{"total":114,"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":"2104.11116","title":"Pose-Controllable Talking Face Generation by Implicitly Modularized Audio-Visual Representation","created":"2021-04-22","cited_by_count":288,"area":null},{"id":"2207.12393","title":"CelebV-HQ: A Large-Scale Video Facial Attributes Dataset","created":"2022-07-25","cited_by_count":250,"area":null},{"id":"2203.14072","title":"Learning to Answer Questions in Dynamic Audio-Visual Scenarios","created":"2022-03-26","cited_by_count":191,"area":null},{"id":"2202.13084","title":"Visual Speech Recognition for Multiple Languages in the Wild","created":"2022-02-26","cited_by_count":95,"area":null},{"id":"2301.01767","title":"Self-Supervised Video Forensics by Audio-Visual Anomaly Detection","created":"2023-01-04","cited_by_count":85,"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":"2211.00924","title":"SyncTalkFace: Talking Face Generation with Precise Lip-Syncing via Audio-Lip Memory","created":"2022-11-02","cited_by_count":65,"area":null},{"id":"2211.15058","title":"Mix and Localize: Localizing Sound Sources in Mixtures","created":"2022-11-28","cited_by_count":54,"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":"2305.11019","title":"Annotation-free Audio-Visual Segmentation","created":"2023-05-18","cited_by_count":46,"area":null},{"id":"2202.06875","title":"Visual Acoustic Matching","created":"2022-02-14","cited_by_count":45,"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":"2308.05037","title":"Separate Anything You Describe","created":"2023-08-09","cited_by_count":43,"area":null},{"id":"2105.07142","title":"Move2Hear: Active Audio-Visual Source Separation","created":"2021-05-15","cited_by_count":35,"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":"2311.05152","title":"Cross-modal Prompts: Adapting Large Pre-trained Models for Audio-Visual Downstream Tasks","created":"2023-11-09","cited_by_count":31,"area":null},{"id":"2204.11573","title":"Joint-Modal Label Denoising for Weakly-Supervised Audio-Visual Video Parsing","created":"2022-04-25","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":"2308.05421","title":"Progressive Spatio-temporal Perception for Audio-Visual Question Answering","created":"2023-08-10","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":"2403.11074","title":"Audio-Visual Segmentation via Unlabeled Frame Exploitation","created":"2024-03-17","cited_by_count":28,"area":null},{"id":"2201.01928","title":"Egocentric Deep Multi-Channel Audio-Visual Active Speaker Localization","created":"2022-01-06","cited_by_count":27,"area":null},{"id":"2302.13700","title":"Imaginary Voice: Face-styled Diffusion Model for Text-to-Speech","created":"2023-02-27","cited_by_count":27,"area":"diffusion"},{"id":"2106.07732","title":"Learning Audio-Visual Dereverberation","created":"2021-06-14","cited_by_count":26,"area":null},{"id":"2111.14448","title":"AVA-AVD: Audio-Visual Speaker Diarization in the Wild","created":"2021-11-29","cited_by_count":25,"area":null},{"id":"2203.17263","title":"Audio-Visual Speech Codecs: Rethinking Audio-Visual Speech Enhancement by Re-Synthesis","created":"2022-03-31","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":"2406.09286","title":"FlowAVSE: Efficient Audio-Visual Speech Enhancement with Conditional Flow Matching","created":"2024-06-13","cited_by_count":23,"area":"diffusion"},{"id":"2305.13050","title":"AudioToken: Adaptation of Text-Conditioned Diffusion Models for Audio-to-Image Generation","created":"2023-05-22","cited_by_count":22,"area":"diffusion"},{"id":"2309.05281","title":"Class-Incremental Grouping Network for Continual Audio-Visual Learning","created":"2023-09-11","cited_by_count":22,"area":null},{"id":"2203.02216","title":"Look\\&Listen: Multi-Modal Correlation Learning for Active Speaker Detection and Speech Enhancement","created":"2022-03-04","cited_by_count":20,"area":null},{"id":"2311.15080","title":"Weakly-Supervised Audio-Visual Segmentation","created":"2023-11-25","cited_by_count":19,"area":null},{"id":"2204.12489","title":"Sound Localization by Self-Supervised Time Delay Estimation","created":"2022-04-26","cited_by_count":18,"area":null},{"id":"2303.11329","title":"Sound Localization from Motion: Jointly Learning Sound Direction