{"total":98,"rows":[{"id":"2207.09983","title":"Diffsound: Discrete Diffusion Model for Text-to-sound Generation","created":"2022-07-20","cited_by_count":257,"area":"diffusion"},{"id":"2212.09478","title":"MM-Diffusion: Learning Multi-Modal Diffusion Models for Joint Audio and Video Generation","created":"2022-12-19","cited_by_count":227,"area":"diffusion"},{"id":"2407.00634","title":"Tarsier: Recipes for Training and Evaluating Large Video Description Models","created":"2024-06-30","cited_by_count":141,"area":null},{"id":"2110.08791","title":"Taming Visually Guided Sound Generation","created":"2021-10-17","cited_by_count":136,"area":null},{"id":"2306.17203","title":"Diff-Foley: Synchronized Video-to-Audio Synthesis with Latent Diffusion Models","created":"2023-06-29","cited_by_count":134,"area":"diffusion"},{"id":"2101.03149","title":"VisualVoice: Audio-Visual Speech Separation with Cross-Modal Consistency","created":"2021-01-08","cited_by_count":114,"area":null},{"id":"2407.01494","title":"FoleyCrafter: Bring Silent Videos to Life with Lifelike and Synchronized Sounds","created":"2024-07-01","cited_by_count":110,"area":null},{"id":"2112.04446","title":"Everything at Once -- Multi-modal Fusion Transformer for Video Retrieval","created":"2021-12-08","cited_by_count":79,"area":null},{"id":"2308.09300","title":"V2A-Mapper: A Lightweight Solution for Vision-to-Audio Generation by Connecting Foundation Models","created":"2023-08-18","cited_by_count":65,"area":null},{"id":"2111.00418","title":"Deep Learning in Human Activity Recognition with Wearable Sensors: A Review on Advances","created":"2021-10-31","cited_by_count":54,"area":null},{"id":"2304.08490","title":"Conditional Generation of Audio from Video via Foley Analogies","created":"2023-04-17","cited_by_count":52,"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":"2210.12649","title":"Anticipative Feature Fusion Transformer for Multi-Modal Action Anticipation","created":"2022-10-23","cited_by_count":41,"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":"2506.19774","title":"Kling-Foley: Multimodal Diffusion Transformer for High-Quality Video-to-Audio Generation","created":"2025-06-24","cited_by_count":40,"area":"diffusion"},{"id":"2305.14381","title":"Connecting Multi-modal Contrastive Representations","created":"2023-05-22","cited_by_count":36,"area":null},{"id":"2411.05679","title":"Tell What You Hear From What You See -- Video to Audio Generation Through Text","created":"2024-11-08","cited_by_count":34,"area":null},{"id":"2109.11955","title":"Visual Scene Graphs for Audio Source Separation","created":"2021-09-24","cited_by_count":29,"area":null},{"id":"2202.09195","title":"A Review on Methods and Applications in Multimodal Deep Learning","created":"2022-02-18","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":"2403.07938","title":"Text-to-Audio Generation Synchronized with Videos","created":"2024-03-08","cited_by_count":28,"area":"diffusion"},{"id":"2407.10387","title":"Masked Generative Video-to-Audio Transformers with Enhanced Synchronicity","created":"2024-07-15","cited_by_count":28,"area":null},{"id":"2104.13332","title":"End-to-End Video-To-Speech Synthesis using Generative Adversarial Networks","created":"2021-04-27","cited_by_count":27,"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":"2409.19132","title":"From Vision to Audio and Beyond: A Unified Model for Audio-Visual Representation and Generation","created":"2024-09-27","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":"2205.05072","title":"Learning Visual Styles from Audio-Visual Associations","created":"2022-05-10","cited_by_count":22,"area":null},{"id":"2210.02884","title":"Vision+X: A Survey on Multimodal Learning in the Light of Data","created":"2022-10-05","cited_by_count":22,"area":null},{"id":"2303.16897","title":"Physics-Driven Diffusion Models for Impact Sound Synthesis from Videos","created":"2023-03-29","cited_by_count":22,"area":"diffusion"},{"id":"2107.09262","title":"FoleyGAN: Visually Guided Generative Adversarial Network-Based Synchronous Sound Generation in Silent Videos","created":"2021-07-20","cited_by_count":20,"area":null},{"id":"2305.06594","title":"V2Meow: Meowing to the Visual Beat via Video-to-Music Generation","created":"2023-05-11","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":"2412.10768","title":"VinTAGe: