{"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":"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":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864},{"id":"2201.05989","title":"Instant Neural Graphics Primitives with a Multiresolution Hash Encoding","created":"2022-01-16","cited_by_count":3723},{"id":"1912.04958","title":"Analyzing and Improving the Image Quality of StyleGAN","created":"2019-12-03","cited_by_count":3588},{"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":"2006.16241","title":"The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization","created":"2020-06-29","cited_by_count":1850},{"id":"2203.05557","title":"Conditional Prompt Learning for Vision-Language Models","created":"2022-03-10","cited_by_count":1433},{"id":"2302.08453","title":"T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models","created":"2023-02-16","cited_by_count":1351},{"id":"2004.06165","title":"Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks","created":"2020-04-13","cited_by_count":1214},{"id":"1412.2306","title":"Deep Visual-Semantic Alignments for Generating Image Descriptions","created":"2014-12-07","cited_by_count":968},{"id":"2210.03117","title":"MaPLe: Multi-modal Prompt Learning","created":"2022-10-06","cited_by_count":687},{"id":"1812.07119","title":"Composing Text and Image for Image Retrieval - An Empirical Odyssey","created":"2018-12-18","cited_by_count":236},{"id":"2211.13752","title":"Sketch-Guided Text-to-Image Diffusion Models","created":"2022-11-24","cited_by_count":180},{"id":"2303.15247","title":"Zero-Shot Composed Image Retrieval with Textual Inversion","created":"2023-03-27","cited_by_count":176},{"id":"2211.14813","title":"SegCLIP: Patch Aggregation with Learnable Centers for Open-Vocabulary Semantic Segmentation","created":"2022-11-27","cited_by_count":164},{"id":"2302.03084","title":"Pic2Word: Mapping Pictures to Words for Zero-shot Composed Image Retrieval","created":"2023-02-06","cited_by_count":156},{"id":"1909.05506","title":"CAMP: Cross-Modal Adaptive Message Passing for Text-Image Retrieval","created":"2019-09-12","cited_by_count":110},{"id":"2204.01694","title":"\"This is my unicorn, Fluffy\": Personalizing frozen vision-language representations","created":"2022-04-04","cited_by_count":95},{"id":"2203.12691","title":"Learning to generate line drawings that convey geometry and semantics","created":"2022-03-23","cited_by_count":83},{"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":"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":"2210.01115","title":"LASP: Text-to-Text Optimization for Language-Aware Soft Prompting of Vision & Language Models","created":"2022-10-03","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":"1711.08389","title":"Conditional Image-Text Embedding Networks","created":"2017-11-22","cited_by_count":50},{"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":"2001.02890","title":"Deep Plastic Surgery: Robust and Controllable Image Editing with Human-Drawn Sketches","created":"2020-01-09","cited_by_count":37},{"id":"1607.07295","title":"Learning Aligned Cross-Modal Representations from Weakly Aligned Data","created":"2016-07-25","cited_by_count":34},{"id":"1904.06611","title":"LiveSketch: Query Perturbations for Guided Sketch-based Visual Search","created":"2019-04-14","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":"2207.08150","title":"FashionViL: Fashion-Focused Vision-and-Language Representation Learning","created":"2022-07-17","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":"2203.14804","title":"Partially Does It: Towards Scene-Level FG-SBIR with Partial Input","created":"2022-03-28","cited_by_count":20},{"id":"2207.01723","title":"Adaptive Fine-Grained Sketch-Based Image Retrieval","created":"2022-07-04","cited_by_count":15},{"id":"1608.07973","title":"Linking Image and Text with 2-Way Nets","created":"2016-08-29","cited_by_count":14},{"id":"2203.09554","title":"CoGS: Controllable Generation and Search from Sketch and Style","created":"2022-03-17","cited_by_count":14},{"id":"2303.13779","title":"Exploiting Unlabelled Photos for Stronger Fine-Grained SBIR","created":"2023-03-24","cited_by_count":14},{"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}