Invariance and Equivariance for Self-supervised Sound Localisation","created":"2022-06-26","cited_by_count":44,"area":null},{"id":"2208.09579","title":"Learning in Audio-visual Context: A Review, Analysis, and New Perspective","created":"2022-08-20","cited_by_count":44,"area":null},{"id":"2303.17490","title":"Sound to Visual Scene Generation by Audio-to-Visual Latent Alignment","created":"2023-03-30","cited_by_count":41,"area":null},{"id":"2306.00956","title":"The ObjectFolder Benchmark: Multisensory Learning with Neural and Real Objects","created":"2023-06-01","cited_by_count":41,"area":null},{"id":"2303.13471","title":"Egocentric Audio-Visual Object Localization","created":"2023-03-23","cited_by_count":40,"area":null},{"id":"2204.00604","title":"Quantized GAN for Complex Music Generation from Dance Videos","created":"2022-04-01","cited_by_count":37,"area":null},{"id":"2303.14676","title":"PDPP: Projected Diffusion for Procedure Planning in Instructional Videos","created":"2023-03-26","cited_by_count":36,"area":null},{"id":"2105.07142","title":"Move2Hear: Active Audio-Visual Source Separation","created":"2021-05-15","cited_by_count":35,"area":null},{"id":"2108.03256","title":"The Right to Talk: An Audio-Visual Transformer Approach","created":"2021-08-06","cited_by_count":33,"area":null},{"id":"2112.11749","title":"Class-aware Sounding Objects Localization via Audiovisual Correspondence","created":"2021-12-22","cited_by_count":32,"area":null},{"id":"2202.03007","title":"Learning Sound Localization Better From Semantically Similar Samples","created":"2022-02-07","cited_by_count":32,"area":null},{"id":"2309.10724","title":"Sound Source Localization is All about Cross-Modal Alignment","created":"2023-09-19","cited_by_count":31,"area":null},{"id":"2104.06401","title":"Self-supervised object detection from audio-visual correspondence","created":"2021-04-13","cited_by_count":29,"area":null},{"id":"2109.11955","title":"Visual Scene Graphs for Audio Source Separation","created":"2021-09-24","cited_by_count":29,"area":null},{"id":"2212.03814","title":"iQuery: Instruments as Queries for Audio-Visual Sound Separation","created":"2022-12-07","cited_by_count":29,"area":null},{"id":"2310.06238","title":"Tackling Data Bias in MUSIC-AVQA: Crafting a Balanced Dataset for Unbiased Question-Answering","created":"2023-10-10","cited_by_count":29,"area":null},{"id":"2104.00315","title":"Unsupervised Sound Localization via Iterative Contrastive Learning","created":"2021-04-01","cited_by_count":28,"area":null},{"id":"2203.03598","title":"Audio-visual Generalised Zero-shot Learning with Cross-modal Attention and Language","created":"2022-03-07","cited_by_count":27,"area":null},{"id":"2103.08468","title":"Beyond Image to Depth: Improving Depth Prediction using Echoes","created":"2021-03-15","cited_by_count":24,"area":null},{"id":"2108.00688","title":"Self-supervised Audiovisual Representation Learning for Remote Sensing Data","created":"2021-08-02","cited_by_count":24,"area":null},{"id":"2207.10141","title":"AudioScopeV2: Audio-Visual Attention Architectures for Calibrated Open-Domain On-Screen Sound Separation","created":"2022-07-20","cited_by_count":24,"area":null},{"id":"2104.02000","title":"Can audio-visual integration strengthen robustness under multimodal attacks?","created":"2021-04-05","cited_by_count":23,"area":null},{"id":"2111.10882","title":"Geometry-Aware Multi-Task Learning for Binaural Audio Generation from Video","created":"2021-11-21","cited_by_count":22,"area":null},{"id":"2211.02250","title":"Real-Time Target Sound Extraction","created":"2022-11-04","cited_by_count":22,"area":null},{"id":"2309.05281","title":"Class-Incremental Grouping Network for Continual Audio-Visual Learning","created":"2023-09-11","cited_by_count":22,"area":null},{"id":"2303.16342","title":"Language-Guided Audio-Visual Source Separation via Trimodal Consistency","created":"2023-03-28","cited_by_count":20,"area":null},{"id":"2305.03907","title":"Listen to Look into the Future: Audio-Visual Egocentric Gaze Anticipation","created":"2023-05-06","cited_by_count":20,"area":null},{"id":"2202.06406","title":"Visual Sound Localization in the Wild by Cross-Modal Interference Erasing","created":"2022-02-13","cited_by_count":19,"area":null},{"id":"2207.09966","title":"Temporal and cross-modal attention for audio-visual zero-shot learning","created":"2022-07-20","cited_by_count":19,"area":null},{"id":"2311.15080","title":"Weakly-Supervised Audio-Visual