{"list":"other","total":60,"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":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"2106.07447","title":"HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units","created":"2021-06-14","cited_by_count":2342},{"id":"2005.08100","title":"Conformer: Convolution-augmented Transformer for Speech Recognition","created":"2020-05-16","cited_by_count":1863},{"id":"1709.06158","title":"Matterport3D: Learning from RGB-D Data in Indoor Environments","created":"2017-09-18","cited_by_count":1376},{"id":"2010.05646","title":"HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis","created":"2020-10-12","cited_by_count":1154},{"id":"2008.10010","title":"A Lip Sync Expert Is All You Need for Speech to Lip Generation In The Wild","created":"2020-08-23","cited_by_count":672},{"id":"1510.08484","title":"MUSAN: A Music, Speech, and Noise Corpus","created":"2015-10-28","cited_by_count":425},{"id":"2106.04624","title":"SpeechBrain: A General-Purpose Speech Toolkit","created":"2021-06-08","cited_by_count":406},{"id":"2103.11078","title":"AD-NeRF: Audio Driven Neural Radiance Fields for Talking Head Synthesis","created":"2021-03-20","cited_by_count":339},{"id":"1804.03641","title":"Audio-Visual Scene Analysis with Self-Supervised Multisensory Features","created":"2018-04-10","cited_by_count":335},{"id":"2107.04734","title":"Layer-wise Analysis of a Self-supervised Speech Representation Model","created":"2021-07-10","cited_by_count":298},{"id":"2205.10643","title":"Self-Supervised Speech Representation Learning: A Review","created":"2022-05-21","cited_by_count":260},{"id":"1804.03160","title":"The Sound of Pixels","created":"2018-04-09","cited_by_count":259},{"id":"2008.04237","title":"Self-Supervised Learning of Audio-Visual Objects from Video","created":"2020-08-10","cited_by_count":188},{"id":"2006.12847","title":"Real Time Speech Enhancement in the Waveform Domain","created":"2020-06-23","cited_by_count":186},{"id":"2107.09293","title":"Audio2Head: Audio-driven One-shot Talking-head Generation with Natural Head Motion","created":"2021-07-20","cited_by_count":149},{"id":"1904.05979","title":"The Sound of Motions","created":"2019-04-11","cited_by_count":146},{"id":"1803.08673","title":"Revisiting Single Image Depth Estimation: Toward Higher Resolution Maps with Accurate Object Boundaries","created":"2018-03-23","cited_by_count":145},{"id":"1512.08512","title":"Visually Indicated Sounds","created":"2015-12-28","cited_by_count":128},{"id":"2104.03538","title":"MetricGAN+: An Improved Version of MetricGAN for Speech Enhancement","created":"2021-04-08","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":"2004.09476","title":"Music Gesture for Visual Sound Separation","created":"2020-04-20","cited_by_count":112},{"id":"2007.08547","title":"Talking-head Generation with Rhythmic Head Motion","created":"2020-07-16","cited_by_count":112},{"id":"1904.07750","title":"Co-Separating Sounds of Visual Objects","created":"2019-04-16","cited_by_count":110},{"id":"1804.04121","title":"The Conversation: Deep Audio-Visual Speech Enhancement","created":"2018-04-11","cited_by_count":109},{"id":"1901.03861","title":"HorizonNet: Learning Room Layout with 1D Representation and Pano Stretch Data Augmentation","created":"2019-01-12","cited_by_count":108},{"id":"2206.08312","title":"SoundSpaces 2.0: A Simulation Platform for Visual-Acoustic Learning","created":"2022-06-16","cited_by_count":95},{"id":"1901.01342","title":"AVA-ActiveSpeaker: An Audio-Visual Dataset for Active Speaker Detection","created":"2019-01-05","cited_by_count":83},{"id":"2012.11583","title":"Semantic Audio-Visual Navigation","created":"2020-12-21","cited_by_count":82},{"id":"2008.09586","title":"An Overview of Deep-Learning-Based Audio-Visual Speech Enhancement and Separation","created":"2020-08-21","cited_by_count":81},{"id":"1712.07271","title":"Learning Sight from Sound: Ambient Sound Provides Supervision for Visual Learning","created":"2017-12-20","cited_by_count":67},{"id":"2005.01616","title":"VisualEchoes: Spatial Image Representation Learning through Echolocation","created":"2020-05-04","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":"2202.10910","title":"Sound Adversarial Audio-Visual Navigation","created":"2022-02-22","cited_by_count":48},{"id":"2206.04006","title":"Few-Shot Audio-Visual Learning of Environment Acoustics","created":"2022-06-08","cited_by_count":48},{"id":"2202.06875","title":"Visual Acoustic Matching","created":"2022-02-14","cited_by_count":45},{"id":"1811.06795","title":"Building and Evaluation of a Real Room Impulse Response Dataset","created":"2018-11-16","cited_by_count":43},{"id":"2104.00568","title":"LED2-Net: Monocular 360 Layout Estimation via Differentiable Depth Rendering","created":"2021-04-01","cited_by_count":43},{"id":"2005.09812","title":"Active Speakers in Context","created":"2020-05-20","cited_by_count":41},{"id":"2006.05694","title":"HiFi-GAN: High-Fidelity Denoising and Dereverberation Based on Speech Deep Features in Adversarial Networks","created":"2020-06-10","cited_by_count":40},{"id":"2204.05841","title":"VoiceFixer: A Unified Framework for High-Fidelity Speech Restoration","created":"2022-04-12","cited_by_count":37},{"id":"2110.04057","title":"FAST-RIR: Fast neural diffuse room impulse response generator","created":"2021-10-07","cited_by_count":35},{"id":"2103.14201","title":"Image2Reverb: Cross-Modal Reverb Impulse Response Synthesis","created":"2021-03-26","cited_by_count":34},{"id":"1907.04975","title":"My lips are concealed: Audio-visual speech enhancement through obstructions","created":"2019-07-11","cited_by_count":26},{"id":"2106.07732","title":"Learning Audio-Visual Dereverberation","created":"2021-06-14","cited_by_count":26},{"id":"1907.00939","title":"Pano Popups: Indoor 3D Reconstruction with a Plane-Aware Network","created":"2019-07-01","cited_by_count":25},{"id":"2204.01787","title":"GWA: A Large High-Quality Acoustic Dataset for Audio Processing","created":"2022-04-04","cited_by_count":25},{"id":"2203.17263","title":"Audio-Visual Speech Codecs: Rethinking Audio-Visual Speech Enhancement by Re-Synthesis","created":"2022-03-31","cited_by_count":24},{"id":"2205.09248","title":"MESH2IR: Neural Acoustic Impulse Response Generator for Complex 3D Scenes","created":"2022-05-18","cited_by_count":23},{"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":"1909.07352","title":"Audio-Visual Speech Separation and Dereverberation with a Two-Stage Multimodal Network","created":"2019-09-16","cited_by_count":13},{"id":"2012.10852","title":"Visual Speech Enhancement Without A Real Visual Stream","created":"2020-12-20","cited_by_count":6},{"id":"2211.12623","title":"SkipConvGAN: Monaural Speech Dereverberation using Generative Adversarial Networks via Complex Time-Frequency Masking","created":"2022-11-22","cited_by_count":6},{"id":"2211.12632","title":"Complex-Valued Time-Frequency Self-Attention for Speech Dereverberation","created":"2022-11-22","cited_by_count":6},{"id":"2204.01977","title":"Audio-visual multi-channel speech separation, dereverberation and recognition","created":"2022-04-05","cited_by_count":3}],"next_cursor":null}