{"total":137,"rows":[{"id":"2307.10802","title":"Meta-Transformer: A Unified Framework for Multimodal Learning","created":"2023-07-20","cited_by_count":136,"area":null},{"id":"2210.10340","title":"The Devil in Linear Transformer","created":"2022-10-19","cited_by_count":98,"area":null},{"id":"2301.13190","title":"Audio-Visual Segmentation with Semantics","created":"2023-01-30","cited_by_count":75,"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":"2307.01146","title":"AVSegFormer: Audio-Visual Segmentation with Transformer","created":"2023-07-03","cited_by_count":68,"area":null},{"id":"2304.01008","title":"Self-Supervised Multimodal Learning: A Survey","created":"2023-03-31","cited_by_count":58,"area":null},{"id":"2305.16318","title":"Referred by Multi-Modality: A Unified Temporal Transformer for Video Object Segmentation","created":"2023-05-25","cited_by_count":54,"area":null},{"id":"2305.01836","title":"AV-SAM: Segment Anything Model Meets Audio-Visual Localization and Segmentation","created":"2023-05-03","cited_by_count":53,"area":null},{"id":"2309.09709","title":"CATR: Combinatorial-Dependence Audio-Queried Transformer for Audio-Visual Video Segmentation","created":"2023-09-18","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":"2302.02088","title":"AV-NeRF: Learning Neural Fields for Real-World Audio-Visual Scene Synthesis","created":"2023-02-04","cited_by_count":49,"area":null},{"id":"2302.00646","title":"Epic-Sounds: A Large-scale Dataset of Actions That Sound","created":"2023-02-01","cited_by_count":47,"area":null},{"id":"2303.11302","title":"Learning Audio-Visual Source Localization via False Negative Aware Contrastive Learning","created":"2023-03-20","cited_by_count":47,"area":null},{"id":"2305.11019","title":"Annotation-free Audio-Visual Segmentation","created":"2023-05-18","cited_by_count":46,"area":null},{"id":"2306.06211","title":"A Survey on Segment Anything Model (SAM): Vision Foundation Model Meets Prompt Engineering","created":"2023-05-12","cited_by_count":45,"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":"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":"2310.08303","title":"Multimodal Variational Auto-encoder based Audio-Visual Segmentation","created":"2023-10-12","cited_by_count":38,"area":null},{"id":"2308.08288","title":"Improving Audio-Visual Segmentation with Bidirectional Generation","created":"2023-08-16","cited_by_count":37,"area":null},{"id":"2309.07929","title":"Prompting Segmentation with Sound Is Generalizable Audio-Visual Source Localizer","created":"2023-09-13","cited_by_count":37,"area":null},{"id":"2512.10945","title":"MeViS: A Multi-Modal Dataset for Referring Motion Expression Video Segmentation","created":"2025-12-11","cited_by_count":35,"area":null},{"id":"2304.02970","title":"Unraveling Instance Associations: A Closer Look for Audio-Visual Segmentation","created":"2023-04-06","cited_by_count":34,"area":null},{"id":"2307.13236","title":"Audio-aware Query-enhanced Transformer for Audio-Visual Segmentation","created":"2023-07-25","cited_by_count":33,"area":null},{"id":"2407.10957","title":"Ref-AVS: Refer and Segment Objects in Audio-Visual Scenes","created":"2024-07-15","cited_by_count":33,"area":null},{"id":"2307.16620","title":"Audio-Visual Segmentation by Exploring Cross-Modal Mutual Semantics","created":"2023-07-31","cited_by_count":32,"area":null},{"id":"2308.10175","title":"BAVS: Bootstrapping Audio-Visual Segmentation by Integrating Foundation Knowledge","created":"2023-08-20","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":"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":"2309.09501","title":"Discovering Sounding Objects by Audio Queries for Audio Visual Segmentation","created":"2023-09-18","cited_by_count":29,"area":null},{"id":"2310.06238","title":"Tackling Data Bias in MUSIC-AVQA: Crafting a Balanced Dataset for Unbiased Question-Answering","created":"2023-10-10","cited_by_count":29,"area":null},{"id":"2403.07347","title":"Frequency Decoupling for Motion Magnification via Multi-Level Isomorphic Architecture","created":"2024-03-12","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":"2312.06462","title":"Cooperation Does Matter: Exploring Multi-Order Bilateral Relations for Audio-Visual Segmentation","created":"2023-12-11","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":"2407.08126","title":"Label-anticipated Event Disentanglement for Audio-Visual Video Parsing","created":"2024-07-11","cited_by_count":25,"area":null},{"id":"2312.01017","title":"Unveiling