{"total":113,"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":"2303.17480","title":"Seeing What You Said: Talking Face Generation Guided by a Lip Reading Expert","created":"2023-03-29","cited_by_count":98,"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":"2110.07603","title":"Sub-word Level Lip Reading With Visual Attention","created":"2021-10-14","cited_by_count":63,"area":null},{"id":"2205.10237","title":"M3ED: Multi-modal Multi-scene Multi-label Emotional Dialogue Database","created":"2022-05-09","cited_by_count":50,"area":null},{"id":"2305.13353","title":"RenderMe-360: A Large Digital Asset Library and Benchmarks Towards High-fidelity Head Avatars","created":"2023-05-22","cited_by_count":45,"area":null},{"id":"2209.02604","title":"Make Acoustic and Visual Cues Matter: CH-SIMS v2.0 Dataset and AV-Mixup Consistent Module","created":"2022-08-22","cited_by_count":44,"area":null},{"id":"2501.16566","title":"AffectGPT: A New Dataset, Model, and Benchmark for Emotion Understanding with Multimodal Large Language Models","created":"2025-01-27","cited_by_count":44,"area":"mllm"},{"id":"2209.04355","title":"MIntRec: A New Dataset for Multimodal Intent Recognition","created":"2022-09-09","cited_by_count":41,"area":null},{"id":"2303.04439","title":"A Light Weight Model for Active Speaker Detection","created":"2023-03-08","cited_by_count":40,"area":null},{"id":"2301.10939","title":"Affective Faces for Goal-Driven Dyadic Communication","created":"2023-01-26","cited_by_count":35,"area":null},{"id":"2301.08730","title":"Novel-View Acoustic Synthesis","created":"2023-01-20","cited_by_count":33,"area":null},{"id":"2207.07783","title":"Learning Long-Term Spatial-Temporal Graphs for Active Speaker Detection","created":"2022-07-15","cited_by_count":30,"area":null},{"id":"2312.09818","title":"SMILE: Multimodal Dataset for Understanding Laughter in Video with Language Models","created":"2023-12-15","cited_by_count":28,"area":null},{"id":"2406.14272","title":"MultiTalk: Enhancing 3D Talking Head Generation Across Languages with Multilingual Video Dataset","created":"2024-06-20","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":"2311.00994","title":"LaughTalk: Expressive 3D Talking Head Generation with Laughter","created":"2023-11-02","cited_by_count":27,"area":null},{"id":"2403.10943","title":"MIntRec2.0: A Large-scale Benchmark Dataset for Multimodal Intent Recognition and Out-of-scope Detection in Conversations","created":"2024-03-16","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":"2203.14250","title":"End-to-End Active Speaker Detection","created":"2022-03-27","cited_by_count":25,"area":null},{"id":"2301.08237","title":"LoCoNet: Long-Short Context Network for Active Speaker Detection","created":"2023-01-19","cited_by_count":25,"area":null},{"id":"2512.22065","title":"StreamAvatar: Streaming Diffusion Models for Real-Time Interactive Human Avatars","created":"2025-12-26","cited_by_count":25,"area":"diffusion"},{"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":"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":"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":"2212.06301","title":"Egocentric Video Task Translation","created":"2022-12-13","cited_by_count":19,"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":"2303.16024","title":"Egocentric Auditory Attention Localization in Conversations","created":"2023-03-28","cited_by_count":18,"area":null},{"id":"2309.12306","title":"TalkNCE: Improving Active Speaker Detection with Talk-Aware Contrastive Learning","created":"2023-09-21","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":"2309.08738","title":"AV-MaskEnhancer: Enhancing Video Representations through Audio-Visual Masked Autoencoder","created":"2023-09-15","cited_by_count":11,"area":null},{"id":"2504.02386","title":"VoiceCraft-Dub: Automated Video Dubbing with Neural Codec Language Models","created":"2025-04-03","cited_by_count":11,"area":null},{"id":"2505.06685","title":"Emotion-Qwen: A Unified Framework for Emotion and Vision Understanding","created":"2025-05-10","cited_by_count":11,"area":"moe"},{"id":"2604.07823","title":"LPM 1.0: Video-based Character Performance Model","created":"2026-04-09","cited_by_count":11,"area":null},{"id":"2505.12654","title":"Predicting Turn-Taking and Backchannel in Human-Machine Conversations Using Linguistic, Acoustic, and Visual Signals","created":"2025-05-19","cited_by_count":10,"area":null},{"id":"2206.10421","title":"Rethinking Audio-visual Synchronization for Active Speaker Detection","created":"2022-06-21","cited_by_count":9,"area":null},{"id":"2210.07764","title":"Intel Labs at Ego4D Challenge 2022: A Better Baseline for Audio-Visual Diarization","created":"2022-10-14","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":"2412.17295","title":"Friends-MMC: A Dataset for Multi-modal Multi-party Conversation Understanding","created":"2024-12-23","cited_by_count":9,"area":null},{"id":"2502.12478","title":"MSE-Adapter: A Lightweight Plugin Endowing LLMs with the Capability to Perform Multimodal Sentiment Analysis and Emotion Recognition","created":"2025-02-18","cited_by_count":9,"area":null},{"id":"2505.11109","title":"MAVOS-DD: Multilingual Audio-Video Open-Set Deepfake Detection Benchmark","created":"2025-05-16","cited_by_count":9,"area":null},{"id":"2207.01869","title":"Distance Matters in Human-Object Interaction Detection","created":"2022-07-05","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":"2303.05321","title":"WASD: A Wilder Active Speaker Detection Dataset","created":"2023-03-09","cited_by_count":6,"area":null},{"id":"2306.10608","title":"STHG: Spatial-Temporal Heterogeneous Graph Learning for Advanced Audio-Visual Diarization","created":"2023-06-18","cited_by_count":6,"area":null},{"id":"2501.11899","title":"LASER: Lip Landmark Assisted Speaker Detection for Robustness","created":"2025-01-21","cited_by_count":6,"area":null},{"id":"2505.21954","title":"Revisiting Active Speaker Detection: An In-the-Wild Benchmark for Generalization and Robustness","created":"2025-05-28","cited_by_count":6,"area":null},{"id":"2512.14234","title":"ViBES: A Conversational Agent with Behaviorally-Intelligent 3D Virtual Body","created":"2025-12-16","cited_by_count":6,"area":"agents"},{"id":"2605.26486","title":"LongCat-Video-Avatar 1.5 Technical Report","created":"2026-05-26","cited_by_count":6,"area":null},{"id":"2203.16840","title":"Speaker Extraction with Co-Speech Gestures Cue","created":"2022-03-31","cited_by_count":5,"area":null},{"id":"2408.05364","title":"Spherical World-Locking for Audio-Visual Localization in Egocentric Videos","created":"2024-08-09","cited_by_count":5,"area":null},{"id":"2412.08594","title":"ASDnB: Merging Face with Body Cues For Robust Active Speaker Detection","created":"2024-12-11","cited_by_count":5,"area":null},{"id":"2505.01068","title":"Multimodal Transformers are Hierarchical Modal-wise Heterogeneous Graphs","created":"2025-05-02","cited_by_count":5,"area":null},{"id":"2510.23727","title":"MUStReason: A Benchmark for Diagnosing Pragmatic Reasoning in Video-LMs for Multimodal Sarcasm Detection","created":"2025-10-27","cited_by_count":5,"area":null},{"id":"2112.01479","title":"Learning