{"total":25,"rows":[{"id":"2107.00135","title":"Attention Bottlenecks for Multimodal Fusion","created":"2021-06-30","cited_by_count":361,"area":null},{"id":"2412.04431","title":"Infinity: Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis","created":"2024-12-05","cited_by_count":304,"area":null},{"id":"2406.07548","title":"Image and Video Tokenization with Binary Spherical Quantization","created":"2024-06-11","cited_by_count":112,"area":null},{"id":"2103.16559","title":"Broaden Your Views for Self-Supervised Video Learning","created":"2021-03-30","cited_by_count":108,"area":null},{"id":"2203.01205","title":"Audio Self-supervised Learning: A Survey","created":"2022-03-02","cited_by_count":65,"area":null},{"id":"2103.06508","title":"Multi-Format Contrastive Learning of Audio Representations","created":"2021-03-11","cited_by_count":39,"area":null},{"id":"2110.04621","title":"Universal Paralinguistic Speech Representations Using Self-Supervised Conformers","created":"2021-10-09","cited_by_count":32,"area":null},{"id":"2207.10141","title":"AudioScopeV2: Audio-Visual Attention Architectures for Calibrated Open-Domain On-Screen Sound Separation","created":"2022-07-20","cited_by_count":24,"area":null},{"id":"2110.07313","title":"Conformer-Based Self-Supervised Learning for Non-Speech Audio Tasks","created":"2021-10-14","cited_by_count":22,"area":null},{"id":"2303.16024","title":"Egocentric Auditory Attention Localization in Conversations","created":"2023-03-28","cited_by_count":18,"area":null},{"id":"2205.06907","title":"Multimodal Conversational AI: A Survey of Datasets and Approaches","created":"2022-05-13","cited_by_count":16,"area":null},{"id":"2508.05599","title":"WeTok: Powerful Discrete Tokenization for High-Fidelity Visual Reconstruction","created":"2025-08-07","cited_by_count":9,"area":null},{"id":"2105.02132","title":"Self-Supervised Learning from Automatically Separated Sound Scenes","created":"2021-05-05","cited_by_count":6,"area":null},{"id":"2512.14697","title":"Spherical Leech Quantization for Visual Tokenization and Generation","created":"2025-12-16","cited_by_count":6,"area":null},{"id":"2106.09669","title":"Improving On-Screen Sound Separation for Open-Domain Videos with Audio-Visual Self-Attention","created":"2021-06-17","cited_by_count":5,"area":null},{"id":"2602.14041","title":"BitDance: Scaling Autoregressive Generative Models with Binary Tokens","created":"2026-02-15","cited_by_count":4,"area":null},{"id":"2304.14912","title":"Human Activity Recognition Using Self-Supervised Representations of Wearable Data","created":"2023-04-26","cited_by_count":2,"area":null},{"id":"2412.00049","title":"A Survey of Recent Advances and Challenges in Deep Audio-Visual Correlation Learning","created":"2024-11-24","cited_by_count":2,"area":null},{"id":"2603.16373","title":"Semantic One-Dimensional Tokenizer for Image Reconstruction and Generation","created":"2026-03-17","cited_by_count":2,"area":null},{"id":"2105.10536","title":"Semi-Supervised Audio Representation Learning for Modeling Beehive Strengths","created":"2021-05-21","cited_by_count":1,"area":null},{"id":"2112.12272","title":"Human Activity Recognition on wrist-worn accelerometers using self-supervised neural networks","created":"2021-12-22","cited_by_count":1,"area":null},{"id":"2203.10425","title":"A Study on Robustness to Perturbations for Representations of Environmental Sound","created":"2022-03-20","cited_by_count":1,"area":null},{"id":"2410.24075","title":"Identifying Spatio-Temporal Drivers of Extreme Events","created":"2024-10-31","cited_by_count":1,"area":null},{"id":"2112.09348","title":"Expedition: A System for the Unsupervised Learning of a Hierarchy of Concepts","created":"2021-12-17","cited_by_count":0,"area":null},{"id":"2202.13673","title":"Recent Advances and Challenges in Deep Audio-Visual Correlation Learning","created":"2022-02-28","cited_by_count":0,"area":null}],"next_cursor":null}