{"list":"other","total":77,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2011.13456","title":"Score-Based Generative Modeling through Stochastic Differential Equations","created":"2020-11-26","cited_by_count":9122},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"1503.03585","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","created":"2015-03-12","cited_by_count":7058},{"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":"2102.09672","title":"Improved Denoising Diffusion Probabilistic Models","created":"2021-02-18","cited_by_count":3761},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"2104.08718","title":"CLIPScore: A Reference-free Evaluation Metric for Image Captioning","created":"2021-04-18","cited_by_count":2424},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"id":"2107.03006","title":"Structured Denoising Diffusion Models in Discrete State-Spaces","created":"2021-07-07","cited_by_count":1719},{"id":"1906.00446","title":"Generating Diverse High-Fidelity Images with VQ-VAE-2","created":"2019-06-02","cited_by_count":1387},{"id":"1707.07998","title":"Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering","created":"2017-07-25","cited_by_count":1312},{"id":"2106.15282","title":"Cascaded Diffusion Models for High Fidelity Image Generation","created":"2021-05-30","cited_by_count":1163},{"id":"1812.08008","title":"OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2018-12-18","cited_by_count":1162},{"id":"2107.00630","title":"Variational Diffusion Models","created":"2021-07-01","cited_by_count":1153},{"id":"1611.08050","title":"Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2016-11-24","cited_by_count":1064},{"id":"2006.09011","title":"Improved Techniques for Training Score-Based Generative Models","created":"2020-06-16","cited_by_count":1043},{"id":"1705.09406","title":"Multimodal Machine Learning: A Survey and Taxonomy","created":"2017-05-26","cited_by_count":1013},{"id":"2111.14822","title":"Vector Quantized Diffusion Model for Text-to-Image Synthesis","created":"2021-11-29","cited_by_count":774},{"id":"1906.00910","title":"Learning Representations by Maximizing Mutual Information Across Views","created":"2019-06-03","cited_by_count":734},{"id":"1801.04062","title":"MINE: Mutual Information Neural Estimation","created":"2018-01-12","cited_by_count":683},{"id":"2101.09258","title":"Maximum Likelihood Training of Score-Based Diffusion Models","created":"2021-01-22","cited_by_count":672},{"id":"1711.10485","title":"AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks","created":"2017-11-28","cited_by_count":664},{"id":"2106.05931","title":"Score-based Generative Modeling in Latent Space","created":"2021-06-10","cited_by_count":636},{"id":"1612.03242","title":"StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks","created":"2016-12-10","cited_by_count":577},{"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":"1910.06711","title":"MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis","created":"2019-10-08","cited_by_count":354},{"id":"1804.03641","title":"Audio-Visual Scene Analysis with Self-Supervised Multisensory Features","created":"2018-04-10","cited_by_count":335},{"id":"1904.01310","title":"DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-to-Image Synthesis","created":"2019-04-02","cited_by_count":308},{"id":"1603.03925","title":"Image Captioning with Semantic Attention","created":"2016-03-12","cited_by_count":260},{"id":"2101.04702","title":"Cross-Modal Contrastive Learning for Text-to-Image Generation","created":"2021-01-12","cited_by_count":259},{"id":"1807.00230","title":"Cooperative Learning of Audio and Video Models from Self-Supervised Synchronization","created":"2018-06-30","cited_by_count":249},{"id":"1610.09001","title":"SoundNet: Learning Sound Representations from Unlabeled Video","created":"2016-10-27","cited_by_count":247},{"id":"1710.10916","title":"StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networks","created":"2017-10-19","cited_by_count":229},{"id":"1908.08498","title":"EPIC-Fusion: Audio-Visual Temporal Binding for Egocentric Action