{"list":"other","total":78,"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":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1502.01852","title":"Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification","created":"2015-02-06","cited_by_count":3611},{"id":"1911.11763","title":"SuperGlue: Learning Feature Matching with Graph Neural Networks","created":"2019-11-26","cited_by_count":1443},{"id":"2104.00680","title":"LoFTR: Detector-Free Local Feature Matching with Transformers","created":"2021-04-01","cited_by_count":984},{"id":"1704.07813","title":"Unsupervised Learning of Depth and Ego-Motion from Video","created":"2017-04-25","cited_by_count":782},{"id":"2109.08238","title":"Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AI","created":"2021-09-16","cited_by_count":592},{"id":"2103.15875","title":"In-Place Scene Labelling and Understanding with Implicit Scene Representation","created":"2021-03-29","cited_by_count":415},{"id":"1702.01105","title":"Joint 2D-3D-Semantic Data for Indoor Scene Understanding","created":"2017-02-03","cited_by_count":406},{"id":"1804.03641","title":"Audio-Visual Scene Analysis with Self-Supervised Multisensory Features","created":"2018-04-10","cited_by_count":335},{"id":"2301.12661","title":"Make-An-Audio: Text-To-Audio Generation with Prompt-Enhanced Diffusion Models","created":"2023-01-30","cited_by_count":324},{"id":"2209.15352","title":"AudioGen: Textually Guided Audio Generation","created":"2022-09-30","cited_by_count":295},{"id":"2207.09983","title":"Diffsound: Discrete Diffusion Model for Text-to-sound Generation","created":"2022-07-20","cited_by_count":257},{"id":"1612.01840","title":"FMA: A Dataset For Music Analysis","created":"2016-12-06","cited_by_count":207},{"id":"2004.12943","title":"Audio-Visual Instance Discrimination with Cross-Modal Agreement","created":"2020-04-27","cited_by_count":195},{"id":"1607.00325","title":"Permutation Invariant Training of Deep Models for Speaker-Independent Multi-talker Speech Separation","created":"2016-07-01","cited_by_count":191},{"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":"2001.08740","title":"Audiovisual SlowFast Networks for Video Recognition","created":"2020-01-23","cited_by_count":146},{"id":"2110.08791","title":"Taming Visually Guided Sound Generation","created":"2021-10-17","cited_by_count":136},{"id":"2201.07131","title":"Leveraging Real Talking Faces via Self-Supervision for Robust Forgery Detection","created":"2022-01-18","cited_by_count":130},{"id":"1512.08512","title":"Visually Indicated Sounds","created":"2015-12-28","cited_by_count":128},{"id":"2206.13597","title":"NeuRIS: Neural Reconstruction of Indoor Scenes Using Normal Priors","created":"2022-06-27","cited_by_count":125},{"id":"2101.03149","title":"VisualVoice: Audio-Visual Speech Separation with Cross-Modal Consistency","created":"2021-01-08","cited_by_count":114},{"id":"2107.06592","title":"Is Someone Speaking? Exploring Long-term Temporal Features for Audio-visual Active Speaker Detection","created":"2021-07-14","cited_by_count":113},{"id":"2006.13662","title":"Labelling unlabelled videos from scratch with multi-modal self-supervision","created":"2020-06-24","cited_by_count":100},{"id":"2011.01819","title":"Learning Representations from Audio-Visual Spatial Alignment","created":"2020-11-03","cited_by_count":95},{"id":"2206.08312","title":"SoundSpaces 2.0: A Simulation Platform for Visual-Acoustic Learning","created":"2022-06-16","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":"2301.01767","title":"Self-Supervised Video Forensics by Audio-Visual Anomaly Detection","created":"2023-01-04","cited_by_count":85},{"id":"2007.10984","title":"Foley Music: Learning to Generate Music from Videos","created":"2020-07-21","cited_by_count":83},{"id":"2012.11583","title":"Semantic Audio-Visual Navigation","created":"2020-12-21","cited_by_count":82},{"id":"2203.09324","title":"Localizing Visual Sounds the Easy Way","created":"2022-03-17","cited_by_count":82},{"id":"2212.03239","title":"Perspective Fields for Single Image Camera Calibration","created":"2022-12-06","cited_by_count":75},{"id":"2209.09634","title":"A Closer Look at Weakly-Supervised Audio-Visual Source Localization","created":"2022-08-30","cited_by_count":73},{"id":"2005.01616","title":"VisualEchoes: Spatial Image Representation Learning through Echolocation","created":"2020-05-04","cited_by_count":55},{"id":"2007.09902","title":"Sep-Stereo: Visually Guided Stereophonic Audio Generation by Associating Source Separation","created":"2020-07-20","cited_by_count":55},{"id":"2211.15058","title":"Mix and Localize: Localizing Sound Sources in