{"list":"other","total":115,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1503.03585","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","created":"2015-03-12","cited_by_count":7058},{"id":"2006.07733","title":"Bootstrap your own latent: A new approach to self-supervised Learning","created":"2020-06-13","cited_by_count":4750},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"2006.09882","title":"Unsupervised Learning of Visual Features by Contrasting Cluster Assignments","created":"2020-06-17","cited_by_count":2857},{"id":"2106.08254","title":"BEiT: BERT Pre-Training of Image Transformers","created":"2021-06-15","cited_by_count":2375},{"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":"2103.03230","title":"Barlow Twins: Self-Supervised Learning via Redundancy Reduction","created":"2021-03-04","cited_by_count":1838},{"id":"2103.15691","title":"ViViT: A Video Vision Transformer","created":"2021-03-29","cited_by_count":1620},{"id":"1711.11248","title":"A Closer Look at Spatiotemporal Convolutions for Action Recognition","created":"2017-11-30","cited_by_count":1143},{"id":"2103.03206","title":"Perceiver: General Perception with Iterative Attention","created":"2021-03-04","cited_by_count":1104},{"id":"1406.2199","title":"Two-Stream Convolutional Networks for Action Recognition in Videos","created":"2014-06-09","cited_by_count":1068},{"id":"1705.09406","title":"Multimodal Machine Learning: A Survey and Taxonomy","created":"2017-05-26","cited_by_count":1013},{"id":"2111.07832","title":"iBOT: Image BERT Pre-Training with Online Tokenizer","created":"2021-11-15","cited_by_count":903},{"id":"2104.01778","title":"AST: Audio Spectrogram Transformer","created":"2021-04-05","cited_by_count":643},{"id":"2109.14084","title":"VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding","created":"2021-09-28","cited_by_count":602},{"id":"2112.09133","title":"Masked Feature Prediction for Self-Supervised Visual Pre-Training","created":"2021-12-16","cited_by_count":576},{"id":"1912.10211","title":"PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognition","created":"2019-12-21","cited_by_count":574},{"id":"2005.00341","title":"Jukebox: A Generative Model for Music","created":"2020-04-30","cited_by_count":542},{"id":"2101.08779","title":"AI Choreographer: Music Conditioned 3D Dance Generation with AIST++","created":"2021-01-21","cited_by_count":485},{"id":"1705.08168","title":"Look, Listen and Learn","created":"2017-05-23","cited_by_count":458},{"id":"2104.11178","title":"VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text","created":"2021-04-22","cited_by_count":429},{"id":"1604.06573","title":"Convolutional Two-Stream Network Fusion for Video Action Recognition","created":"2016-04-22","cited_by_count":384},{"id":"2008.03800","title":"Spatiotemporal Contrastive Video Representation Learning","created":"2020-08-09","cited_by_count":372},{"id":"2107.00135","title":"Attention Bottlenecks for Multimodal Fusion","created":"2021-06-30","cited_by_count":361},{"id":"1609.08675","title":"YouTube-8M: A Large-Scale Video Classification Benchmark","created":"2016-09-27","cited_by_count":324},{"id":"1906.06755","title":"Theoretical Limitations of Self-Attention in Neural Sequence Models","created":"2019-06-16","cited_by_count":288},{"id":"2201.02184","title":"Learning Audio-Visual Speech Representation by Masked Multimodal Cluster Prediction","created":"2022-01-05","cited_by_count":287},{"id":"1705.02953","title":"Temporal Segment Networks for Action Recognition in Videos","created":"2017-05-08","cited_by_count":279},{"id":"2006.16228","title":"Self-Supervised MultiModal Versatile Networks","created":"2020-06-29","cited_by_count":276},{"id":"1911.12667","title":"Self-Supervised Learning by Cross-Modal Audio-Video