{"list":"other","total":55,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"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":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"id":"1301.3781","title":"Efficient Estimation of Word Representations in Vector Space","created":"2013-01-16","cited_by_count":4375},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"id":"1809.11096","title":"Large Scale GAN Training for High Fidelity Natural Image Synthesis","created":"2018-09-28","cited_by_count":2626},{"id":"1607.00653","title":"node2vec: Scalable Feature Learning for Networks","created":"2016-07-03","cited_by_count":1918},{"id":"1807.10165","title":"UNet++: A Nested U-Net Architecture for Medical Image Segmentation","created":"2018-07-18","cited_by_count":1525},{"id":"2111.09883","title":"Swin Transformer V2: Scaling Up Capacity and Resolution","created":"2021-11-18","cited_by_count":1228},{"id":"2105.05537","title":"Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation","created":"2021-05-12","cited_by_count":1222},{"id":"2106.15282","title":"Cascaded Diffusion Models for High Fidelity Image Generation","created":"2021-05-30","cited_by_count":1163},{"id":"2209.00796","title":"Diffusion Models: A Comprehensive Survey of Methods and Applications","created":"2022-09-02","cited_by_count":1114},{"id":"2105.13290","title":"CogView: Mastering Text-to-Image Generation via Transformers","created":"2021-05-26","cited_by_count":694},{"id":"1912.05074","title":"UNet++: Redesigning Skip Connections to Exploit Multiscale Features in Image Segmentation","created":"2019-12-11","cited_by_count":586},{"id":"1807.05511","title":"Object Detection with Deep Learning: A Review","created":"2018-07-15","cited_by_count":528},{"id":"2203.13131","title":"Make-A-Scene: Scene-Based Text-to-Image Generation with Human Priors","created":"2022-03-24","cited_by_count":487},{"id":"1709.05584","title":"Representation Learning on Graphs: Methods and Applications","created":"2017-09-17","cited_by_count":457},{"id":"1711.10684","title":"Road Extraction by Deep Residual U-Net","created":"2017-11-29","cited_by_count":333},{"id":"2004.08790","title":"UNet 3+: A Full-Scale Connected UNet for Medical Image Segmentation","created":"2020-04-19","cited_by_count":332},{"id":"1804.01622","title":"Image Generation from Scene Graphs","created":"2018-04-04","cited_by_count":324},{"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":"2204.08583","title":"VQGAN-CLIP: Open Domain Image Generation and Editing with Natural Language Guidance","created":"2022-04-18","cited_by_count":285},{"id":"2101.04702","title":"Cross-Modal Contrastive Learning for Text-to-Image Generation","created":"2021-01-12","cited_by_count":259},{"id":"1812.02378","title":"Auto-Encoding Scene Graphs for Image Captioning","created":"2018-12-06","cited_by_count":255},{"id":"1710.10916","title":"StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networks","created":"2017-10-19","cited_by_count":229},{"id":"1801.01973","title":"A Note on the Inception Score","created":"2018-01-06","cited_by_count":226},{"id":"1902.04049","title":"MultiResUNet : Rethinking the U-Net Architecture for Multimodal Biomedical Image Segmentation","created":"2019-02-11","cited_by_count":195},{"id":"1802.06955","title":"Recurrent Residual Convolutional Neural Network based on U-Net (R2U-Net) for Medical Image Segmentation","created":"2018-02-20","cited_by_count":180},{"id":"1911.12676","title":"xMUDA: Cross-Modal Unsupervised Domain Adaptation for 3D Semantic Segmentation","created":"2019-11-28","cited_by_count":129},{"id":"2111.13792","title":"LAFITE: Towards Language-Free Training for Text-to-Image Generation","created":"2021-11-27","cited_by_count":128},{"id":"1910.07655","title":"Deep Semantic Segmentation of Natural and Medical Images: A Review","created":"2019-10-16","cited_by_count":125},{"id":"2104.01111","title":"A Comprehensive Survey of Scene Graphs: Generation and Application","created":"2021-03-17","cited_by_count":125},{"id":"1903.12314","title":"Relation-Aware Graph Attention Network for Visual Question Answering","created":"2019-03-29","cited_by_count":119},{"id":"1902.10740","title":"Object-driven Text-to-Image Synthesis via Adversarial Training","created":"2019-02-27","cited_by_count":117},{"id":"1811.11389","title":"Image Generation from Layout","created":"2018-11-28","cited_by_count":105},{"id":"1903.10658","title":"Unpaired Image Captioning via Scene Graph Alignments","created":"2019-03-26","cited_by_count":82},{"id":"1909.00958","title":"Graph Representation Learning: A Survey","created":"2019-09-03","cited_by_count":75},{"id":"2201.00443","title":"Scene Graph Generation: A Comprehensive Survey","created":"2022-01-03","cited_by_count":73},{"id":"1702.05870","title":"Cosine Normalization: Using Cosine Similarity Instead of Dot Product in Neural Networks","created":"2017-02-20","cited_by_count":59},{"id":"2007.11731","title":"Comprehensive Image Captioning via Scene Graph Decomposition","created":"2020-07-23","cited_by_count":52},{"id":"1905.01608","title":"PasteGAN: A Semi-Parametric Method to Generate Image from Scene Graph","created":"2019-05-05","cited_by_count":44},{"id":"2203.09773","title":"Local-Global Context Aware Transformer for Language-Guided Video Segmentation","created":"2022-03-18","cited_by_count":41},{"id":"1801.01450","title":"Quantifying Translation-Invariance in Convolutional Neural Networks","created":"2017-12-10","cited_by_count":30},{"id":"2009.02018","title":"TiVGAN: Text to Image to Video Generation with Step-by-Step Evolutionary Generator","created":"2020-09-04","cited_by_count":19},{"id":"1905.03743","title":"Interactive Image Generation Using Scene Graphs","created":"2019-05-09","cited_by_count":17},{"id":"2103.00221","title":"RA-GCN: Graph Convolutional Network for Disease Prediction Problems with Imbalanced Data","created":"2021-02-27","cited_by_count":14},{"id":"2107.04735","title":"Local-to-Global Self-Attention in Vision Transformers","created":"2021-07-10","cited_by_count":13},{"id":"1805.12301","title":"Rotation Equivariance and Invariance in Convolutional Neural Networks","created":"2018-05-31","cited_by_count":12}],"next_cursor":null}