Mixtures","created":"2022-11-28","cited_by_count":54},{"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":"1702.01381","title":"Relative Camera Pose Estimation Using Convolutional Neural Networks","created":"2017-02-05","cited_by_count":47},{"id":"2104.06162","title":"Visually Informed Binaural Audio Generation without Binaural Audios","created":"2021-04-13","cited_by_count":46},{"id":"2202.06875","title":"Visual Acoustic Matching","created":"2022-02-14","cited_by_count":45},{"id":"2102.11870","title":"UnsupervisedR&R: Unsupervised Point Cloud Registration via Differentiable Rendering","created":"2021-02-23","cited_by_count":44},{"id":"2006.06175","title":"Telling Left from Right: Learning Spatial Correspondence of Sight and Sound","created":"2020-06-11","cited_by_count":43},{"id":"2104.13530","title":"Extreme Rotation Estimation using Dense Correlation Volumes","created":"2021-04-28","cited_by_count":42},{"id":"2103.14644","title":"Planar Surface Reconstruction from Sparse Views","created":"2021-03-26","cited_by_count":40},{"id":"2007.10983","title":"Learning Monocular Visual Odometry via Self-Supervised Long-Term Modeling","created":"2020-07-21","cited_by_count":39},{"id":"2101.03682","title":"MAAS: Multi-modal Assignation for Active Speaker Detection","created":"2021-01-11","cited_by_count":36},{"id":"1612.07429","title":"Physically-Based Rendering for Indoor Scene Understanding Using Convolutional Neural Networks","created":"2016-12-22","cited_by_count":35},{"id":"2105.07142","title":"Move2Hear: Active Audio-Visual Source Separation","created":"2021-05-15","cited_by_count":35},{"id":"2103.14201","title":"Image2Reverb: Cross-Modal Reverb Impulse Response Synthesis","created":"2021-03-26","cited_by_count":34},{"id":"2301.08730","title":"Novel-View Acoustic Synthesis","created":"2023-01-20","cited_by_count":33},{"id":"2012.15470","title":"Audio-Visual Floorplan Reconstruction","created":"2020-12-31","cited_by_count":32},{"id":"2104.06401","title":"Self-supervised object detection from audio-visual correspondence","created":"2021-04-13","cited_by_count":29},{"id":"1710.10059","title":"Direction of arrival estimation for multiple sound sources using convolutional recurrent neural network","created":"2017-10-27","cited_by_count":27},{"id":"2106.00677","title":"Bootstrap Your Own Correspondences","created":"2021-06-01","cited_by_count":27},{"id":"2206.08365","title":"Virtual Correspondence: Humans as a Cue for Extreme-View Geometry","created":"2022-06-16","cited_by_count":25},{"id":"2103.08468","title":"Beyond Image to Depth: Improving Depth Prediction using Echoes","created":"2021-03-15","cited_by_count":24},{"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":"2204.13696","title":"NeurMiPs: Neural Mixture of Planar Experts for View Synthesis","created":"2022-04-28","cited_by_count":23},{"id":"2209.13583","title":"Learning State-Aware Visual Representations from Audible Interactions","created":"2022-09-27","cited_by_count":23},{"id":"1901.00063","title":"Extreme Relative Pose Estimation for RGB-D Scans via Scene Completion","created":"2018-12-31","cited_by_count":22},{"id":"2111.10882","title":"Geometry-Aware Multi-Task Learning for Binaural Audio Generation from Video","created":"2021-11-21","cited_by_count":22},{"id":"1912.11695","title":"Extreme Relative Pose Network under Hybrid Representations","created":"2019-12-25","cited_by_count":19},{"id":"2002.10981","title":"AutoFoley: Artificial Synthesis of Synchronized Sound Tracks for Silent Videos with Deep Learning","created":"2020-02-21","cited_by_count":19},{"id":"2007.13727","title":"Associative3D: Volumetric Reconstruction from Sparse Views","created":"2020-07-27","cited_by_count":18},{"id":"2204.12489","title":"Sound Localization by Self-Supervised Time Delay Estimation","created":"2022-04-26","cited_by_count":18},{"id":"2111.05846","title":"Structure from Silence: Learning Scene Structure from Ambient Sound","created":"2021-11-10","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":"2105.00708","title":"Exploiting Audio-Visual Consistency with Partial Supervision for Spatial Audio Generation","created":"2021-05-03","cited_by_count":14},{"id":"1904.01916","title":"End-to-end Binaural Sound Localisation from the Raw Waveform","created":"2019-04-03","cited_by_count":6},{"id":"2006.07995","title":"BatVision with GCC-PHAT Features for Better Sound to Vision Predictions","created":"2020-06-14","cited_by_count":5},{"id":"2112.01520","title":"Recognizing Scenes from Novel Viewpoints","created":"2021-12-02","cited_by_count":5},{"id":"2207.03697","title":"End-to-End Binaural Speech Synthesis","created":"2022-07-08","cited_by_count":4}],"next_cursor":null}