and Camera Rotation","created":"2023-03-20","cited_by_count":18,"area":null},{"id":"2111.05846","title":"Structure from Silence: Learning Scene Structure from Ambient Sound","created":"2021-11-10","cited_by_count":17,"area":null},{"id":"2405.12221","title":"Images that Sound: Composing Images and Sounds on a Single Canvas","created":"2024-05-20","cited_by_count":17,"area":"diffusion"},{"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":"2303.06357","title":"CASP-Net: Rethinking Video Saliency Prediction from an Audio-VisualConsistency Perceptual Perspective","created":"2023-03-11","cited_by_count":15,"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":"2306.00595","title":"Revisit Weakly-Supervised Audio-Visual Video Parsing from the Language Perspective","created":"2023-06-01","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":"2306.01432","title":"Audio-Visual Speech Enhancement with Score-Based Generative Models","created":"2023-06-02","cited_by_count":12,"area":"diffusion"},{"id":"2407.13083","title":"Modeling and Driving Human Body Soundfields through Acoustic Primitives","created":"2024-07-18","cited_by_count":12,"area":null},{"id":"2307.02041","title":"Multimodal Imbalance-Aware Gradient Modulation for Weakly-supervised Audio-Visual Video Parsing","created":"2023-07-05","cited_by_count":11,"area":null},{"id":"2308.08143","title":"IIANet: An Intra- and Inter-Modality Attention Network for Audio-Visual Speech Separation","created":"2023-08-16","cited_by_count":11,"area":null},{"id":"2404.05206","title":"SoundingActions: Learning How Actions Sound from Narrated Egocentric Videos","created":"2024-04-08","cited_by_count":11,"area":null},{"id":"2307.04231","title":"Mx2M: Masked Cross-Modality Modeling in Domain Adaptation for 3D Semantic Segmentation","created":"2023-07-09","cited_by_count":10,"area":null},{"id":"2212.10744","title":"An Audio-Visual Speech Separation Model Inspired by Cortico-Thalamo-Cortical Circuits","created":"2022-12-21","cited_by_count":9,"area":null},{"id":"2310.19581","title":"Seeing Through the Conversation: Audio-Visual Speech Separation based on Diffusion Model","created":"2023-10-30","cited_by_count":9,"area":"diffusion"},{"id":"2503.16956","title":"From Faces to Voices: Learning Hierarchical Representations for High-quality Video-to-Speech","created":"2025-03-21","cited_by_count":9,"area":null},{"id":"2211.10999","title":"LA-VocE: Low-SNR Audio-visual Speech Enhancement using Neural Vocoders","created":"2022-11-20","cited_by_count":8,"area":null},{"id":"2212.11377","title":"ReVISE: Self-Supervised Speech Resynthesis with Visual Input for Universal and Generalized Speech Enhancement","created":"2022-12-21","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":"2404.12725","title":"Separate in the Speech Chain: Cross-Modal Conditional Audio-Visual Target Speech Extraction","created":"2024-04-19","cited_by_count":7,"area":null},{"id":"2506.02178","title":"Cocktail-Party Audio-Visual Speech Recognition","created":"2025-06-02","cited_by_count":7,"area":null},{"id":"2310.15130","title":"Novel-View Acoustic Synthesis from 3D Reconstructed Rooms","created":"2023-10-23","cited_by_count":6,"area":null},{"id":"2311.06285","title":"Sounding Bodies: Modeling 3D Spatial Sound of Humans Using Body Pose and Audio","created":"2023-11-01","cited_by_count":6,"area":null},{"id":"2411.07751","title":"SAV-SE: Scene-aware Audio-Visual Speech Enhancement with Selective State Space Model","created":"2024-11-12","cited_by_count":6,"area":"ssm"},{"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":"2302.05907","title":"LipLearner: Customizable Silent Speech Interactions on Mobile Devices","created":"2023-02-12","cited_by_count":5,"area":null},{"id":"2309.08030","title":"AV2Wav: Diffusion-Based Re-synthesis from Continuous Self-supervised Features for Audio-Visual Speech Enhancement","created":"2023-09-14","cited_by_count":5,"area":"diffusion"},{"id":"2312.10305","title":"Self-Supervised Disentangled Representation Learning for Robust Target Speech Extraction","created":"2023-12-16","cited_by_count":5,"area":null},{"id":"2406.02554","title":"Hear Me, See Me, Understand Me: Audio-Visual Autism Behavior Recognition","created":"2024-03-22","cited_by_count":5,"area":null},{"id":"2505.12154","title":"Learning