Clustering","created":"2019-11-28","cited_by_count":267},{"id":"1804.03160","title":"The Sound of Pixels","created":"2018-04-09","cited_by_count":259},{"id":"1503.08909","title":"Beyond Short Snippets: Deep Networks for Video Classification","created":"2015-03-31","cited_by_count":233},{"id":"2110.05069","title":"Efficient Training of Audio Transformers with Patchout","created":"2021-10-11","cited_by_count":226},{"id":"2104.14558","title":"A Large-Scale Study on Unsupervised Spatiotemporal Representation Learning","created":"2021-04-29","cited_by_count":214},{"id":"2008.04237","title":"Self-Supervised Learning of Audio-Visual Objects from Video","created":"2020-08-10","cited_by_count":188},{"id":"2003.00392","title":"Fine-grained Video-Text Retrieval with Hierarchical Graph Reasoning","created":"2020-03-01","cited_by_count":180},{"id":"2104.02691","title":"Localizing Visual Sounds the Hard Way","created":"2021-04-06","cited_by_count":170},{"id":"2010.10915","title":"Contrastive Learning of General-Purpose Audio Representations","created":"2020-10-21","cited_by_count":169},{"id":"2112.01529","title":"BEVT: BERT Pretraining of Video Transformers","created":"2021-12-02","cited_by_count":169},{"id":"2202.01855","title":"Self-supervised Learning with Random-projection Quantizer for Speech Recognition","created":"2022-02-03","cited_by_count":162},{"id":"1812.07809","title":"Found in Translation: Learning Robust Joint Representations by Cyclic Translations Between Modalities","created":"2018-12-19","cited_by_count":149},{"id":"1904.05979","title":"The Sound of Motions","created":"2019-04-11","cited_by_count":146},{"id":"2101.07974","title":"TCLR: Temporal Contrastive Learning for Video Representation","created":"2021-01-20","cited_by_count":136},{"id":"1904.04289","title":"SCSampler: Sampling Salient Clips from Video for Efficient Action Recognition","created":"2019-04-08","cited_by_count":134},{"id":"1611.00471","title":"Dual Attention Networks for Multimodal Reasoning and Matching","created":"2016-11-02","cited_by_count":114},{"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":"2104.11746","title":"VidTr: Video Transformer Without Convolutions","created":"2021-04-23","cited_by_count":112},{"id":"2006.09199","title":"AVLnet: Learning Audio-Visual Language Representations from Instructional Videos","created":"2020-06-16","cited_by_count":111},{"id":"1904.07750","title":"Co-Separating Sounds of Visual Objects","created":"2019-04-16","cited_by_count":110},{"id":"2103.16559","title":"Broaden Your Views for Self-Supervised Video Learning","created":"2021-03-30","cited_by_count":108},{"id":"1610.01206","title":"A Survey of Multi-View Representation Learning","created":"2016-10-03","cited_by_count":107},{"id":"2011.01819","title":"Learning Representations from Audio-Visual Spatial Alignment","created":"2020-11-03","cited_by_count":95},{"id":"1905.00078","title":"Deep Learning for Audio Signal Processing","created":"2019-04-30","cited_by_count":92},{"id":"2007.10984","title":"Foley Music: Learning to Generate Music from Videos","created":"2020-07-21","cited_by_count":83},{"id":"2103.12718","title":"Self-Supervised Pretraining Improves Self-Supervised Pretraining","created":"2021-03-23","cited_by_count":82},{"id":"2001.00294","title":"Video Cloze Procedure for Self-Supervised Spatio-Temporal Learning","created":"2020-01-02","cited_by_count":81},{"id":"2012.10671","title":"SMART Frame Selection for Action Recognition","created":"2020-12-19","cited_by_count":73},{"id":"2001.04758","title":"Deep Audio-Visual Learning: A Survey","created":"2020-01-14","cited_by_count":69},{"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":"1906.05571","title":"Learning Spatio-Temporal Representation with Local and Global Diffusion","created":"2019-06-13","cited_by_count":61},{"id":"1812.08249","title":"D3D: Distilled 