{"list":"other","total":52,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1611.01144","title":"Categorical Reparameterization with Gumbel-Softmax","created":"2016-11-03","cited_by_count":2739},{"id":"1611.00712","title":"The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables","created":"2016-11-02","cited_by_count":1148},{"id":"1711.10925","title":"Deep Image Prior","created":"2017-11-29","cited_by_count":1098},{"id":"2004.14368","title":"VGGSound: A Large-scale Audio-Visual Dataset","created":"2020-04-29","cited_by_count":648},{"id":"2202.11094","title":"GroupViT: Semantic Segmentation Emerges from Text Supervision","created":"2022-02-22","cited_by_count":531},{"id":"1705.08168","title":"Look, Listen and Learn","created":"2017-05-23","cited_by_count":458},{"id":"1811.02508","title":"SDR - half-baked or well done?","created":"2018-11-06","cited_by_count":423},{"id":"1804.03160","title":"The Sound of Pixels","created":"2018-04-09","cited_by_count":259},{"id":"1807.00230","title":"Cooperative Learning of Audio and Video Models from Self-Supervised Synchronization","created":"2018-06-30","cited_by_count":249},{"id":"1610.09001","title":"SoundNet: Learning Sound Representations from Unlabeled Video","created":"2016-10-27","cited_by_count":247},{"id":"1508.04306","title":"Deep clustering: Discriminative embeddings for segmentation and separation","created":"2015-08-18","cited_by_count":212},{"id":"2004.12943","title":"Audio-Visual Instance Discrimination with Cross-Modal Agreement","created":"2020-04-27","cited_by_count":195},{"id":"1803.03849","title":"Learning to Localize Sound Source in Visual Scenes","created":"2018-03-10","cited_by_count":189},{"id":"2008.04237","title":"Self-Supervised Learning of Audio-Visual Objects from Video","created":"2020-08-10","cited_by_count":188},{"id":"2104.02691","title":"Localizing Visual Sounds the Hard Way","created":"2021-04-06","cited_by_count":170},{"id":"1804.03619","title":"Looking to Listen at the Cocktail Party: A Speaker-Independent Audio-Visual Model for Speech Separation","created":"2018-04-10","cited_by_count":162},{"id":"1904.05979","title":"The Sound of Motions","created":"2019-04-11","cited_by_count":146},{"id":"2007.10558","title":"Unified Multisensory Perception: Weakly-Supervised Audio-Visual Video Parsing","created":"2020-07-21","cited_by_count":146},{"id":"1806.03185","title":"Wave-U-Net: A Multi-Scale Neural Network for End-to-End Audio Source Separation","created":"2018-06-08","cited_by_count":125},{"id":"2007.06355","title":"Multiple Sound Sources Localization from Coarse to Fine","created":"2020-07-13","cited_by_count":118},{"id":"1804.01665","title":"Learning to Separate Object Sounds by Watching Unlabeled Video","created":"2018-04-05","cited_by_count":114},{"id":"2004.09476","title":"Music Gesture for Visual Sound Separation","created":"2020-04-20","cited_by_count":112},{"id":"2011.01819","title":"Learning Representations from Audio-Visual Spatial Alignment","created":"2020-11-03","cited_by_count":95},{"id":"1809.02587","title":"Self-Supervised Generation of Spatial Audio for 360 Video","created":"2018-09-07","cited_by_count":93},{"id":"2203.09324","title":"Localizing Visual Sounds the Easy Way","created":"2022-03-17","cited_by_count":82},{"id":"2103.15916","title":"Robust Audio-Visual Instance Discrimination","created":"2021-03-29","cited_by_count":80},{"id":"2209.09634","title":"A Closer Look at Weakly-Supervised Audio-Visual Source Localization","created":"2022-08-30","cited_by_count":73},{"id":"1902.07473","title":"Dual-modality seq2seq network for audio-visual event localization","created":"2019-02-20","cited_by_count":72},{"id":"1712.07271","title":"Learning Sight from Sound: Ambient Sound Provides Supervision for Visual Learning","created":"2017-12-20","cited_by_count":67},{"id":"1812.04204","title":"2.5D Visual Sound","created":"2018-12-11","cited_by_count":63},{"id":"2104.02026","title":"Cyclic Co-Learning of Sounding Object Visual Grounding and Sound Separation","created":"2021-04-05","cited_by_count":59},{"id":"2011.01143","title":"Into the Wild with AudioScope: Unsupervised Audio-Visual Separation of On-Screen Sounds","created":"2020-11-02","cited_by_count":55},{"id":"1908.11602","title":"Recursive Visual Sound Separation Using Minus-Plus Net","created":"2019-08-30","cited_by_count":53},{"id":"2305.01836","title":"AV-SAM: Segment Anything Model Meets Audio-Visual Localization and Segmentation","created":"2023-05-03","cited_by_count":53},{"id":"2109.05418","title":"Decoupling Magnitude and Phase Estimation with Deep ResUNet for Music Source Separation","created":"2021-09-12","cited_by_count":48},{"id":"2308.11073","title":"Audio-Visual Class-Incremental Learning","created":"2023-08-21","cited_by_count":33},{"id":"2109.11955","title":"Visual Scene Graphs for Audio Source Separation","created":"2021-09-24","cited_by_count":29},{"id":"2403.07938","title":"Text-to-Audio Generation Synchronized with Videos","created":"2024-03-08","cited_by_count":28},{"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},{"id":"2011.00803","title":"What's All the FUSS About Free Universal Sound Separation Data?","created":"2020-11-02","cited_by_count":22},{"id":"2309.05281","title":"Class-Incremental Grouping Network for Continual Audio-Visual Learning","created":"2023-09-11","cited_by_count":22},{"id":"2305.19458","title":"A Unified Audio-Visual Learning Framework for Localization, Separation, and Recognition","created":"2023-05-30","cited_by_count":21},{"id":"2305.12903","title":"DiffAVA: Personalized Text-to-Audio Generation with Visual Alignment","created":"2023-05-22","cited_by_count":19},{"id":"2311.15080","title":"Weakly-Supervised Audio-Visual Segmentation","created":"2023-11-25","cited_by_count":19},{"id":"1911.07951","title":"Improving Universal Sound Separation Using Sound Classification","created":"2019-11-18","cited_by_count":17},{"id":"1911.02182","title":"Finding Strength in Weakness: Learning to Separate Sounds with Weak Supervision","created":"2019-11-06","cited_by_count":13},{"id":"1804.09288","title":"A Closer Look at Weak Label Learning for Audio Events","created":"2018-04-24","cited_by_count":12},{"id":"1811.03076","title":"Class-conditional embeddings for music source separation","created":"2018-11-07","cited_by_count":12},{"id":"2207.00562","title":"Distance-Based Sound Separation","created":"2022-07-01","cited_by_count":8},{"id":"1611.04871","title":"Audio Event and Scene Recognition: A Unified Approach using Strongly and Weakly Labeled Data","created":"2016-11-12","cited_by_count":3}],"next_cursor":null}