Spatial-Temporal Graphs for Active Speaker Detection","created":"2021-12-02","cited_by_count":4,"area":null},{"id":"2212.00539","title":"Audio-Visual Activity Guided Cross-Modal Identity Association for Active Speaker Detection","created":"2022-12-01","cited_by_count":4,"area":null},{"id":"2301.10180","title":"A Multi-Purpose Audio-Visual Corpus for Multi-Modal Persian Speech Recognition: the Arman-AV Dataset","created":"2023-01-21","cited_by_count":4,"area":null},{"id":"2309.08295","title":"A Real-Time Active Speaker Detection System Integrating an Audio-Visual Signal with a Spatial Querying Mechanism","created":"2023-09-15","cited_by_count":4,"area":null},{"id":"2505.17536","title":"Multimodal Conversation Structure Understanding","created":"2025-05-23","cited_by_count":4,"area":"mllm"},{"id":"2506.21080","title":"EgoAdapt: Adaptive Multisensory Distillation and Policy Learning for Efficient Egocentric Perception","created":"2025-06-26","cited_by_count":4,"area":null},{"id":"2507.21448","title":"Real-Time Audio-Visual Speech Enhancement Using Pre-trained Visual Representations","created":"2025-07-29","cited_by_count":4,"area":null},{"id":"2210.00753","title":"Push-Pull: Characterizing the Adversarial Robustness for Audio-Visual Active Speaker Detection","created":"2022-10-03","cited_by_count":3,"area":null},{"id":"2211.15377","title":"Whose Emotion Matters? Speaking Activity Localisation without Prior Knowledge","created":"2022-11-23","cited_by_count":3,"area":null},{"id":"2312.09066","title":"CMOSE: Comprehensive Multi-Modality Online Student Engagement Dataset with High-Quality Labels","created":"2023-12-14","cited_by_count":3,"area":null},{"id":"2404.19171","title":"Explicit Correlation Learning for Generalizable Cross-Modal Deepfake Detection","created":"2024-04-30","cited_by_count":3,"area":null},{"id":"2504.05576","title":"SoundVista: Novel-View Ambient Sound Synthesis via Visual-Acoustic Binding","created":"2025-04-08","cited_by_count":3,"area":null},{"id":"2505.15772","title":"MIKU-PAL: An Automated and Standardized Multi-Modal Method for Speech Paralinguistic and Affect Labeling","created":"2025-05-21","cited_by_count":3,"area":null},{"id":"2206.10861","title":"UniCon+: ICTCAS-UCAS Submission to the AVA-ActiveSpeaker Task at ActivityNet Challenge 2022","created":"2022-06-22","cited_by_count":2,"area":null},{"id":"2210.15563","title":"Multimodal Transformer Distillation for Audio-Visual Synchronization","created":"2022-10-27","cited_by_count":2,"area":null},{"id":"2304.04068","title":"Word-level Persian Lipreading Dataset","created":"2023-04-08","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":"2408.12102","title":"Integrating Audio, Visual, and Semantic Information for Enhanced Multimodal Speaker Diarization","created":"2024-08-22","cited_by_count":2,"area":null},{"id":"2412.13037","title":"TAME: Temporal Audio-based Mamba for Enhanced Drone Trajectory Estimation and Classification","created":"2024-12-17","cited_by_count":2,"area":"ssm"},{"id":"2602.00597","title":"Hermes the Polyglot: A Unified Framework to Enhance Expressiveness for Multimodal Interlingual Subtitling","created":"2026-01-31","cited_by_count":2,"area":null},{"id":"2606.16731","title":"MuVAP: Multimodal Multiparty Voice Activity Projection for Turn-taking Prediction in the Wild","created":"2026-06-15","cited_by_count":2,"area":null},{"id":"2211.01299","title":"Late Audio-Visual Fusion for In-The-Wild Speaker Diarization","created":"2022-11-02","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":"2402.13152","title":"AnnoTheia: A Semi-Automatic Annotation Toolkit for