to Highlight Audio by Watching Movies","created":"2025-05-17","cited_by_count":5,"area":null},{"id":"2207.01136","title":"Beyond Visual Field of View: Perceiving 3D Environment with Echoes and Vision","created":"2022-07-03","cited_by_count":4,"area":null},{"id":"2306.00160","title":"Audio-Visual Speech Separation in Noisy Environments with a Lightweight Iterative Model","created":"2023-05-31","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":"2407.02004","title":"SAVE: Segment Audio-Visual Easy way using Segment Anything Model","created":"2024-07-02","cited_by_count":4,"area":null},{"id":"2407.07825","title":"RT-LA-VocE: Real-Time Low-SNR Audio-Visual Speech Enhancement","created":"2024-07-10","cited_by_count":4,"area":null},{"id":"2501.03181","title":"FaceSpeak: Expressive and High-Quality Speech Synthesis from Human Portraits of Different Styles","created":"2025-01-02","cited_by_count":4,"area":null},{"id":"2306.15464","title":"Large-scale unsupervised audio pre-training for video-to-speech synthesis","created":"2023-06-27","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":"2501.13375","title":"Bridging The Multi-Modality Gaps of Audio, Visual and Linguistic for Speech Enhancement","created":"2025-01-23","cited_by_count":3,"area":null},{"id":"2504.16936","title":"Multifaceted Evaluation of Audio-Visual Capability for MLLMs: Effectiveness, Efficiency, Generalizability and Robustness","created":"2025-04-03","cited_by_count":3,"area":"mllm"},{"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":"2112.09060","title":"Towards Robust Real-time Audio-Visual Speech Enhancement","created":"2021-12-16","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":"2309.17189","title":"RTFS-Net: Recurrent Time-Frequency Modelling for Efficient Audio-Visual Speech Separation","created":"2023-09-29","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":"2411.04933","title":"SaSR-Net: Source-Aware Semantic Representation Network for Enhancing Audio-Visual Question Answering","created":"2024-11-07","cited_by_count":2,"area":null},{"id":"2509.05747","title":"InterAct: A Large-Scale Dataset of Dynamic, Expressive and Interactive Activities between Two People in Daily Scenarios","created":"2025-09-06","cited_by_count":2,"area":null},{"id":"2509.23610","title":"Efficient Audio-Visual Speech Separation with Discrete Lip Semantics and Multi-Scale Global-Local Attention","created":"2025-09-28","cited_by_count":2,"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":"2209.11200","title":"Attention is All They Need: Exploring the Media Archaeology of the Computer Vision Research Paper","created":"2022-09-22","cited_by_count":1,"area":null},{"id":"2307.16584","title":"Audio-visual video-to-speech synthesis with synthesized input audio","created":"2023-07-31","cited_by_count":1,"area":null},{"id":"2401.14185","title":"TDFNet: An Efficient Audio-Visual Speech Separation Model with Top-down Fusion","created":"2024-01-25","cited_by_count":1,"area":null},{"id":"2406.11619","title":"AV-CrossNet: an Audiovisual Complex Spectral Mapping Network for Speech Separation By Leveraging Narrow- and Cross-Band Modeling","created":"2024-06-17","cited_by_count":1,"area":null},{"id":"2407.01244","title":"CLHOP: Combined Audio-Video Learning for Horse 3D Pose and Shape Estimation","created":"2024-07-01","cited_by_count":1,"area":null},{"id":"2501.18157","title":"Efficient Audiovisual Speech Processing via MUTUD: Multimodal Training and Unimodal Deployment","created":"2025-01-30","cited_by_count":1,"area":null},{"id":"2505.03186","title":"CoGenAV: Versatile Audio-Visual Representation Learning via Contrastive-Generative Synchronization","created":"2025-05-06","cited_by_count":1,"area":null},{"id":"2509.14379","title":"Diffusion-Based Unsupervised Audio-Visual Speech Separation in Noisy Environments with Noise Prior","created":"2025-09-17","cited_by_count":1,"area":null},{"id":"2510.10509","title":"MARS-Sep: Multimodal-Aligned Reinforced Sound Separation","created":"2025-10-12","cited_by_count":1,"area":"alignment"},{"id":"2602.03762","title":"Conditional Flow Matching for Visually-Guided Acoustic Highlighting","created":"2026-02-03","cited_by_count":1,"area":"diffusion"}],"next_cursor":"100"}