{"total":209,"rows":[{"id":"2105.12397","title":"Improving Sign Language Translation with Monolingual Data by Sign Back-Translation","created":"2021-05-26","cited_by_count":179,"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":"2303.14307","title":"Auto-AVSR: Audio-Visual Speech Recognition with Automatic Labels","created":"2023-03-25","cited_by_count":114,"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":"2207.00419","title":"Self-Supervised Learning for Videos: A Survey","created":"2022-06-18","cited_by_count":85,"area":null},{"id":"2203.09324","title":"Localizing Visual Sounds the Easy Way","created":"2022-03-17","cited_by_count":82,"area":null},{"id":"2103.10094","title":"KoDF: A Large-scale Korean DeepFake Detection Dataset","created":"2021-03-18","cited_by_count":80,"area":null},{"id":"2103.15916","title":"Robust Audio-Visual Instance Discrimination","created":"2021-03-29","cited_by_count":80,"area":null},{"id":"2201.00791","title":"DFA-NeRF: Personalized Talking Head Generation via Disentangled Face Attributes Neural Rendering","created":"2022-01-03","cited_by_count":80,"area":null},{"id":"2306.10799","title":"SelfTalk: A Self-Supervised Commutative Training Diagram to Comprehend 3D Talking Faces","created":"2023-06-19","cited_by_count":68,"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":"2112.13592","title":"Multimodal Image Synthesis and Editing: The Generative AI Era","created":"2021-12-27","cited_by_count":52,"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":"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":"2111.10592","title":"Deep Spoken Keyword Spotting: An Overview","created":"2021-11-20","cited_by_count":43,"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":"2309.15701","title":"HyPoradise: An Open Baseline for Generative Speech Recognition with Large Language Models","created":"2023-09-27","cited_by_count":42,"area":null},{"id":"2112.04432","title":"Audio-Visual Synchronisation in the wild","created":"2021-12-08","cited_by_count":40,"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":"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":"2404.05583","title":"Towards More General Video-based Deepfake Detection through Facial Component Guided Adaptation for Foundation Model","created":"2024-04-08","cited_by_count":38,"area":null},{"id":"2101.03682","title":"MAAS: Multi-modal Assignation for Active Speaker Detection","created":"2021-01-11","cited_by_count":36,"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":"2402.15151","title":"Where Visual Speech Meets Language: VSP-LLM Framework for Efficient and Context-Aware Visual Speech Processing","created":"2024-02-23","cited_by_count":30,"area":null},{"id":"2212.04054","title":"Learning to Dub Movies via Hierarchical Prosody Models","created":"2022-12-08","cited_by_count":29,"area":null},{"id":"2307.10008","title":"MODA: Mapping-Once Audio-driven Portrait Animation with Dual Attentions","created":"2023-07-19","cited_by_count":29,"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":"2403.11074","title":"Audio-Visual Segmentation via Unlabeled Frame Exploitation","created":"2024-03-17","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":"2311.00994","title":"LaughTalk: Expressive 3D Talking Head Generation with Laughter","created":"2023-11-02","cited_by_count":27,"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":"2308.14177","title":"AI-Generated Content (AIGC) for Various Data Modalities: A Survey","created":"2023-08-27","cited_by_count":25,"area":null},{"id":"2111.12890","title":"V2C: Visual Voice Cloning","created":"2021-11-25","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":"2104.02000","title":"Can audio-visual integration strengthen robustness under multimodal attacks?","created":"2021-04-05","cited_by_count":23,"area":null},{"id":"2412.00175","title":"Circumventing shortcuts in audio-visual deepfake detection datasets with unsupervised learning","created":"2024-11-29","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":"2301.01456","title":"Audio-Visual Efficient Conformer for Robust Speech Recognition","created":"2023-01-04","cited_by_count":22,"area":null},{"id":"2108.07640","title":"Look Who's Talking: Active Speaker Detection in the Wild","created":"2021-08-17","cited_by_count":21,"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":"2309.10787","title":"AV-SUPERB: A Multi-Task Evaluation Benchmark for Audio-Visual Representation Models","created":"2023-09-19","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":"2206.04523","title":"Face-Dubbing++: Lip-Synchronous, Voice Preserving Translation of Videos","created":"2022-06-09","cited_by_count":18,"area":null},{"id":"2108.04325","title":"AnyoneNet: Synchronized Speech and Talking Head Generation for Arbitrary Person","created":"2021-08-09","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":"2202.12883","title":"Human Detection of Political Speech Deepfakes across Transcripts, Audio, and Video","created":"2022-02-25","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":"2411.02256","title":"Unified Speech Recognition: A Single Model for Auditory, Visual, and Audiovisual Inputs","created":"2024-11-04","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":"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":"2405.10025","title":"Listen Again and Choose the Right Answer: A New Paradigm for Automatic Speech Recognition with Large Language Models","created":"2024-05-16","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":"2206.07684","title":"AVATAR: Unconstrained Audiovisual Speech Recognition","created":"2022-06-15","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":"2111.10139","title":"More than Words: In-the-Wild