{"total":298,"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":"2206.06488","title":"Multimodal Learning with Transformers: A Survey","created":"2022-06-13","cited_by_count":400,"area":null},{"id":"2201.02184","title":"Learning Audio-Visual Speech Representation by Masked Multimodal Cluster Prediction","created":"2022-01-05","cited_by_count":287,"area":null},{"id":"2102.06657","title":"End-to-end Audio-visual Speech Recognition with Conformers","created":"2021-02-12","cited_by_count":151,"area":null},{"id":"2111.01690","title":"Recent Advances in End-to-End Automatic Speech Recognition","created":"2021-11-02","cited_by_count":140,"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":"2303.14307","title":"Auto-AVSR: Audio-Visual Speech Recognition with Automatic Labels","created":"2023-03-25","cited_by_count":114,"area":null},{"id":"2211.14758","title":"VideoReTalking: Audio-based Lip Synchronization for Talking Head Video Editing In the Wild","created":"2022-11-27","cited_by_count":106,"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":"2305.08293","title":"Identity-Preserving Talking Face Generation with Landmark and Appearance Priors","created":"2023-05-15","cited_by_count":98,"area":null},{"id":"2306.08990","title":"Emotional Speech-Driven Animation with Content-Emotion Disentanglement","created":"2023-06-15","cited_by_count":98,"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":"2311.17590","title":"SyncTalk: The Devil is in the Synchronization for Talking Head Synthesis","created":"2023-11-29","cited_by_count":86,"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":"2404.01647","title":"EDTalk: Efficient Disentanglement for Emotional Talking Head Synthesis","created":"2024-04-02","cited_by_count":80,"area":null},{"id":"2201.01763","title":"Robust Self-Supervised Audio-Visual Speech Recognition","created":"2022-01-05","cited_by_count":75,"area":null},{"id":"2403.17881","title":"Deepfake Generation and Detection: A Benchmark and Survey","created":"2024-03-26","cited_by_count":67,"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":"2203.14263","title":"A General Survey on Attention Mechanisms in Deep Learning","created":"2022-03-27","cited_by_count":64,"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":"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":"2212.06246","title":"Jointly Learning Visual and Auditory Speech Representations from Raw Data","created":"2022-12-12","cited_by_count":47,"area":null},{"id":"2106.09171","title":"LiRA: Learning Visual Speech Representations from Audio through Self-supervision","created":"2021-06-16","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":"2303.08536","title":"Watch or Listen: Robust Audio-Visual Speech Recognition with Visual Corruption Modeling and Reliability Scoring","created":"2023-03-15","cited_by_count":42,"area":null},{"id":"2106.11059","title":"Improving Multi-Modal Learning with Uni-Modal Teachers","created":"2021-06-21","cited_by_count":41,"area":null},{"id":"2204.01726","title":"Lip to Speech Synthesis with Visual Context Attentional GAN","created":"2022-04-04","cited_by_count":41,"area":null},{"id":"2306.09126","title":"STARSS23: An Audio-Visual Dataset of Spatial Recordings of Real Scenes with Spatiotemporal Annotations of Sound Events","created":"2023-06-15","cited_by_count":41,"area":null},{"id":"2406.07867","title":"Let's Go Real Talk: Spoken Dialogue Model for Face-to-Face Conversation","created":"2024-06-12","cited_by_count":41,"area":null},{"id":"2112.04432","title":"Audio-Visual Synchronisation in the wild","created":"2021-12-08","cited_by_count":40,"area":null},{"id":"2110.08243","title":"Neural Dubber: Dubbing for Videos According to Scripts","created":"2021-10-15","cited_by_count":39,"area":null},{"id":"2204.01725","title":"Distinguishing Homophenes Using Multi-Head Visual-Audio Memory for Lip Reading","created":"2022-04-04","cited_by_count":39,"area":null},{"id":"2303.00628","title":"MuAViC: A Multilingual Audio-Visual Corpus for Robust Speech Recognition and Robust Speech-to-Text Translation","created":"2023-03-01","cited_by_count":39,"area":null},{"id":"2209.15200","title":"An efficient encoder-decoder architecture with top-down attention for speech separation","created":"2022-09-30","cited_by_count":38,"area":null},{"id":"2201.08071","title":"Temporal Sentence Grounding in Videos: A Survey and Future Directions","created":"2022-01-20","cited_by_count":37,"area":null},{"id":"2211.11275","title":"VATLM: Visual-Audio-Text Pre-Training with Unified Masked Prediction for Speech Representation