3D Networks for Video Action Recognition","created":"2018-12-19","cited_by_count":60},{"id":"2105.04489","title":"Spoken Moments: Learning Joint Audio-Visual Representations from Video Descriptions","created":"2021-05-10","cited_by_count":53},{"id":"1810.01455","title":"Representation Flow for Action Recognition","created":"2018-10-02","cited_by_count":51},{"id":"2104.09952","title":"MGSampler: An Explainable Sampling Strategy for Video Action Recognition","created":"2021-04-20","cited_by_count":49},{"id":"2003.13042","title":"Omni-sourced Webly-supervised Learning for Video Recognition","created":"2020-03-29","cited_by_count":48},{"id":"2008.02531","title":"Self-supervised Video Representation Learning Using Inter-intra Contrastive Framework","created":"2020-08-06","cited_by_count":46},{"id":"1711.02209","title":"Unsupervised Learning of Semantic Audio Representations","created":"2017-11-06","cited_by_count":44},{"id":"2103.06508","title":"Multi-Format Contrastive Learning of Audio Representations","created":"2021-03-11","cited_by_count":39},{"id":"2008.06581","title":"Audio-Visual Event Localization via Recursive Fusion by Joint Co-Attention","created":"2020-08-14","cited_by_count":37},{"id":"1909.08782","title":"Large-scale representation learning from visually grounded untranscribed speech","created":"2019-09-19","cited_by_count":33},{"id":"2104.12807","title":"Multimodal Self-Supervised Learning of General Audio Representations","created":"2021-04-26","cited_by_count":32},{"id":"1512.00795","title":"Actions ~ Transformations","created":"2015-12-02","cited_by_count":30},{"id":"2104.06401","title":"Self-supervised object detection from audio-visual correspondence","created":"2021-04-13","cited_by_count":29},{"id":"2106.01621","title":"ERANNs: Efficient Residual Audio Neural Networks for Audio Pattern Recognition","created":"2021-06-03","cited_by_count":29},{"id":"1609.06782","title":"Deep Learning for Video Classification and Captioning","created":"2016-09-22","cited_by_count":28},{"id":"1710.05106","title":"CM-GANs: Cross-modal Generative Adversarial Networks for Common Representation Learning","created":"2017-10-14","cited_by_count":27},{"id":"1908.02590","title":"Audio-visual Speech Enhancement Using Conditional Variational Auto-Encoders","created":"2019-08-07","cited_by_count":27},{"id":"1911.05894","title":"Coincidence, Categorization, and Consolidation: Learning to Recognize Sounds with Minimal Supervision","created":"2019-11-14","cited_by_count":27},{"id":"2104.13332","title":"End-to-End Video-To-Speech Synthesis using Generative Adversarial Networks","created":"2021-04-27","cited_by_count":27},{"id":"2105.11087","title":"Recent Advances and Trends in Multimodal Deep Learning: A Review","created":"2021-05-24","cited_by_count":26},{"id":"2001.04627","title":"Self-supervising Action Recognition by Statistical Moment and Subspace Descriptors","created":"2020-01-14","cited_by_count":24},{"id":"1909.03795","title":"Language learning using Speech to Image retrieval","created":"2019-09-09","cited_by_count":21},{"id":"1908.03737","title":"Deep Triplet Neural Networks with Cluster-CCA for Audio-Visual Cross-modal Retrieval","created":"2019-08-10","cited_by_count":18},{"id":"2102.07751","title":"Deep Co-Attention Network for Multi-View Subspace Learning","created":"2021-02-15","cited_by_count":17},{"id":"1908.03744","title":"Audio-Visual Embedding for Cross-Modal MusicVideo Retrieval through Supervised Deep CCA","created":"2019-08-10","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":"2001.09414","title":"Curriculum Audiovisual Learning","created":"2020-01-26","cited_by_count":14},{"id":"2102.03424","title":"Learning Audio-Visual Correlations from Variational Cross-Modal Generation","created":"2021-02-05","cited_by_count":14}],"next_cursor":"100"}