{"list":"other","total":67,"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":"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":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"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":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"1606.03498","title":"Improved Techniques for Training GANs","created":"2016-06-10","cited_by_count":2970},{"id":"1809.11096","title":"Large Scale GAN Training for High Fidelity Natural Image Synthesis","created":"2018-09-28","cited_by_count":2626},{"id":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"id":"1411.1784","title":"Conditional Generative Adversarial Nets","created":"2014-11-06","cited_by_count":2162},{"id":"2006.06676","title":"Training Generative Adversarial Networks with Limited Data","created":"2020-06-11","cited_by_count":1186},{"id":"2112.03857","title":"Grounded Language-Image Pre-training","created":"2021-12-07","cited_by_count":1156},{"id":"2106.04560","title":"Scaling Vision Transformers","created":"2021-06-08","cited_by_count":999},{"id":"1605.05396","title":"Generative Adversarial Text to Image Synthesis","created":"2016-05-17","cited_by_count":735},{"id":"2205.08534","title":"Vision Transformer Adapter for Dense Predictions","created":"2022-05-17","cited_by_count":565},{"id":"2112.01526","title":"MViTv2: Improved Multiscale Vision Transformers for Classification and Detection","created":"2021-12-02","cited_by_count":519},{"id":"2101.02702","title":"TrackFormer: Multi-Object Tracking with Transformers","created":"2021-01-07","cited_by_count":518},{"id":"1701.04862","title":"Towards Principled Methods for Training Generative Adversarial Networks","created":"2017-01-17","cited_by_count":464},{"id":"1610.07629","title":"A Learned Representation For Artistic Style","created":"2016-10-24","cited_by_count":341},{"id":"1511.05440","title":"Deep multi-scale video prediction beyond mean square error","created":"2015-11-17","cited_by_count":300},{"id":"1605.07157","title":"Unsupervised Learning for Physical Interaction through Video Prediction","created":"2016-05-23","cited_by_count":260},{"id":"1802.05637","title":"cGANs with Projection Discriminator","created":"2018-02-15","cited_by_count":254},{"id":"1908.10553","title":"Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Video","created":"2019-08-28","cited_by_count":244},{"id":"1710.11252","title":"Stochastic Variational Video Prediction","created":"2017-10-30","cited_by_count":234},{"id":"1705.02894","title":"Geometric GAN","created":"2017-05-08","cited_by_count":233},{"id":"1706.08500","title":"GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium","created":"2017-06-26","cited_by_count":213},{"id":"1605.08104","title":"Deep Predictive Coding Networks for Video Prediction and Unsupervised Learning","created":"2016-05-25","cited_by_count":204},{"id":"1604.03901","title":"Single-Image Depth Perception in the Wild","created":"2016-04-13","cited_by_count":180},{"id":"1506.04579","title":"ParseNet: Looking Wider to See Better","created":"2015-06-15","cited_by_count":177},{"id":"1707.00683","title":"Modulating early visual processing by language","created":"2017-07-02","cited_by_count":167},{"id":"2012.04781","title":"You Only Need Adversarial Supervision for Semantic Image Synthesis","created":"2020-12-08","cited_by_count":129},{"id":"1910.06809","title":"Learning to Predict Layout-to-image Conditional Convolutions for Semantic Image Synthesis","created":"2019-10-15","cited_by_count":108},{"id":"1809.04184","title":"Searching for Efficient Multi-Scale Architectures for Dense Image Prediction","created":"2018-09-11","cited_by_count":96},{"id":"1704.07804","title":"SfM-Net: Learning of Structure and Motion from Video","created":"2017-04-25","cited_by_count":89},{"id":"1903.01434","title":"VideoFlow: A Conditional Flow-Based Model for Stochastic Video Generation","created":"2019-03-04","cited_by_count":74},{"id":"2111.04060","title":"Are we ready for a new paradigm shift? A Survey on Visual Deep MLP","created":"2021-11-07","cited_by_count":63},{"id":"2103.01950","title":"Predicting Video with VQVAE","created":"2021-03-02","cited_by_count":61},{"id":"1703.02291","title":"Triple Generative Adversarial Nets","created":"2017-03-07","cited_by_count":60},{"id":"2102.02629","title":"Learning Monocular Depth in Dynamic Scenes via Instance-Aware Projection Consistency","created":"2021-02-04","cited_by_count":58},{"id":"2004.04977","title":"SESAME: Semantic Editing of Scenes by Adding, Manipulating or Erasing Objects","created":"2020-04-10","cited_by_count":43},{"id":"2103.15145","title":"TransCenter: Transformers with Dense Representations for Multiple-Object Tracking","created":"2021-03-28","cited_by_count":42},{"id":"2001.03653","title":"Towards GAN Benchmarks Which Require Generalization","created":"2020-01-10","cited_by_count":31},{"id":"2211.09807","title":"Towards All-in-one Pre-training via Maximizing Multi-modal Mutual Information","created":"2022-11-17","cited_by_count":31},{"id":"1901.03353","title":"RetinaMask: Learning to predict masks improves state-of-the-art single-shot detection for free","created":"2019-01-10","cited_by_count":24},{"id":"1708.08819","title":"Coulomb GANs: Provably Optimal Nash Equilibria via Potential Fields","created":"2017-08-29","cited_by_count":20},{"id":"2002.09124","title":"GANs May Have No Nash Equilibria","created":"2020-02-21","cited_by_count":20},{"id":"1705.07215","title":"On Convergence and Stability of GANs","created":"2017-05-19","cited_by_count":18},{"id":"1810.00746","title":"Bayesian Prediction of Future Street Scenes using Synthetic Likelihoods","created":"2018-10-01","cited_by_count":17},{"id":"2004.05821","title":"Monocular Depth Estimation with Self-supervised Instance Adaptation","created":"2020-04-13","cited_by_count":12},{"id":"2112.09747","title":"A Simple Single-Scale Vision Transformer for Object Localization and Instance Segmentation","created":"2021-12-17","cited_by_count":12},{"id":"2006.14208","title":"Searching towards Class-Aware Generators for Conditional Generative Adversarial Networks","created":"2020-06-25","cited_by_count":6},{"id":"2008.00192","title":"PanoNet: Real-time Panoptic Segmentation through Position-Sensitive Feature Embedding","created":"2020-08-01","cited_by_count":5},{"id":"2003.08376","title":"Inverting the Pose Forecasting Pipeline with SPF2: Sequential Pointcloud Forecasting for Sequential Pose Forecasting","created":"2020-03-18","cited_by_count":4},{"id":"2006.12681","title":"ContraGAN: Contrastive Learning for Conditional Image Generation","created":"2020-06-23","cited_by_count":3},{"id":"1806.09235","title":"Towards a Better Understanding and Regularization of GAN Training Dynamics","created":"2018-06-24","cited_by_count":2},{"id":"2106.15011","title":"Are conditional GANs explicitly conditional?","created":"2021-06-28","cited_by_count":2},{"id":"2010.02893","title":"SAFENet: Self-Supervised Monocular Depth Estimation with Semantic-Aware Feature Extraction","created":"2020-10-06","cited_by_count":1},{"id":"2303.01196","title":"STDepthFormer: Predicting Spatio-temporal Depth from Video with a Self-supervised Transformer Model","created":"2023-03-02","cited_by_count":1}],"next_cursor":null}