{"list":"other","total":67,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2005.10242","title":"Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere","created":"2020-05-20","cited_by_count":1405},{"id":"1904.08779","title":"SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition","created":"2019-04-18","cited_by_count":1380},{"id":"1711.03213","title":"CyCADA: Cycle-Consistent Adversarial Domain Adaptation","created":"2017-11-08","cited_by_count":1082},{"id":"1504.06852","title":"FlowNet: Learning Optical Flow with Convolutional Networks","created":"2015-04-26","cited_by_count":1059},{"id":"1512.02134","title":"A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation","created":"2015-12-07","cited_by_count":881},{"id":"2005.10243","title":"What Makes for Good Views for Contrastive Learning?","created":"2020-05-20","cited_by_count":846},{"id":"2211.06687","title":"Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation","created":"2022-11-12","cited_by_count":719},{"id":"1609.09430","title":"CNN Architectures for Large-Scale Audio Classification","created":"2016-09-29","cited_by_count":704},{"id":"2004.14368","title":"VGGSound: A Large-scale Audio-Visual Dataset","created":"2020-04-29","cited_by_count":648},{"id":"2104.01778","title":"AST: Audio Spectrogram Transformer","created":"2021-04-05","cited_by_count":643},{"id":"1902.09229","title":"A Theoretical Analysis of Contrastive Unsupervised Representation Learning","created":"2019-02-25","cited_by_count":530},{"id":"1701.01370","title":"Learning from Synthetic Humans","created":"2017-01-05","cited_by_count":359},{"id":"2010.00475","title":"FSD50K: An Open Dataset of Human-Labeled Sound Events","created":"2020-10-01","cited_by_count":342},{"id":"1612.07828","title":"Learning from Simulated and Unsupervised Images through Adversarial Training","created":"2016-12-22","cited_by_count":288},{"id":"2302.07944","title":"Effective Data Augmentation With Diffusion Models","created":"2023-02-07","cited_by_count":283},{"id":"2104.06490","title":"DatasetGAN: Efficient Labeled Data Factory with Minimal Human Effort","created":"2021-04-13","cited_by_count":264},{"id":"1704.01279","title":"Neural Audio Synthesis of Musical Notes with WaveNet Autoencoders","created":"2017-04-05","cited_by_count":225},{"id":"1812.08466","title":"Fr\\'echet Audio Distance: A Metric for Evaluating Music Enhancement Algorithms","created":"2018-12-20","cited_by_count":225},{"id":"2202.04538","title":"Generating Training Data with Language Models: Towards Zero-Shot Language Understanding","created":"2022-02-09","cited_by_count":199},{"id":"2306.00984","title":"StableRep: Synthetic Images from Text-to-Image Models Make Strong Visual Representation Learners","created":"2023-06-01","cited_by_count":177},{"id":"2010.10915","title":"Contrastive Learning of General-Purpose Audio Representations","created":"2020-10-21","cited_by_count":169},{"id":"2003.02245","title":"Data Augmentation using Pre-trained Transformer Models","created":"2020-03-04","cited_by_count":168},{"id":"2008.10150","title":"Contrastive learning, multi-view redundancy, and linear models","created":"2020-08-24","cited_by_count":146},{"id":"2104.05833","title":"Semantic Segmentation with Generative Models: Semi-Supervised Learning and Strong Out-of-Domain Generalization","created":"2021-04-12","cited_by_count":141},{"id":"1905.10887","title":"Classification Accuracy Score for Conditional Generative Models","created":"2019-05-26","cited_by_count":136},{"id":"2012.01469","title":"Fair Attribute Classification through Latent Space De-biasing","created":"2020-12-02","cited_by_count":125},{"id":"1812.05040","title":"Learning Semantic Segmentation from Synthetic Data: A Geometrically Guided Input-Output Adaptation Approach","created":"2018-12-12","cited_by_count":119},{"id":"2103.06695","title":"BYOL for Audio: Self-Supervised Learning for General-Purpose Audio Representation","created":"2021-03-11","cited_by_count":106},{"id":"2106.05258","title":"Generative Models as a Data Source for Multiview Representation Learning","created":"2021-06-09","cited_by_count":104},{"id":"2101.08515","title":"Pre-training without Natural Images","created":"2021-01-21","cited_by_count":100},{"id":"2106.05963","title":"Learning to See by Looking at Noise","created":"2021-06-10","cited_by_count":92},{"id":"2311.01616","title":"Adapting Frechet Audio Distance for Generative Music Evaluation","created":"2023-11-02","cited_by_count":92},{"id":"2103.04379","title":"Repurposing GANs for One-shot Semantic Part Segmentation","created":"2021-03-07","cited_by_count":88},{"id":"2208.12415","title":"MuLan: A Joint Embedding of Music