{"list":"other","total":53,"rows":[{"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":"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1503.03585","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","created":"2015-03-12","cited_by_count":7058},{"id":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"id":"1312.6114","title":"Auto-Encoding Variational Bayes","created":"2013-12-20","cited_by_count":4053},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"1802.02611","title":"Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation","created":"2018-02-07","cited_by_count":3223},{"id":"2212.10560","title":"Self-Instruct: Aligning Language Models with Self-Generated Instructions","created":"2022-12-20","cited_by_count":2724},{"id":"2303.12712","title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","created":"2023-03-22","cited_by_count":2592},{"id":"2208.01626","title":"Prompt-to-Prompt Image Editing with Cross Attention Control","created":"2022-08-02","cited_by_count":2431},{"id":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"id":"1606.04797","title":"V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation","created":"2016-06-15","cited_by_count":2292},{"id":"1902.09212","title":"Deep High-Resolution Representation Learning for Human Pose Estimation","created":"2019-02-25","cited_by_count":1339},{"id":"1406.2283","title":"Depth Map Prediction from a Single Image using a Multi-Scale Deep Network","created":"2014-06-09","cited_by_count":1274},{"id":"2305.05665","title":"ImageBind: One Embedding Space To Bind Them All","created":"2023-05-09","cited_by_count":1175},{"id":"2106.15282","title":"Cascaded Diffusion Models for High Fidelity Image Generation","created":"2021-05-30","cited_by_count":1163},{"id":"2107.06278","title":"Per-Pixel Classification is Not All You Need for Semantic Segmentation","created":"2021-07-13","cited_by_count":1152},{"id":"1410.8516","title":"NICE: Non-linear Independent Components Estimation","created":"2014-10-30","cited_by_count":1058},{"id":"2112.03126","title":"Label-Efficient Semantic Segmentation with Diffusion Models","created":"2021-12-06","cited_by_count":499},{"id":"2303.04803","title":"Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models","created":"2023-03-08","cited_by_count":375},{"id":"1812.02849","title":"A Survey of Unsupervised Deep Domain Adaptation","created":"2018-12-06","cited_by_count":361},{"id":"2001.10773","title":"Virtual KITTI 2","created":"2020-01-29","cited_by_count":353},{"id":"2302.09210","title":"How Good Are GPT Models at Machine Translation? A Comprehensive Evaluation","created":"2023-02-18","cited_by_count":348},{"id":"1605.06457","title":"Virtual Worlds as Proxy for Multi-Object Tracking Analysis","created":"2016-05-20","cited_by_count":341},{"id":"1604.05144","title":"ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentation","created":"2016-04-18","cited_by_count":331},{"id":"1803.10464","title":"Learning Pixel-level Semantic Affinity with Image-level Supervision for Weakly Supervised Semantic Segmentation","created":"2018-03-28","cited_by_count":321},{"id":"2210.07574","title":"Is synthetic data from generative models ready for image recognition?","created":"2022-10-14","cited_by_count":320},{"id":"2303.13516","title":"Ablating Concepts in Text-to-Image Diffusion Models","created":"2023-03-23","cited_by_count":317},{"id":"2212.11270","title":"Generalized Decoding for Pixel, Image, and Language","created":"2022-12-21","cited_by_count":294},{"id":"2104.06490","title":"DatasetGAN: Efficient Labeled Data Factory with Minimal Human Effort","created":"2021-04-13","cited_by_count":264},{"id":"1906.00817","title":"Zero-Shot Semantic Segmentation","created":"2019-06-03","cited_by_count":245},{"id":"2112.07910","title":"Decoupling Zero-Shot Semantic Segmentation","created":"2021-12-15","cited_by_count":199},{"id":"2303.11681","title":"DiffuMask: Synthesizing Images with Pixel-level Annotations for Semantic Segmentation Using Diffusion Models","created":"2023-03-21","cited_by_count":162},{"id":"2111.03186","title":"EditGAN: High-Precision Semantic Image Editing","created":"2021-11-04","cited_by_count":156},{"id":"2203.14211","title":"DepthFormer: Exploiting Long-Range Correlation and Local Information for Accurate Monocular Depth Estimation","created":"2022-03-27","cited_by_count":118},{"id":"2201.04684","title":"BigDatasetGAN: Synthesizing ImageNet with Pixel-wise Annotations","created":"2022-01-12","cited_by_count":99},{"id":"2008.06893","title":"Context-aware Feature Generation for Zero-shot Semantic Segmentation","created":"2020-08-16","cited_by_count":94},{"id":"2104.04465","title":"Bootstrapping Semantic Segmentation with Regional Contrast","created":"2021-04-09","cited_by_count":80},{"id":"2104.11692","title":"A Closer Look at Self-training for Zero-Label Semantic Segmentation","created":"2021-04-21","cited_by_count":57},{"id":"2108.06536","title":"Exploiting a Joint Embedding Space for Generalized Zero-Shot Semantic Segmentation","created":"2021-08-14","cited_by_count":53},{"id":"2108.12517","title":"SIGN: Spatial-information Incorporated Generative Network for Generalized Zero-shot Semantic Segmentation","created":"2021-08-27","cited_by_count":41},{"id":"2304.04106","title":"MedGen3D: A Deep Generative Framework for Paired 3D Image and Mask Generation","created":"2023-04-08","cited_by_count":34},{"id":"2307.09756","title":"Generative Prompt Model for Weakly Supervised Object Localization","created":"2023-07-19","cited_by_count":20},{"id":"2210.13835","title":"Synthetic Data Supervised Salient Object Detection","created":"2022-10-25","cited_by_count":15},{"id":"2203.10674","title":"RareGAN: Generating Samples for Rare Classes","created":"2022-03-20","cited_by_count":9},{"id":"2212.12645","title":"HandsOff: Labeled Dataset Generation With No Additional Human Annotations","created":"2022-12-24","cited_by_count":9},{"id":"2003.08526","title":"Pose Augmentation: Class-agnostic Object Pose Transformation for Object Recognition","created":"2020-03-19","cited_by_count":6},{"id":"2106.10309","title":"Towards Single Stage Weakly Supervised Semantic Segmentation","created":"2021-06-18","cited_by_count":5}],"next_cursor":null}