Audio-Visual Speech Technologies","created":"2024-02-20","cited_by_count":1,"area":null},{"id":"2409.09018","title":"An Efficient and Streaming Audio Visual Active Speaker Detection System","created":"2024-09-13","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":"2511.17181","title":"Investigating self-supervised representations for audio-visual deepfake detection","created":"2025-11-21","cited_by_count":1,"area":null},{"id":"2512.15707","title":"GateFusion: Hierarchical Gated Cross-Modal Fusion for Active Speaker Detection","created":"2025-12-17","cited_by_count":1,"area":null},{"id":"2601.01749","title":"MANGO:Natural Multi-speaker 3D Talking Head Generation via 2D-Lifted Enhancement","created":"2026-01-05","cited_by_count":1,"area":null},{"id":"2602.19004","title":"MoBind: Motion Binding for Fine-Grained IMU-Video Pose Alignment","created":"2026-02-22","cited_by_count":1,"area":null},{"id":"2603.24569","title":"POLY-SIM: Polyglot Speaker Identification with Missing Modality Grand Challenge 2026 Evaluation Plan","created":"2026-03-25","cited_by_count":1,"area":null},{"id":"2604.17211","title":"EmbodiedHead: Real-Time Listening and Speaking Avatar for Conversational Agents","created":"2026-04-19","cited_by_count":1,"area":null},{"id":"2609.15128","title":"Omni-Streaming Thinking","created":"2026-09-14","cited_by_count":1,"area":null},{"id":"2203.02655","title":"Audio-visual speech separation based on joint feature representation with cross-modal attention","created":"2022-03-05","cited_by_count":0,"area":null},{"id":"2210.06177","title":"VCSE: Time-Domain Visual-Contextual Speaker Extraction Network","created":"2022-10-09","cited_by_count":0,"area":null},{"id":"2402.13004","title":"Comparison of Conventional Hybrid and CTC/Attention Decoders for Continuous Visual Speech Recognition","created":"2024-02-20","cited_by_count":0,"area":null},{"id":"2406.00495","title":"Audio-Visual Talker Localization in Video for Spatial Sound Reproduction","created":"2024-06-01","cited_by_count":0,"area":null},{"id":"2410.14509","title":"CLIP-VAD: Exploiting Vision-Language Models for Voice Activity Detection","created":"2024-10-18","cited_by_count":0,"area":"mllm"},{"id":"2411.13674","title":"FabuLight-ASD: Unveiling Speech Activity via Body Language","created":"2024-11-20","cited_by_count":0,"area":null},{"id":"2502.00464","title":"Evaluation of End-to-End Continuous Spanish Lipreading in Different Data Conditions","created":"2025-02-01","cited_by_count":0,"area":null},{"id":"2502.02172","title":"EditIQ: Automated Cinematic Editing of Static Wide-Angle Videos via Dialogue Interpretation and Saliency Cues","created":"2025-02-04","cited_by_count":0,"area":null},{"id":"2506.02247","title":"EgoVIS@CVPR: PAIR-Net: Enhancing Egocentric Speaker Detection via Pretrained Audio-Visual Fusion and Alignment Loss","created":"2025-06-02","cited_by_count":0,"area":null},{"id":"2512.17655","title":"Bitbox: Behavioral Imaging Toolbox for Computational Analysis of Behavior from Videos","created":"2025-12-19","cited_by_count":0,"area":null},{"id":"2601.07565","title":"Expert-Guided Multimodal Fusion for Unified Emotion and Sentiment Analysis","created":"2026-01-12","cited_by_count":0,"area":null},{"id":"2603.16966","title":"CineSRD: Leveraging Visual, Acoustic, and Linguistic Cues for Open-World Visual Media Speaker Diarization","created":"2026-03-17","cited_by_count":0,"area":null},{"id":"2603.18082","title":"EgoAdapt: Enhancing Robustness in Egocentric Interactive Speaker Detection Under Missing Modalities","created":"2026-03-18","cited_by_count":0,"area":null}],"next_cursor":"100"}