Visually-Driven Prosody for Text-to-Speech","created":"2021-11-19","cited_by_count":12,"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":"2205.04152","title":"Scaling up sign spotting through sign language dictionaries","created":"2022-05-09","cited_by_count":12,"area":null},{"id":"2308.15256","title":"Let There Be Sound: Reconstructing High Quality Speech from Silent Videos","created":"2023-08-29","cited_by_count":12,"area":null},{"id":"2309.02434","title":"ReliTalk: Relightable Talking Portrait Generation from a Single Video","created":"2023-09-05","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":"2104.04310","title":"Context-self contrastive pretraining for crop type semantic segmentation","created":"2021-04-09","cited_by_count":11,"area":null},{"id":"2110.15957","title":"Visual Keyword Spotting with Attention","created":"2021-10-29","cited_by_count":11,"area":null},{"id":"2308.01831","title":"Textless Unit-to-Unit training for Many-to-Many Multilingual Speech-to-Speech Translation","created":"2023-08-03","cited_by_count":11,"area":null},{"id":"2309.04814","title":"Speech2Lip: High-fidelity Speech to Lip Generation by Learning from a Short Video","created":"2023-09-09","cited_by_count":11,"area":null},{"id":"2403.14402","title":"XLAVS-R: Cross-Lingual Audio-Visual Speech Representation Learning for Noise-Robust Speech Perception","created":"2024-03-21","cited_by_count":11,"area":null},{"id":"2503.21408","title":"VALLR: Visual ASR Language Model for Lip Reading","created":"2025-03-27","cited_by_count":11,"area":null},{"id":"2112.04748","title":"LipSound2: Self-Supervised Pre-Training for Lip-to-Speech Reconstruction and Lip Reading","created":"2021-12-09","cited_by_count":10,"area":null},{"id":"2406.06612","title":"SEE-2-SOUND: Zero-Shot Spatial Environment-to-Spatial Sound","created":"2024-06-06","cited_by_count":10,"area":null},{"id":"2104.02971","title":"MPN: Multimodal Parallel Network for Audio-Visual Event Localization","created":"2021-04-07","cited_by_count":9,"area":null},{"id":"2302.02141","title":"LipFormer: Learning to Lipread Unseen Speakers based on Visual-Landmark Transformers","created":"2023-02-04","cited_by_count":9,"area":null},{"id":"2305.09212","title":"Cross-Modal Global Interaction and Local Alignment for Audio-Visual Speech Recognition","created":"2023-05-16","cited_by_count":9,"area":null},{"id":"2311.14063","title":"Do VSR Models Generalize Beyond LRS3?","created":"2023-11-23","cited_by_count":9,"area":null},{"id":"2312.04369","title":"SingingHead: A Large-scale 4D Dataset for Singing Head Animation","created":"2023-12-07","cited_by_count":9,"area":null},{"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":"2209.00642","title":"Lip-to-Speech Synthesis for Arbitrary Speakers in the Wild","created":"2022-09-01","cited_by_count":8,"area":null},{"id":"2306.06410","title":"OpenSR: Open-Modality Speech Recognition via Maintaining Multi-Modality Alignment","created":"2023-06-10","cited_by_count":8,"area":null},{"id":"2401.09802","title":"Efficient Training for Multilingual Visual Speech Recognition: Pre-training with Discretized Visual Speech Representation","created":"2024-01-18","cited_by_count":8,"area":null},{"id":"2405.14161","title":"Self-Taught Recognizer: Toward Unsupervised Adaptation for Speech Foundation Models","created":"2024-05-23","cited_by_count":8,"area":null},{"id":"2409.14340","title":"Self-Supervised Audio-Visual Soundscape Stylization","created":"2024-09-22","cited_by_count":8,"area":null},{"id":"2107.06831","title":"Parallel and High-Fidelity Text-to-Lip Generation","created":"2021-07-14","cited_by_count":7,"area":null},{"id":"2108.13630","title":"SimulLR: Simultaneous Lip Reading Transducer with Attention-Guided Adaptive Memory","created":"2021-08-31","cited_by_count":7,"area":null},{"id":"2306.10563","title":"Hearing Lips in Noise: Universal Viseme-Phoneme Mapping and Transfer for Robust Audio-Visual Speech Recognition","created":"2023-06-18","cited_by_count":7,"area":null},{"id":"2306.11541","title":"Audio-Driven 3D Facial Animation from In-the-Wild Videos","created":"2023-06-20","cited_by_count":7,"area":null},{"id":"2307.04552","title":"SparseVSR: Lightweight and Noise Robust Visual Speech Recognition","created":"2023-07-10","cited_by_count":7,"area":null},{"id":"2311.12457","title":"LIP-RTVE: An Audiovisual Database for Continuous Spanish in the Wild","created":"2023-11-21","cited_by_count":7,"area":null},{"id":"2401.09759","title":"SlideAVSR: A Dataset of Paper Explanation Videos for Audio-Visual Speech Recognition","created":"2024-01-18","cited_by_count":7,"area":null},{"id":"2403.01087","title":"Towards Accurate Lip-to-Speech Synthesis in-the-Wild","created":"2024-03-02","cited_by_count":7,"area":null},{"id":"2405.12983","title":"Multilingual Audio-Visual Speech Recognition with Hybrid CTC/RNN-T Fast Conformer","created":"2024-03-14","cited_by_count":7,"area":null},{"id":"2407.03563","title":"Learning Video Temporal Dynamics with Cross-Modal Attention for Robust Audio-Visual Speech Recognition","created":"2024-07-04","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":"2507.18863","title":"Phoneme-Level Visual Speech Recognition via Point-Visual Fusion and Language Model Reconstruction","created":"2025-07-25","cited_by_count":7,"area":null},{"id":"2104.05418","title":"Contrastive Learning of Global-Local Video Representations","created":"2021-04-07","cited_by_count":6,"area":null},{"id":"2109.08061","title":"Invertible Frowns: Video-to-Video Facial Emotion Translation","created":"2021-09-16","cited_by_count":6,"area":null},{"id":"2303.05321","title":"WASD: A Wilder Active Speaker Detection Dataset","created":"2023-03-09","cited_by_count":6,"area":null}],"next_cursor":"100"}