Learning","created":"2022-11-21","cited_by_count":37,"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":"2401.15668","title":"Lips Are Lying: Spotting the Temporal Inconsistency between Audio and Visual in Lip-Syncing DeepFakes","created":"2024-01-28","cited_by_count":32,"area":null},{"id":"2103.10211","title":"Space-Time Crop & Attend: Improving Cross-modal Video Representation Learning","created":"2021-03-18","cited_by_count":31,"area":null},{"id":"2201.10439","title":"Transformer-Based Video Front-Ends for Audio-Visual Speech Recognition for Single and Multi-Person Video","created":"2022-01-25","cited_by_count":31,"area":null},{"id":"2505.12079","title":"SepPrune: Structured Pruning for Efficient Deep Speech Separation","created":"2025-05-17","cited_by_count":31,"area":null},{"id":"2507.09862","title":"SpeakerVid-5M: A Large-Scale High-Quality Dataset for Audio-Visual Dyadic Interactive Human Generation","created":"2025-07-14","cited_by_count":30,"area":null},{"id":"2305.19603","title":"Intelligible Lip-to-Speech Synthesis with Speech Units","created":"2023-05-31","cited_by_count":28,"area":null},{"id":"2104.02775","title":"Looking into Your Speech: Learning Cross-modal Affinity for Audio-visual Speech Separation","created":"2021-03-25","cited_by_count":27,"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":"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":"2302.06419","title":"AV-data2vec: Self-supervised Learning of Audio-Visual Speech Representations with Contextualized Target Representations","created":"2023-02-10","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":"2312.05430","title":"FT2TF: First-Person Statement Text-To-Talking Face Generation","created":"2023-12-09","cited_by_count":26,"area":null},{"id":"2411.11278","title":"Towards Open-Vocabulary Audio-Visual Event Localization","created":"2024-11-18","cited_by_count":26,"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":"2201.06260","title":"Towards Realistic Visual Dubbing with Heterogeneous Sources","created":"2022-01-17","cited_by_count":24,"area":null},{"id":"2207.06020","title":"Visual Context-driven Audio Feature Enhancement for Robust End-to-End Audio-Visual Speech Recognition","created":"2022-07-13","cited_by_count":24,"area":null},{"id":"2101.06053","title":"The Multimodal Sentiment Analysis in Car Reviews (MuSe-CaR) Dataset: Collection, Insights and Improvements","created":"2021-01-15","cited_by_count":22,"area":null},{"id":"2205.05072","title":"Learning Visual Styles from Audio-Visual Associations","created":"2022-05-10","cited_by_count":22,"area":null},{"id":"2209.14156","title":"TVLT: Textless Vision-Language Transformer","created":"2022-09-28","cited_by_count":22,"area":null},{"id":"2301.01456","title":"Audio-Visual Efficient Conformer for Robust Speech Recognition","created":"2023-01-04","cited_by_count":22,"area":null},{"id":"2402.05457","title":"It's Never Too Late: Fusing Acoustic Information into Large Language Models for Automatic Speech Recognition","created":"2024-02-08","cited_by_count":22,"area":null},{"id":"2205.10839","title":"Deep Learning for Visual Speech Analysis: A Survey","created":"2022-05-22","cited_by_count":21,"area":null},{"id":"2302.08841","title":"Lip-to-Speech Synthesis in the Wild with Multi-task Learning","created":"2023-02-17","cited_by_count":21,"area":null},{"id":"2303.17200","title":"SynthVSR: Scaling Up Visual Speech Recognition With Synthetic Supervision","created":"2023-03-30","cited_by_count":21,"area":null},{"id":"2405.10272","title":"Faces that Speak: Jointly Synthesising Talking Face and Speech from Text","created":"2024-05-16","cited_by_count":21,"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":"2206.12714","title":"Defending Multimodal Fusion Models against Single-Source Adversaries","created":"2022-06-25","cited_by_count":20,"area":null},{"id":"2204.02090","title":"VocaLiST: An Audio-Visual Synchronisation Model for Lips and Voices","created":"2022-04-05","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":"2308.12558","title":"Hyperbolic Audio-visual Zero-shot Learning","created":"2023-08-24","cited_by_count":19,"area":null},{"id":"2503.11315","title":"MMS-LLaMA: Efficient LLM-based Audio-Visual Speech Recognition with Minimal Multimodal Speech Tokens","created":"2025-03-14","cited_by_count":19,"area":null},{"id":"2204.01265","title":"Multi-modality Associative Bridging through Memory: Speech Sound Recollected from Face Video","created":"2022-04-04","cited_by_count":18,"area":null},{"id":"2206.04523","title":"Face-Dubbing++: Lip-Synchronous, Voice