Segmentation","created":"2023-11-25","cited_by_count":19,"area":null},{"id":"2104.08506","title":"Visually Guided Sound Source Separation and Localization using Self-Supervised Motion Representations","created":"2021-04-17","cited_by_count":18,"area":null},{"id":"2305.17343","title":"Modality-Independent Teachers Meet Weakly-Supervised Audio-Visual Event Parser","created":"2023-05-27","cited_by_count":18,"area":null},{"id":"2104.09829","title":"Detector-Free Weakly Supervised Grounding by Separation","created":"2021-04-20","cited_by_count":16,"area":null},{"id":"2202.00850","title":"Active Audio-Visual Separation of Dynamic Sound Sources","created":"2022-02-02","cited_by_count":16,"area":null},{"id":"2211.01966","title":"MarginNCE: Robust Sound Localization with a Negative Margin","created":"2022-11-03","cited_by_count":16,"area":null},{"id":"2308.12370","title":"AdVerb: Visually Guided Audio Dereverberation","created":"2023-08-23","cited_by_count":15,"area":null},{"id":"2105.00708","title":"Exploiting Audio-Visual Consistency with Partial Supervision for Spatial Audio Generation","created":"2021-05-03","cited_by_count":14,"area":null},{"id":"2203.04099","title":"VoViT: Low Latency Graph-based Audio-Visual Voice Separation Transformer","created":"2022-03-08","cited_by_count":14,"area":null},{"id":"2104.09946","title":"A cappella: Audio-visual Singing Voice Separation","created":"2021-04-20","cited_by_count":12,"area":null},{"id":"2210.16472","title":"Learning Audio-Visual Dynamics Using Scene Graphs for Audio Source Separation","created":"2022-10-29","cited_by_count":11,"area":null},{"id":"2308.00122","title":"High-Quality Visually-Guided Sound Separation from Diverse Categories","created":"2023-07-31","cited_by_count":11,"area":null},{"id":"2311.00320","title":"Semantic Hearing: Programming Acoustic Scenes with Binaural Hearables","created":"2023-11-01","cited_by_count":11,"area":null},{"id":"2407.05358","title":"CPM: Class-conditional Prompting Machine for Audio-visual Segmentation","created":"2024-07-07","cited_by_count":11,"area":null},{"id":"2306.00923","title":"Sonicverse: A Multisensory Simulation Platform for Embodied Household Agents that See and Hear","created":"2023-06-01","cited_by_count":9,"area":null},{"id":"2310.07517","title":"CM-PIE: Cross-modal perception for interactive-enhanced audio-visual video parsing","created":"2023-10-11","cited_by_count":9,"area":null},{"id":"2105.04727","title":"Separate but Together: Unsupervised Federated Learning for Speech Enhancement from Non-IID Data","created":"2021-05-11","cited_by_count":8,"area":null},{"id":"2207.11964","title":"ConceptBeam: Concept Driven Target Speech Extraction","created":"2022-07-25","cited_by_count":8,"area":null},{"id":"2307.04760","title":"Learning Spatial Features from Audio-Visual Correspondence in Egocentric Videos","created":"2023-07-10","cited_by_count":8,"area":null},{"id":"2310.20446","title":"LAVSS: Location-Guided Audio-Visual Spatial Audio Separation","created":"2023-10-31","cited_by_count":8,"area":null},{"id":"2407.13676","title":"Aligning Sight and Sound: Advanced Sound Source Localization Through Audio-Visual Alignment","created":"2024-07-18","cited_by_count":8,"area":null},{"id":"2508.08237","title":"VGGSounder: Audio-Visual Evaluations for Foundation Models","created":"2025-08-11","cited_by_count":8,"area":null},{"id":"2305.03568","title":"A vector quantized masked autoencoder for audiovisual speech emotion recognition","created":"2023-05-05","cited_by_count":7,"area":null},{"id":"2411.02860","title":"Continual Audio-Visual Sound Separation","created":"2024-11-05","cited_by_count":7,"area":null},{"id":"2109.08867","title":"V-SlowFast Network for Efficient Visual Sound Separation","created":"2021-09-18","cited_by_count":6,"area":null},{"id":"2110.13412","title":"TriBERT: Full-body Human-centric Audio-visual Representation Learning for Visual Sound Separation","created":"2021-10-26","cited_by_count":6,"area":null},{"id":"2112.09726","title":"Soundify: Matching Sound Effects to Video","created":"2021-12-17","cited_by_count":6,"area":null},{"id":"2106.06939","title":"Cross-Modal Attention Consistency for Video-Audio Unsupervised Learning","created":"2021-06-13","cited_by_count":5,"area":null},{"id":"2106.09669","title":"Improving On-Screen Sound Separation for Open-Domain Videos with Audio-Visual Self-Attention","created":"2021-06-17","cited_by_count":5,"area":null},{"id":"2404.01740","title":"Weakly-supervised Audio Separation via