{"list":"other","total":64,"rows":[{"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":"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":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"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":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"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":"1502.01852","title":"Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification","created":"2015-02-06","cited_by_count":3611},{"id":"1310.4546","title":"Distributed Representations of Words and Phrases and their Compositionality","created":"2013-10-16","cited_by_count":3474},{"id":"2208.01626","title":"Prompt-to-Prompt Image Editing with Cross Attention Control","created":"2022-08-02","cited_by_count":2431},{"id":"2109.01134","title":"Learning to Prompt for Vision-Language Models","created":"2021-09-02","cited_by_count":2281},{"id":"2208.01618","title":"An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion","created":"2022-08-02","cited_by_count":2245},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"id":"2108.01073","title":"SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations","created":"2021-08-02","cited_by_count":1937},{"id":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681},{"id":"2111.02114","title":"LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs","created":"2021-11-03","cited_by_count":1555},{"id":"2203.05557","title":"Conditional Prompt Learning for Vision-Language Models","created":"2022-03-10","cited_by_count":1433},{"id":"1811.12231","title":"ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness","created":"2018-11-29","cited_by_count":1432},{"id":"2212.07143","title":"Reproducible scaling laws for contrastive language-image learning","created":"2022-12-14","cited_by_count":1173},{"id":"2106.15282","title":"Cascaded Diffusion Models for High Fidelity Image Generation","created":"2021-05-30","cited_by_count":1163},{"id":"2211.12572","title":"Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation","created":"2022-11-22","cited_by_count":906},{"id":"2105.13290","title":"CogView: Mastering Text-to-Image Generation via Transformers","created":"2021-05-26","cited_by_count":694},{"id":"2112.03126","title":"Label-Efficient Semantic Segmentation with Diffusion Models","created":"2021-12-06","cited_by_count":499},{"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":"2303.04803","title":"Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models","created":"2023-03-08","cited_by_count":375},{"id":"1704.03477","title":"A Neural Representation of Sketch Drawings","created":"2017-04-11","cited_by_count":313},{"id":"2203.17274","title":"Exploring Visual Prompts for Adapting Large-Scale Models","created":"2022-03-31","cited_by_count":274},{"id":"1804.10745","title":"Generalizing Across Domains via Cross-Gradient Training","created":"2018-04-28","cited_by_count":268},{"id":"1904.03451","title":"Doodle to Search: Practical Zero-Shot Sketch-based Image Retrieval","created":"2019-04-06","cited_by_count":79},{"id":"2303.13440","title":"CLIP for All Things Zero-Shot Sketch-Based Image Retrieval, Fine-Grained or Not","created":"2023-03-23","cited_by_count":79},{"id":"2002.10381","title":"Sketchformer: Transformer-based Representation for Sketched Structure","created":"2020-02-24","cited_by_count":78},{"id":"2303.10735","title":"SKED: Sketch-guided Text-based 3D Editing","created":"2023-03-19","cited_by_count":73},{"id":"1807.11724","title":"A Zero-Shot Framework for Sketch-based Image Retrieval","created":"2018-07-31","cited_by_count":71},{"id":"1703.05605","title":"Deep Sketch Hashing: Fast Free-hand Sketch-Based Image Retrieval","created":"2017-03-16","cited_by_count":68},{"id":"2003.02683","title":"SketchyCOCO: Image Generation from Freehand Scene Sketches","created":"2020-03-05","cited_by_count":67},{"id":"2002.10310","title":"Sketch Less for More: On-the-Fly Fine-Grained Sketch Based Image Retrieval","created":"2020-02-24","cited_by_count":59},{"id":"1903.03372","title":"Semantically Tied Paired Cycle Consistency for Zero-Shot Sketch-based Image Retrieval","created":"2019-03-08","cited_by_count":57},{"id":"2309.16779","title":"Intriguing properties of generative classifiers","created":"2023-09-28","cited_by_count":52},{"id":"2103.15706","title":"StyleMeUp: Towards Style-Agnostic Sketch-Based Image Retrieval","created":"2021-03-29","cited_by_count":50},{"id":"2203.02113","title":"FS-COCO: Towards Understanding of Freehand Sketches of Common Objects in Context","created":"2022-03-04","cited_by_count":49},{"id":"1904.03208","title":"Semantic-Aware Knowledge Preservation for Zero-Shot Sketch-Based Image Retrieval","created":"2019-04-05","cited_by_count":40},{"id":"2103.13990","title":"More Photos are All You Need: Semi-Supervised Learning for Fine-Grained Sketch Based Image Retrieval","created":"2021-03-25","cited_by_count":38},{"id":"2001.02890","title":"Deep Plastic Surgery: Robust and Controllable Image Editing with Human-Drawn Sketches","created":"2020-01-09","cited_by_count":37},{"id":"1804.01401","title":"SketchMate: Deep Hashing for Million-Scale Human Sketch Retrieval","created":"2018-04-04","cited_by_count":35},{"id":"1904.06611","title":"LiveSketch: Query Perturbations for Guided Sketch-based Visual Search","created":"2019-04-14","cited_by_count":34},{"id":"2203.14691","title":"Sketch3T: Test-Time Training for Zero-Shot SBIR","created":"2022-03-28","cited_by_count":34},{"id":"2303.11162","title":"Picture that Sketch: Photorealistic Image Generation from Abstract Sketches","created":"2023-03-20","cited_by_count":34},{"id":"2007.15103","title":"Cross-Modal Hierarchical Modelling for Fine-Grained Sketch Based Image Retrieval","created":"2020-07-29","cited_by_count":32},{"id":"2204.11964","title":"SceneTrilogy: On Human Scene-Sketch and its Complementarity with Photo and Text","created":"2022-04-25","cited_by_count":30},{"id":"2208.03354","title":"A Sketch Is Worth a Thousand Words: Image Retrieval with Text and Sketch","created":"2022-08-05","cited_by_count":28},{"id":"2203.14817","title":"Sketching without Worrying: Noise-Tolerant Sketch-Based Image Retrieval","created":"2022-03-28","cited_by_count":27},{"id":"2303.14348","title":"Zero-Shot Everything Sketch-Based Image Retrieval, and in Explainable Style","created":"2023-03-25","cited_by_count":25},{"id":"2012.04251","title":"Variational Interaction Information Maximization for Cross-domain Disentanglement","created":"2020-12-08","cited_by_count":23},{"id":"2203.14843","title":"Doodle It Yourself: Class Incremental Learning by Drawing a Few Sketches","created":"2022-03-28","cited_by_count":23},{"id":"2203.14804","title":"Partially Does It: Towards Scene-Level FG-SBIR with Partial Input","created":"2022-03-28","cited_by_count":20},{"id":"2303.13430","title":"Medical diffusion on a budget: Textual Inversion for medical image generation","created":"2023-03-23","cited_by_count":20},{"id":"2207.01723","title":"Adaptive Fine-Grained Sketch-Based Image Retrieval","created":"2022-07-04","cited_by_count":15},{"id":"2303.13779","title":"Exploiting Unlabelled Photos for Stronger Fine-Grained SBIR","created":"2023-03-24","cited_by_count":14},{"id":"2312.04364","title":"DemoCaricature: Democratising Caricature Generation with a Rough Sketch","created":"2023-12-07","cited_by_count":10},{"id":"2403.07203","title":"How to Handle Sketch-Abstraction in Sketch-Based Image Retrieval?","created":"2024-03-11","cited_by_count":10}],"next_cursor":null}