the Power of Audio-Visual Early Fusion Transformers with Dense Interactions through Masked Modeling","created":"2023-12-02","cited_by_count":24,"area":null},{"id":"2407.11820","title":"Stepping Stones: A Progressive Training Strategy for Audio-Visual Semantic Segmentation","created":"2024-07-16","cited_by_count":23,"area":null},{"id":"2508.00265","title":"Multimodal Referring Segmentation: A Survey","created":"2025-08-01","cited_by_count":22,"area":null},{"id":"2310.18709","title":"Audio-Visual Instance Segmentation","created":"2023-10-28","cited_by_count":21,"area":null},{"id":"2310.00132","title":"QDFormer: Towards Robust Audiovisual Segmentation in Complex Environments with Quantization-based Semantic Decomposition","created":"2023-09-29","cited_by_count":20,"area":null},{"id":"2406.00919","title":"Advancing Weakly-Supervised Audio-Visual Video Parsing via Segment-wise Pseudo Labeling","created":"2024-06-03","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":"2303.02344","title":"Improving Audio-Visual Video Parsing with Pseudo Visual Labels","created":"2023-03-04","cited_by_count":18,"area":null},{"id":"2303.15616","title":"Fine-grained Audible Video Description","created":"2023-03-27","cited_by_count":18,"area":null},{"id":"2505.11217","title":"Seeing Sound, Hearing Sight: Uncovering Modality Bias and Conflict of AI models in Sound Localization","created":"2025-05-16","cited_by_count":18,"area":null},{"id":"2506.01558","title":"SAM2-LOVE: Segment Anything Model 2 in Language-aided Audio-Visual Scenes","created":"2025-06-02","cited_by_count":17,"area":null},{"id":"2311.04066","title":"Can CLIP Help Sound Source Localization?","created":"2023-11-07","cited_by_count":14,"area":null},{"id":"2410.21170","title":"Joint Audio-Visual Idling Vehicle Detection with Streamlined Input Dependencies","created":"2024-10-28","cited_by_count":14,"area":null},{"id":"2407.10947","title":"Can Textual Semantics Mitigate Sounding Object Segmentation Preference?","created":"2024-07-15","cited_by_count":13,"area":null},{"id":"2407.05358","title":"CPM: Class-conditional Prompting Machine for Audio-visual Segmentation","created":"2024-07-07","cited_by_count":11,"area":null},{"id":"2504.02061","title":"Aligned Better, Listen Better for Audio-Visual Large Language Models","created":"2025-04-02","cited_by_count":10,"area":null},{"id":"2506.23271","title":"Mettle: Meta-Token Learning for Memory-Efficient Audio-Visual Adaptation","created":"2025-06-29","cited_by_count":10,"area":null},{"id":"2211.14419","title":"Panoramic Video Salient Object Detection with Ambisonic Audio Guidance","created":"2022-11-26","cited_by_count":9,"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":"2503.12847","title":"Robust Audio-Visual Segmentation via Audio-Guided Visual Convergent Alignment","created":"2025-03-17","cited_by_count":8,"area":null},{"id":"2305.19406","title":"PaintSeg: Training-free Segmentation via Painting","created":"2023-05-30","cited_by_count":7,"area":null},{"id":"2401.14405","title":"Multimodal Pathway: Improve Transformers with Irrelevant Data from Other Modalities","created":"2024-01-25","cited_by_count":7,"area":null},{"id":"2402.02327","title":"Bootstrapping Audio-Visual Segmentation by Strengthening Audio Cues","created":"2024-02-04","cited_by_count":7,"area":null},{"id":"2403.14203","title":"Unsupervised Audio-Visual Segmentation with Modality Alignment","created":"2024-03-21","cited_by_count":7,"area":null},{"id":"2511.17890","title":"Decoupled Audio-Visual Dataset Distillation","created":"2025-11-22","cited_by_count":7,"area":null},{"id":"2210.08164","title":"Linear Video Transformer with Feature Fixation","created":"2022-10-15","cited_by_count":6,"area":null},{"id":"2403.04924","title":"$\\text{R}^2$-Bench: Benchmarking the Robustness of Referring Perception Models under Perturbations","created":"2024-03-07","cited_by_count":6,"area":null},{"id":"2408.01708","title":"AVESFormer: Efficient Transformer Design for Real-Time Audio-Visual Segmentation","created":"2024-08-03","cited_by_count":6,"area":null},{"id":"2506.23623","title":"Revisiting Audio-Visual Segmentation with Vision-Centric Transformer","created":"2025-06-30","cited_by_count":6,"area":null},{"id":"2509.17537","title":"SimToken: A Simple Baseline for Referring Audio-Visual Segmentation","created":"2025-09-22","cited_by_count":6,"area":null},{"id":"2305.07223","title":"Transavs: End-To-End Audio-Visual Segmentation With Transformer","created":"2023-05-12","cited_by_count":5,"area":null},{"id":"2309.06728","title":"Leveraging