Bi-modal Semantic Similarity","created":"2024-04-02","cited_by_count":5,"area":null},{"id":"2412.06209","title":"Sound2Vision: Generating Diverse Visuals from Audio through Cross-Modal Latent Alignment","created":"2024-12-09","cited_by_count":5,"area":null},{"id":"2104.02606","title":"Weakly-supervised Audio-visual Sound Source Detection and Separation","created":"2021-03-25","cited_by_count":4,"area":null},{"id":"2109.02763","title":"Binaural SoundNet: Predicting Semantics, Depth and Motion with Binaural Sounds","created":"2021-09-06","cited_by_count":4,"area":null},{"id":"2112.00216","title":"PoseKernelLifter: Metric Lifting of 3D Human Pose using Sound","created":"2021-12-01","cited_by_count":4,"area":null},{"id":"2310.11713","title":"Separating Invisible Sounds Toward Universal Audiovisual Scene-Aware Sound Separation","created":"2023-10-18","cited_by_count":4,"area":null},{"id":"2401.04023","title":"Efficient Multiscale Multimodal Bottleneck Transformer for Audio-Video Classification","created":"2024-01-08","cited_by_count":4,"area":null},{"id":"2410.01020","title":"A Critical Assessment of Visual Sound Source Localization Models Including Negative Audio","created":"2024-10-01","cited_by_count":4,"area":null},{"id":"2107.00231","title":"Audiovisual Singing Voice Separation","created":"2021-07-01","cited_by_count":3,"area":null},{"id":"2409.00486","title":"Multi-scale Multi-instance Visual Sound Localization and Segmentation","created":"2024-08-31","cited_by_count":3,"area":null},{"id":"2510.09065","title":"MMAudioSep: Taming Video-to-Audio Generative Model Towards Video/Text-Queried Sound Separation","created":"2025-10-10","cited_by_count":3,"area":null},{"id":"2510.18346","title":"AV-Master: Dual-Path Comprehensive Perception Makes Better Audio-Visual Question Answering","created":"2025-10-21","cited_by_count":3,"area":null},{"id":"2603.28757","title":"SonoWorld: From One Image to a 3D Audio-Visual Scene","created":"2026-03-30","cited_by_count":3,"area":null},{"id":"2102.02028","title":"Music source separation conditioned on 3D point clouds","created":"2021-02-03","cited_by_count":2,"area":null},{"id":"2203.13535","title":"SeCo: Separating Unknown Musical Visual Sounds with Consistency Guidance","created":"2022-03-25","cited_by_count":2,"area":null},{"id":"2306.10684","title":"Visually-Guided Sound Source Separation with Audio-Visual Predictive Coding","created":"2023-06-19","cited_by_count":2,"area":null},{"id":"2403.19002","title":"Robust Active Speaker Detection in Noisy Environments","created":"2024-03-27","cited_by_count":2,"area":null},{"id":"2409.19270","title":"OpenSep: Leveraging Large Language Models with Textual Inversion for Open World Audio Separation","created":"2024-09-28","cited_by_count":2,"area":null},{"id":"2412.00049","title":"A Survey of Recent Advances and Challenges in Deep Audio-Visual Correlation Learning","created":"2024-11-24","cited_by_count":2,"area":null},{"id":"2506.00358","title":"$\\texttt{AVROBUSTBENCH}$: Benchmarking the Robustness of Audio-Visual Recognition Models at Test-Time","created":"2025-05-31","cited_by_count":2,"area":null},{"id":"2506.01015","title":"AuralSAM2: Enabling SAM2 Hear Through Pyramid Audio-Visual Feature Prompting","created":"2025-06-01","cited_by_count":2,"area":null},{"id":"2105.01517","title":"Where and When: Space-Time Attention for Audio-Visual Explanations","created":"2021-05-04","cited_by_count":1,"area":null},{"id":"2202.05961","title":"Audio-Visual Fusion Layers for Event Type Aware Video Recognition","created":"2022-02-12","cited_by_count":1,"area":null},{"id":"2309.03869","title":"Text-to-feature diffusion for audio-visual few-shot learning","created":"2023-09-07","cited_by_count":1,"area":null},{"id":"2312.14021","title":"Leveraging Visual Supervision for Array-based Active Speaker Detection and Localization","created":"2023-12-21","cited_by_count":1,"area":null},{"id":"2103.13096","title":"Repetitive Activity Counting by Sight and Sound","created":"2021-03-24","cited_by_count":0,"area":null},{"id":"2106.00180","title":"Dual Normalization Multitasking for Audio-Visual Sounding Object Localization","created":"2021-06-01","cited_by_count":0,"area":null},{"id":"2202.13673","title":"Recent Advances and Challenges in Deep Audio-Visual Correlation Learning","created":"2022-02-28","cited_by_count":0,"area":null},{"id":"2203.15991","title":"The Sound of Bounding-Boxes","created":"2022-03-30","cited_by_count":0,"area":null}],"next_cursor":"100"}