{"list":"other","total":55,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"1512.04150","title":"Learning Deep Features for Discriminative Localization","created":"2015-12-14","cited_by_count":2436},{"id":"1809.07454","title":"Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation","created":"2018-09-20","cited_by_count":406},{"id":"2209.15352","title":"AudioGen: Textually Guided Audio Generation","created":"2022-09-30","cited_by_count":295},{"id":"1804.03160","title":"The Sound of Pixels","created":"2018-04-09","cited_by_count":259},{"id":"1908.08498","title":"EPIC-Fusion: Audio-Visual Temporal Binding for Egocentric Action Recognition","created":"2019-08-22","cited_by_count":226},{"id":"1803.03849","title":"Learning to Localize Sound Source in Visual Scenes","created":"2018-03-10","cited_by_count":189},{"id":"1904.05979","title":"The Sound of Motions","created":"2019-04-11","cited_by_count":146},{"id":"1904.04289","title":"SCSampler: Sampling Salient Clips from Video for Efficient Action Recognition","created":"2019-04-08","cited_by_count":134},{"id":"2007.06355","title":"Multiple Sound Sources Localization from Coarse to Fine","created":"2020-07-13","cited_by_count":118},{"id":"1711.00541","title":"TasNet: time-domain audio separation network for real-time, single-channel speech separation","created":"2017-11-01","cited_by_count":115},{"id":"1804.01665","title":"Learning to Separate Object Sounds by Watching Unlabeled Video","created":"2018-04-05","cited_by_count":114},{"id":"2101.03149","title":"VisualVoice: Audio-Visual Speech Separation with Cross-Modal Consistency","created":"2021-01-08","cited_by_count":114},{"id":"2004.09476","title":"Music Gesture for Visual Sound Separation","created":"2020-04-20","cited_by_count":112},{"id":"1904.07750","title":"Co-Separating Sounds of Visual Objects","created":"2019-04-16","cited_by_count":110},{"id":"1712.01393","title":"Visual to Sound: Generating Natural Sound for Videos in the Wild","created":"2017-12-04","cited_by_count":98},{"id":"1809.02587","title":"Self-Supervised Generation of Spatial Audio for 360 Video","created":"2018-09-07","cited_by_count":93},{"id":"2007.10984","title":"Foley Music: Learning to Generate Music from Videos","created":"2020-07-21","cited_by_count":83},{"id":"2001.04758","title":"Deep Audio-Visual Learning: A Survey","created":"2020-01-14","cited_by_count":69},{"id":"1712.07271","title":"Learning Sight from Sound: Ambient Sound Provides Supervision for Visual Learning","created":"2017-12-20","cited_by_count":67},{"id":"2204.00628","title":"Learning Neural Acoustic Fields","created":"2022-04-04","cited_by_count":65},{"id":"1812.04204","title":"2.5D Visual Sound","created":"2018-12-11","cited_by_count":63},{"id":"1910.11760","title":"Self-supervised Moving Vehicle Tracking with Stereo Sound","created":"2019-10-25","cited_by_count":63},{"id":"2008.05789","title":"Look, Listen, and Attend: Co-Attention Network for Self-Supervised Audio-Visual Representation Learning","created":"2020-08-13","cited_by_count":63},{"id":"1804.00326","title":"Seeing Voices and Hearing Faces: Cross-modal biometric matching","created":"2018-04-01","cited_by_count":60},{"id":"2104.02026","title":"Cyclic Co-Learning of Sounding Object Visual Grounding and Sound Separation","created":"2021-04-05","cited_by_count":59},{"id":"2007.09902","title":"Sep-Stereo: Visually Guided Stereophonic Audio Generation by Associating Source Separation","created":"2020-07-20","cited_by_count":55},{"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":"2302.02088","title":"AV-NeRF: Learning Neural Fields for Real-World Audio-Visual Scene Synthesis","created":"2023-02-04","cited_by_count":49},{"id":"2206.04006","title":"Few-Shot Audio-Visual Learning of Environment Acoustics","created":"2022-06-08","cited_by_count":48},{"id":"2104.06162","title":"Visually Informed Binaural Audio Generation without Binaural Audios","created":"2021-04-13","cited_by_count":46},{"id":"2105.07142","title":"Move2Hear: Active Audio-Visual Source Separation","created":"2021-05-15","cited_by_count":35},{"id":"2108.03256","title":"The Right to Talk: An Audio-Visual Transformer Approach","created":"2021-08-06","cited_by_count":33},{"id":"1711.08102","title":"CMCGAN: A Uniform Framework for Cross-Modal Visual-Audio Mutual Generation","created":"2017-11-22","cited_by_count":31},{"id":"2109.11955","title":"Visual Scene Graphs for Audio Source Separation","created":"2021-09-24","cited_by_count":29},{"id":"2212.03814","title":"iQuery: Instruments as Queries for Audio-Visual Sound Separation","created":"2022-12-07","cited_by_count":29},{"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},{"id":"1805.04792","title":"Scene-Aware Audio for 360\\textdegree{} Videos","created":"2018-05-12","cited_by_count":25},{"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},{"id":"2111.10882","title":"Geometry-Aware Multi-Task Learning for Binaural Audio Generation from Video","created":"2021-11-21","cited_by_count":22},{"id":"2104.08506","title":"Visually Guided Sound Source Separation and Localization using Self-Supervised Motion Representations","created":"2021-04-17","cited_by_count":18},{"id":"2111.08046","title":"Beyond Mono to Binaural: Generating Binaural Audio from Mono Audio with Depth and Cross Modal Attention","created":"2021-11-15","cited_by_count":17},{"id":"2202.00850","title":"Active Audio-Visual Separation of Dynamic Sound Sources","created":"2022-02-02","cited_by_count":16},{"id":"2006.03028","title":"Visually Guided Sound Source Separation using Cascaded Opponent Filter Network","created":"2020-06-04","cited_by_count":15},{"id":"2105.00708","title":"Exploiting Audio-Visual Consistency with Partial Supervision for Spatial Audio Generation","created":"2021-05-03","cited_by_count":14},{"id":"2203.04099","title":"VoViT: Low Latency Graph-based Audio-Visual Voice Separation Transformer","created":"2022-03-08","cited_by_count":14},{"id":"1905.06286","title":"End-to-End Multi-Channel Speech Separation","created":"2019-05-15","cited_by_count":11},{"id":"2210.16472","title":"Learning Audio-Visual Dynamics Using Scene Graphs for Audio Source Separation","created":"2022-10-29","cited_by_count":11},{"id":"2110.13412","title":"TriBERT: Full-body Human-centric Audio-visual Representation Learning for Visual Sound Separation","created":"2021-10-26","cited_by_count":6},{"id":"2108.01836","title":"Blind and neural network-guided convolutional beamformer for joint denoising, dereverberation, and source separation","created":"2021-08-04","cited_by_count":2},{"id":"1312.2795","title":"Reverberant Audio Source Separation via Sparse and Low-Rank Modeling","created":"2013-12-10","cited_by_count":1}],"next_cursor":null}