Joint Video and Text Conditioning for Holistic Audio Generation","created":"2024-12-14","cited_by_count":16,"area":null},{"id":"2409.07450","title":"VMAS: Video-to-Music Generation via Semantic Alignment in Web Music Videos","created":"2024-09-11","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":"2308.13077","title":"Preserving Modality Structure Improves Multi-Modal Learning","created":"2023-08-24","cited_by_count":13,"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":"2211.10666","title":"VarietySound: Timbre-Controllable Video to Sound Generation via Unsupervised Information Disentanglement","created":"2022-11-19","cited_by_count":11,"area":null},{"id":"2506.12199","title":"ViSAGe: Video-to-Spatial Audio Generation","created":"2025-06-13","cited_by_count":11,"area":null},{"id":"2201.05771","title":"KazakhTTS2: Extending the Open-Source Kazakh TTS Corpus With More Data, Speakers, and Topics","created":"2022-01-15","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":"2410.03335","title":"Audio-Agent: Leveraging LLMs For Audio Generation, Editing and Composition","created":"2024-10-04","cited_by_count":9,"area":"agents"},{"id":"2207.10760","title":"A Proposal for Foley Sound Synthesis Challenge","created":"2022-07-21","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":"2409.14340","title":"Self-Supervised Audio-Visual Soundscape Stylization","created":"2024-09-22","cited_by_count":8,"area":null},{"id":"2503.10719","title":"Long-Video Audio Synthesis with Multi-Agent Collaboration","created":"2025-03-13","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":"2409.06135","title":"Draw an Audio: Leveraging Multi-Instruction for Video-to-Audio Synthesis","created":"2024-09-10","cited_by_count":7,"area":null},{"id":"2104.02656","title":"Collaborative Learning to Generate Audio-Video Jointly","created":"2021-04-01","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":"2309.15494","title":"VideoAdviser: Video Knowledge Distillation for Multimodal Transfer Learning","created":"2023-09-27","cited_by_count":6,"area":"distill"},{"id":"2201.01046","title":"Sound and Visual Representation Learning with Multiple Pretraining Tasks","created":"2022-01-04","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":"2412.15023","title":"FolAI: Synchronized Foley Sound Generation with Semantic and Temporal Alignment","created":"2024-12-19","cited_by_count":5,"area":null},{"id":"2508.08524","title":"StreetReaderAI: Making Street View Accessible Using Context-Aware Multimodal AI","created":"2025-08-11","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":"2307.04292","title":"A Demand-Driven Perspective on Generative Audio AI","created":"2023-07-10","cited_by_count":4,"area":null},{"id":"2310.13451","title":"Two-Stage Triplet Loss Training with Curriculum Augmentation for Audio-Visual Retrieval","created":"2023-10-20","cited_by_count":4,"area":null},{"id":"2404.13789","title":"Anchor-aware Deep Metric Learning for Audio-visual Retrieval","created":"2024-04-21","cited_by_count":4,"area":null},{"id":"2502.12489","title":"A Comprehensive Survey on Generative AI for Video-to-Music Generation","created":"2025-02-18","cited_by_count":4,"area":null},{"id":"2105.08052","title":"The Boombox: Visual Reconstruction from Acoustic Vibrations","created":"2021-05-17","cited_by_count":3,"area":null},{"id":"2405.16136","title":"C3LLM: Conditional Multimodal Content Generation Using Large Language Models","created":"2024-05-25","cited_by_count":3,"area":null},{"id":"2501.09608","title":"Metric Learning with Progressive Self-Distillation for Audio-Visual Embedding Learning","created":"2025-01-16","cited_by_count":3,"area":"distill"},{"id":"2506.04214","title":"Sounding that Object: Interactive Object-Aware Image to Audio Generation","created":"2025-06-04","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":"2104.09760","title":"HCMS: Hierarchical and Conditional Modality Selection for Efficient Video Recognition","created":"2021-04-20","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":"2506.09989","title":"Hearing Hands: Generating Sounds from Physical Interactions in 3D Scenes","created":"2025-06-11","cited_by_count":2,"area":null},{"id":"2603.11042","title":"V2M-Zero: Zero-Pair Time-Aligned Video-to-Music Generation","created":"2026-03-11","cited_by_count":2,"area":null},{"id":"2605.30339","title":"Benchmarking Single-Factor Physical Video-to-Audio Generation","created":"2026-05-28","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":"2303.04585","title":"Exploring Efficient-Tuned Learning Audio Representation Method from BriVL","created":"2023-03-08","cited_by_count":1,"area":null},{"id":"2307.15898","title":"UniBriVL: Robust Universal Representation and Generation of Audio Driven Diffusion Models","created":"2023-07-29","cited_by_count":1,"area":"diffusion"},{"id":"2308.09685","title":"Audiovisual Moments in Time: A Large-Scale Annotated Dataset of Audiovisual Actions","created":"2023-08-18","cited_by_count":1,"area":null},{"id":"2309.13607","title":"MM-NeRF: Multimodal-Guided 3D Multi-Style Transfer of Neural Radiance Field","created":"2023-09-24","cited_by_count":1,"area":null},{"id":"2310.18320","title":"AI (r)evolution -- where are we heading? Thoughts about the future of music and sound technologies in the era of deep learning","created":"2023-09-20","cited_by_count":1,"area":null},{"id":"2311.07630","title":"Cross-modal Generative Model for Visual-Guided Binaural Stereo Generation","created":"2023-11-13","cited_by_count":1,"area":null},{"id":"2411.15447","title":"Gotta Hear Them All: Towards Sound Source Aware Audio Generation","created":"2024-11-23","cited_by_count":1,"area":null},{"id":"2503.24270","title":"Visual Acoustic Fields","created":"2025-03-31","cited_by_count":1,"area":null},{"id":"2601.11995","title":"Learning Audio-Visual Embeddings with Inferred Latent Interaction Graphs","created":"2026-01-17","cited_by_count":1,"area":null},{"id":"2601.14594","title":"LFS: Learnable Frame Selector for Event-Aware and Temporally Diverse Video Captioning","created":"2026-01-21","cited_by_count":1,"area":null},{"id":"2604.04348","title":"OmniSonic: Towards Universal and Holistic Audio Generation from Video and Text","created":"2026-04-06","cited_by_count":1,"area":"moe"},{"id":"2604.10542","title":"VidAudio-Bench: Benchmarking V2A and VT2A Generation across Four Audio Categories","created":"2026-04-12","cited_by_count":1,"area":null},{"id":"2108.11773","title":"Multi-Modulation Network for Audio-Visual Event Localization","created":"2021-08-26","cited_by_count":0,"area":null},{"id":"2110.02404","title":"3D-MOV: Audio-Visual LSTM Autoencoder for 3D Reconstruction of Multiple Objects from Video","created":"2021-10-05","cited_by_count":0,"area":null},{"id":"2308.12408","title":"An Initial Exploration: Learning to Generate Realistic Audio for Silent Video","created":"2023-08-23","cited_by_count":0,"area":null},{"id":"2406.00901","title":"Robust Multi-Modal Speech In-Painting: A Sequence-to-Sequence Approach","created":"2024-06-02","cited_by_count":0,"area":null},{"id":"2505.12734","title":"SounDiT: Geo-Contextual Soundscape-to-Landscape Generation","created":"2025-05-19","cited_by_count":0,"area":null},{"id":"2510.05829","title":"FoleyGRAM: Video-to-Audio Generation with GRAM-Aligned Multimodal Encoders","created":"2025-10-07","cited_by_count":0,"area":null},{"id":"2510.11738","title":"SeeingSounds: Learning Audio-to-Visual Alignment via Text","created":"2025-10-10","cited_by_count":0,"area":null},{"id":"2601.17123","title":"Acoustic Field Video for Multimodal Scene Understanding","created":"2026-01-23","cited_by_count":0,"area":"mllm"},{"id":"2603.10623","title":"Geo-ATBench: A Benchmark for Geospatial Audio Tagging with Geospatial Semantic Context","created":"2026-03-11","cited_by_count":0,"area":null},{"id":"2606.29473","title":"MAVIN: Multi-Shot Audio-Visual Generation with Customized Narrative Control","created":"2026-06-28","cited_by_count":0,"area":null},{"id":"2607.28129","title":"Face and Voice Cross-modal Association with Learning Convex Feature Embedding","created":"2026-07-30","cited_by_count":0,"area":null},{"id":"2608.03742","title":"AI-Based Sound Effect Generation: A Narrative Review of Generative Models Across Input Modalities","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2609.34381","title":"Joint and Cross-Modal Video-Audio Generation and Editing: A Unified Formulation and Design Taxonomy","created":"2026-09-28","cited_by_count":0,"area":null}],"next_cursor":null}