Preserving Translation of Videos","created":"2022-06-09","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":"2309.16772","title":"XVO: Generalized Visual Odometry via Cross-Modal Self-Training","created":"2023-09-28","cited_by_count":18,"area":null},{"id":"2101.10254","title":"Multi-task Learning Approach for Automatic Modulation and Wireless Signal Classification","created":"2021-01-25","cited_by_count":17,"area":null},{"id":"2201.05845","title":"Recent Progress in the CUHK Dysarthric Speech Recognition System","created":"2022-01-15","cited_by_count":17,"area":null},{"id":"2208.04498","title":"Speaker-adaptive Lip Reading with User-dependent Padding","created":"2022-08-09","cited_by_count":17,"area":null},{"id":"2405.04327","title":"Audio-Visual Speech Representation Expert for Enhanced Talking Face Video Generation and Evaluation","created":"2024-05-07","cited_by_count":17,"area":null},{"id":"2507.10203","title":"Improving Multimodal Learning via Imbalanced Learning","created":"2025-07-14","cited_by_count":17,"area":null},{"id":"2109.02081","title":"Deep Person Generation: A Survey from the Perspective of Face, Pose and Cloth Synthesis","created":"2021-09-05","cited_by_count":16,"area":null},{"id":"2303.16501","title":"AVFormer: Injecting Vision into Frozen Speech Models for Zero-Shot AV-ASR","created":"2023-03-29","cited_by_count":16,"area":null},{"id":"2308.07593","title":"AKVSR: Audio Knowledge Empowered Visual Speech Recognition by Compressing Audio Knowledge of a Pretrained Model","created":"2023-08-15","cited_by_count":16,"area":null},{"id":"2308.09311","title":"Lip Reading for Low-resource Languages by Learning and Combining General Speech Knowledge and Language-specific Knowledge","created":"2023-08-18","cited_by_count":16,"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":"2507.10213","title":"Boosting Multimodal Learning via Disentangled Gradient Learning","created":"2025-07-14","cited_by_count":16,"area":null},{"id":"2401.10113","title":"Exposing Lip-syncing Deepfakes from Mouth Inconsistencies","created":"2024-01-18","cited_by_count":15,"area":null},{"id":"2302.08102","title":"Prompt Tuning of Deep Neural Networks for Speaker-adaptive Visual Speech Recognition","created":"2023-02-16","cited_by_count":14,"area":null},{"id":"2303.05309","title":"MixSpeech: Cross-Modality Self-Learning with Audio-Visual Stream Mixup for Visual Speech Translation and Recognition","created":"2023-03-09","cited_by_count":14,"area":null},{"id":"2303.11548","title":"Emotionally Enhanced Talking Face Generation","created":"2023-03-21","cited_by_count":14,"area":null},{"id":"2312.02512","title":"AV2AV: Direct Audio-Visual Speech to Audio-Visual Speech Translation with Unified Audio-Visual Speech Representation","created":"2023-12-05","cited_by_count":14,"area":null},{"id":"2406.12233","title":"SyncVSR: Data-Efficient Visual Speech Recognition with End-to-End Crossmodal Audio Token Synchronization","created":"2024-06-18","cited_by_count":14,"area":null},{"id":"2110.03342","title":"VisualTTS: TTS with Accurate Lip-Speech Synchronization for Automatic Voice Over","created":"2021-10-07","cited_by_count":13,"area":null},{"id":"2206.07684","title":"AVATAR: Unconstrained Audiovisual Speech Recognition","created":"2022-06-15","cited_by_count":13,"area":null},{"id":"2307.09368","title":"Audio-driven Talking Face Generation with Stabilized Synchronization Loss","created":"2023-07-18","cited_by_count":13,"area":null},{"id":"2309.08535","title":"Visual Speech Recognition for Languages with Limited Labeled Data using Automatic Labels from Whisper","created":"2023-09-15","cited_by_count":13,"area":null},{"id":"2203.07996","title":"Leveraging Unimodal Self-Supervised Learning for Multimodal Audio-Visual Speech Recognition","created":"2022-02-24","cited_by_count":12,"area":null},{"id":"2308.06112","title":"Lip2Vec: Efficient and Robust Visual Speech Recognition via Latent-to-Latent Visual to Audio Representation Mapping","created":"2023-08-11","cited_by_count":12,"area":null},{"id":"2403.04245","title":"A Study of Dropout-Induced Modality Bias on Robustness to Missing Video Frames for Audio-Visual Speech Recognition","created":"2024-03-07","cited_by_count":12,"area":null},{"id":"2411.10193","title":"DiMoDif: Discourse Modality-information Differentiation for Audio-visual Deepfake Detection and Localization","created":"2024-11-15","cited_by_count":12,"area":null},{"id":"2110.15957","title":"Visual Keyword Spotting with Attention","created":"2021-10-29","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}],"next_cursor":"100"}