Foundation models for Unsupervised Audio-Visual Segmentation","created":"2023-09-13","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":"2406.06163","title":"Extending Segment Anything Model into Auditory and Temporal Dimensions for Audio-Visual Segmentation","created":"2024-06-10","cited_by_count":5,"area":null},{"id":"2408.08315","title":"Segment Anything for Videos: A Systematic Survey","created":"2024-07-31","cited_by_count":5,"area":null},{"id":"2507.20740","title":"Implicit Counterfactual Learning for Audio-Visual Segmentation","created":"2025-07-28","cited_by_count":5,"area":null},{"id":"2510.10051","title":"Complementary and Contrastive Learning for Audio-Visual Segmentation","created":"2025-10-11","cited_by_count":5,"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":"2410.23230","title":"Aligning Audio-Visual Joint Representations with an Agentic Workflow","created":"2024-10-30","cited_by_count":4,"area":null},{"id":"2504.15118","title":"Improving Sound Source Localization with Joint Slot Attention on Image and Audio","created":"2025-04-21","cited_by_count":4,"area":null},{"id":"2507.04667","title":"What's Making That Sound Right Now? Video-centric Audio-Visual Localization","created":"2025-07-07","cited_by_count":4,"area":null},{"id":"2509.22740","title":"Learning What To Hear: Boosting Sound-Source Association For Robust Audiovisual Instance Segmentation","created":"2025-09-26","cited_by_count":4,"area":null},{"id":"2407.02264","title":"SOAF: Scene Occlusion-aware Neural Acoustic Field","created":"2024-07-02","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":"2508.03724","title":"From Waveforms to Pixels: A Survey on Audio-Visual Segmentation","created":"2025-07-29","cited_by_count":3,"area":null},{"id":"2512.20117","title":"Delayed Bidirectional Alignment via Disentangled Audio Semantics for Audio-Visual Segmentation","created":"2025-12-23","cited_by_count":3,"area":null},{"id":"2603.23906","title":"GenMask: Adapting DiT for Segmentation via Direct Mask Generation","created":"2026-03-25","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":"2211.11381","title":"LISA: Localized Image Stylization with Audio via Implicit Neural Representation","created":"2022-11-21","cited_by_count":2,"area":null},{"id":"2411.02236","title":"3D Audio-Visual Segmentation","created":"2024-11-04","cited_by_count":2,"area":null},{"id":"2505.09615","title":"UWAV: Uncertainty-weighted Weakly-supervised Audio-Visual Video Parsing","created":"2025-05-14","cited_by_count":2,"area":null},{"id":"2506.00358","title":"$\\texttt{AVROBUSTBENCH}$: Benchmarking the Robustness of Audio-Visual Recognition Models at Test-Time","created":"2025-05-31","cited_by_count":2,"area":null},{"id":"2506.01015","title":"AuralSAM2: Enabling SAM2 Hear Through Pyramid Audio-Visual Feature Prompting","created":"2025-06-01","cited_by_count":2,"area":null},{"id":"2509.26604","title":"Video Object Segmentation-Aware Audio Generation","created":"2025-09-30","cited_by_count":2,"area":null},{"id":"2512.00115","title":"MoLT: Mixture of Layer-Wise Tokens for Efficient Audio-Visual Learning","created":"2025-11-27","cited_by_count":2,"area":null},{"id":"2601.08133","title":"How Do Optical Flow and Textual Prompts Collaborate to Assist in Audio-Visual Semantic Segmentation?","created":"2026-01-13","cited_by_count":2,"area":null},{"id":"2602.03892","title":"Audit After Segmentation: Reference-Free Mask Quality Assessment for Language-Referred Audio-Visual Segmentation","created":"2026-02-03","cited_by_count":2,"area":null},{"id":"2304.05930","title":"MED-VT++: Unifying Multimodal Learning with a Multiscale Encoder-Decoder Video Transformer","created":"2023-04-12","cited_by_count":1,"area":null},{"id":"2310.08204","title":"STELLA: Continual Audio-Video Pre-training with Spatio-Temporal Localized Alignment","created":"2023-10-12","cited_by_count":1,"area":null},{"id":"2406.02345","title":"Progressive Confident Masking Attention Network for Audio-Visual Segmentation","created":"2024-06-04","cited_by_count":1,"area":null},{"id":"2412.01488","title":"TACO: Training-free Sound Prompted Segmentation via Semantically Constrained Audio-visual CO-factorization","created":"2024-12-02","cited_by_count":1,"area":null},{"id":"2502.16359","title":"Audio Visual Segmentation Through Text Embeddings","created":"2025-02-22","cited_by_count":1,"area":null},{"id":"2503.24270","title":"Visual Acoustic Fields","created":"2025-03-31","cited_by_count":1,"area":null}],"next_cursor":"100"}