Recognition","created":"2019-08-22","cited_by_count":226},{"id":"1809.04281","title":"Music Transformer","created":"2018-09-12","cited_by_count":211},{"id":"1909.07083","title":"Controllable Text-to-Image Generation","created":"2019-09-16","cited_by_count":187},{"id":"2106.02808","title":"A Variational Perspective on Diffusion-Based Generative Models and Score Matching","created":"2021-06-05","cited_by_count":183},{"id":"1912.04487","title":"Listen to Look: Action Recognition by Previewing Audio","created":"2019-12-10","cited_by_count":163},{"id":"1709.06298","title":"MuseGAN: Multi-track Sequential Generative Adversarial Networks for Symbolic Music Generation and Accompaniment","created":"2017-09-19","cited_by_count":151},{"id":"1910.06222","title":"Understanding the Limitations of Variational Mutual Information Estimators","created":"2019-10-14","cited_by_count":140},{"id":"2108.08827","title":"ImageBART: Bidirectional Context with Multinomial Diffusion for Autoregressive Image Synthesis","created":"2021-08-19","cited_by_count":122},{"id":"2004.09476","title":"Music Gesture for Visual Sound Separation","created":"2020-04-20","cited_by_count":112},{"id":"2002.03712","title":"On Contrastive Learning for Likelihood-free Inference","created":"2020-02-10","cited_by_count":98},{"id":"2007.10984","title":"Foley Music: Learning to Generate Music from Videos","created":"2020-07-21","cited_by_count":83},{"id":"1712.07271","title":"Learning Sight from Sound: Ambient Sound Provides Supervision for Visual Learning","created":"2017-12-20","cited_by_count":67},{"id":"2011.06801","title":"A Comprehensive Survey on Deep Music Generation: Multi-level Representations, Algorithms, Evaluations, and Future Directions","created":"2020-11-13","cited_by_count":56},{"id":"2111.08380","title":"Video Background Music Generation with Controllable Music Transformer","created":"2021-11-16","cited_by_count":56},{"id":"2104.07021","title":"Dressing in Order: Recurrent Person Image Generation for Pose Transfer, Virtual Try-on and Outfit Editing","created":"2021-04-14","cited_by_count":54},{"id":"2108.12141","title":"DAE-GAN: Dynamic Aspect-aware GAN for Text-to-Image Synthesis","created":"2021-08-27","cited_by_count":45},{"id":"2101.04924","title":"Learning to Anticipate Egocentric Actions by Imagination","created":"2021-01-13","cited_by_count":40},{"id":"2112.01799","title":"Global Context with Discrete Diffusion in Vector Quantised Modelling for Image Generation","created":"2021-12-03","cited_by_count":40},{"id":"1909.09944","title":"Watch, Listen and Tell: Multi-modal Weakly Supervised Dense Event Captioning","created":"2019-09-22","cited_by_count":38},{"id":"2204.00604","title":"Quantized GAN for Complex Music Generation from Dance Videos","created":"2022-04-01","cited_by_count":37},{"id":"2111.13333","title":"Predict, Prevent, and Evaluate: Disentangled Text-Driven Image Manipulation Empowered by Pre-Trained Vision-Language Model","created":"2021-11-26","cited_by_count":34},{"id":"1711.07068","title":"Diverse and Accurate Image Description Using a Variational Auto-Encoder with an Additive Gaussian Encoding Space","created":"2017-11-19","cited_by_count":33},{"id":"2007.09852","title":"Multi-label Contrastive Predictive Coding","created":"2020-07-20","cited_by_count":32},{"id":"1804.05448","title":"Watch, Listen, and Describe: Globally and Locally Aligned Cross-Modal Attentions for Video Captioning","created":"2018-04-15","cited_by_count":21},{"id":"2107.06252","title":"Dance2Music: Automatic Dance-driven Music Generation","created":"2021-07-13","cited_by_count":16},{"id":"2102.03424","title":"Learning Audio-Visual Correlations from Variational Cross-Modal Generation","created":"2021-02-05","cited_by_count":14},{"id":"2007.07238","title":"Modeling Artistic Workflows for Image Generation and Editing","created":"2020-07-14","cited_by_count":11},{"id":"2008.07935","title":"Describing Unseen Videos via Multi-Modal Cooperative Dialog Agents","created":"2020-08-18","cited_by_count":11},{"id":"2106.14069","title":"Saying the Unseen: Video Descriptions via Dialog Agents","created":"2021-06-26","cited_by_count":5}],"next_cursor":null}