Audio and Natural Language","created":"2022-08-26","cited_by_count":87},{"id":"2103.09410","title":"Contrastive Learning of Musical Representations","created":"2021-03-17","cited_by_count":82},{"id":"2203.03022","title":"HEAR: Holistic Evaluation of Audio Representations","created":"2022-03-06","cited_by_count":78},{"id":"2312.17742","title":"Learning Vision from Models Rivals Learning Vision from Data","created":"2023-12-28","cited_by_count":71},{"id":"1911.02888","title":"This dataset does not exist: training models from generated images","created":"2019-11-07","cited_by_count":65},{"id":"1909.11699","title":"Speech Recognition with Augmented Synthesized Speech","created":"2019-09-25","cited_by_count":60},{"id":"2106.04566","title":"Data-Efficient Instance Generation from Instance Discrimination","created":"2021-06-08","cited_by_count":58},{"id":"1711.09082","title":"Cross-Domain Self-supervised Multi-task Feature Learning using Synthetic Imagery","created":"2017-11-24","cited_by_count":56},{"id":"1912.09257","title":"Generating Synthetic Audio Data for Attention-Based Speech Recognition Systems","created":"2019-12-19","cited_by_count":47},{"id":"2012.04842","title":"Improving the Fairness of Deep Generative Models without Retraining","created":"2020-12-09","cited_by_count":46},{"id":"2103.09742","title":"Training GANs with Stronger Augmentations via Contrastive Discriminator","created":"2021-03-17","cited_by_count":45},{"id":"2102.05109","title":"CDPAM: Contrastive learning for perceptual audio similarity","created":"2021-02-09","cited_by_count":42},{"id":"2011.11564","title":"Using Synthetic Audio to Improve The Recognition of Out-Of-Vocabulary Words in End-To-End ASR Systems","created":"2020-11-23","cited_by_count":41},{"id":"2103.06508","title":"Multi-Format Contrastive Learning of Audio Representations","created":"2021-03-11","cited_by_count":39},{"id":"2012.03769","title":"Overcoming Barriers to Data Sharing with Medical Image Generation: A Comprehensive Evaluation","created":"2020-11-29","cited_by_count":36},{"id":"2106.07803","title":"SynthASR: Unlocking Synthetic Data for Speech Recognition","created":"2021-06-14","cited_by_count":34},{"id":"2011.07616","title":"Unsupervised Contrastive Learning of Sound Event Representations","created":"2020-11-15","cited_by_count":32},{"id":"2010.09542","title":"CLAR: Contrastive Learning of Auditory Representations","created":"2020-10-19","cited_by_count":31},{"id":"2305.10951","title":"Making More of Little Data: Improving Low-Resource Automatic Speech Recognition Using Data Augmentation","created":"2023-05-18","cited_by_count":31},{"id":"2005.07157","title":"You Do Not Need More Data: Improving End-To-End Speech Recognition by Text-To-Speech Data Augmentation","created":"2020-05-14","cited_by_count":29},{"id":"2211.16412","title":"Procedural Image Programs for Representation Learning","created":"2022-11-29","cited_by_count":28},{"id":"1812.00271","title":"Learning Speaker Representations with Mutual Information","created":"2018-12-01","cited_by_count":26},{"id":"2110.11479","title":"Synt++: Utilizing Imperfect Synthetic Data to Improve Speech Recognition","created":"2021-10-21","cited_by_count":24},{"id":"2303.17200","title":"SynthVSR: Scaling Up Visual Speech Recognition With Synthetic Supervision","created":"2023-03-30","cited_by_count":21},{"id":"2403.17508","title":"Correlation of Fr\\'echet Audio Distance With Human Perception of Environmental Audio Is Embedding Dependant","created":"2024-03-26","cited_by_count":15},{"id":"2405.00934","title":"Benchmarking Representations for Speech, Music, and Acoustic Events","created":"2024-05-02","cited_by_count":15},{"id":"2104.12922","title":"One Billion Audio Sounds from GPU-enabled Modular Synthesis","created":"2021-04-27","cited_by_count":11},{"id":"2010.10203","title":"Replacing Human Audio with Synthetic Audio for On-device Unspoken Punctuation Prediction","created":"2020-10-20","cited_by_count":8},{"id":"2209.12900","title":"The Efficacy of Self-Supervised Speech Models for Audio Representations","created":"2022-09-26","cited_by_count":6},{"id":"2211.11225","title":"TimbreCLIP: Connecting Timbre to Text and Images","created":"2022-11-21","cited_by_count":5},{"id":"2406.00294","title":"Creative Text-to-Audio Generation via Synthesizer Programming","created":"2024-06-01","cited_by_count":4},{"id":"2210.10857","title":"Modeling Animal Vocalizations through Synthesizers","created":"2022-10-19","cited_by_count":3},{"id":"1811.06439","title":"HCU400: An Annotated Dataset for Exploring Aural Phenomenology Through Causal Uncertainty","created":"2018-11-15","cited_by_count":2}],"next_cursor":null}