{"list":"other","total":61,"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":"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":"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":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"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":"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":"2303.05499","title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","created":"2023-03-09","cited_by_count":3332},{"id":"2310.06825","title":"Mistral 7B","created":"2023-10-10","cited_by_count":3164},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"1503.03832","title":"FaceNet: A Unified Embedding for Face Recognition and Clustering","created":"2015-03-12","cited_by_count":2849},{"id":"1311.3618","title":"Describing Textures in the Wild","created":"2013-11-14","cited_by_count":2125},{"id":"1306.5151","title":"Fine-Grained Visual Classification of Aircraft","created":"2013-06-21","cited_by_count":1726},{"id":"1803.07728","title":"Unsupervised Representation Learning by Predicting Image Rotations","created":"2018-03-21","cited_by_count":1591},{"id":"1604.07379","title":"Context Encoders: Feature Learning by Inpainting","created":"2016-04-25","cited_by_count":1428},{"id":"2303.17760","title":"CAMEL: Communicative Agents for \"Mind\" Exploration of Large Language Model Society","created":"2023-03-31","cited_by_count":1395},{"id":"1603.09246","title":"Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles","created":"2016-03-30","cited_by_count":1382},{"id":"2102.08981","title":"Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts","created":"2021-02-17","cited_by_count":1216},{"id":"2401.14159","title":"Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks","created":"2024-01-25","cited_by_count":929},{"id":"1608.02192","title":"Playing for Data: Ground Truth from Computer Games","created":"2016-08-07","cited_by_count":818},{"id":"2311.17042","title":"Adversarial Diffusion Distillation","created":"2023-11-28","cited_by_count":759},{"id":"2301.13188","title":"Extracting Training Data from Diffusion Models","created":"2023-01-30","cited_by_count":732},{"id":"2109.12098","title":"CLIPort: What and Where Pathways for Robotic Manipulation","created":"2021-09-24","cited_by_count":622},{"id":"2211.05105","title":"Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Models","created":"2022-11-09","cited_by_count":513},{"id":"2112.12750","title":"SLIP: Self-supervision meets Language-Image Pre-training","created":"2021-12-23","cited_by_count":436},{"id":"1701.01370","title":"Learning from Synthetic Humans","created":"2017-01-05","cited_by_count":359},{"id":"2304.08466","title":"Synthetic Data from Diffusion Models Improves ImageNet Classification","created":"2023-04-17","cited_by_count":327},{"id":"2210.07574","title":"Is synthetic data from generative models ready for image recognition?","created":"2022-10-14","cited_by_count":320},{"id":"2309.16671","title":"Demystifying CLIP Data","created":"2023-09-28","cited_by_count":270},{"id":"2309.15025","title":"Large Language Model Alignment: A Survey","created":"2023-09-26","cited_by_count":243},{"id":"2305.20088","title":"Improving CLIP Training with Language Rewrites","created":"2023-05-31","cited_by_count":217},{"id":"2112.00374","title":"CLIPstyler: Image Style Transfer with a Single Text Condition","created":"2021-12-01","cited_by_count":203},{"id":"1610.01983","title":"Driving in the Matrix: Can Virtual Worlds Replace Human-Generated Annotations for Real World Tasks?","created":"2016-10-06","cited_by_count":194},{"id":"2306.00984","title":"StableRep: Synthetic Images from Text-to-Image Models Make Strong Visual Representation Learners","created":"2023-06-01","cited_by_count":177},{"id":"2212.08420","title":"Fake it till you make it: Learning transferable representations from synthetic ImageNet clones","created":"2022-12-16","cited_by_count":172},{"id":"2202.06675","title":"Can Machines Help Us Answering Question 16 in Datasheets, and In Turn Reflecting on Inappropriate Content?","created":"2022-02-14","cited_by_count":155},{"id":"1812.05040","title":"Learning Semantic Segmentation from Synthetic Data: A Geometrically Guided Input-Output Adaptation Approach","created":"2018-12-12","cited_by_count":119},{"id":"2312.04567","title":"Scaling Laws of Synthetic Images for Model Training ... for Now","created":"2023-12-07","cited_by_count":108},{"id":"2106.05258","title":"Generative Models as a Data Source for Multiview Representation Learning","created":"2021-06-09","cited_by_count":104},{"id":"2310.20550","title":"CapsFusion: Rethinking Image-Text Data at Scale","created":"2023-10-31","cited_by_count":90},{"id":"1807.09499","title":"How good is my GAN?","created":"2018-07-25","cited_by_count":74},{"id":"2312.17742","title":"Learning Vision from Models Rivals Learning Vision from Data","created":"2023-12-28","cited_by_count":71},{"id":"2112.09924","title":"The Web Is Your Oyster - Knowledge-Intensive NLP against a Very Large Web Corpus","created":"2021-12-18","cited_by_count":60},{"id":"2111.01177","title":"Don't Generate Me: Training Differentially Private Generative Models with Sinkhorn Divergence","created":"2021-11-01","cited_by_count":54},{"id":"2310.10640","title":"LLM Blueprint: Enabling Text-to-Image Generation with Complex and Detailed Prompts","created":"2023-10-16","cited_by_count":54},{"id":"2305.15316","title":"Training on Thin Air: Improve Image Classification with Generated Data","created":"2023-05-24","cited_by_count":50},{"id":"1912.09257","title":"Generating Synthetic Audio Data for Attention-Based Speech Recognition Systems","created":"2019-12-19","cited_by_count":47},{"id":"2311.14284","title":"Paragraph-to-Image Generation with Information-Enriched Diffusion Model","created":"2023-11-24","cited_by_count":39},{"id":"2310.10402","title":"Real-Fake: Effective Training Data Synthesis Through Distribution Matching","created":"2023-10-16","cited_by_count":36},{"id":"2212.13563","title":"Noise-aware Learning from Web-crawled Image-Text Data for Image Captioning","created":"2022-12-27","cited_by_count":22},{"id":"2302.14051","title":"Internet Explorer: Targeted Representation Learning on the Open Web","created":"2023-02-27","cited_by_count":21},{"id":"2305.08675","title":"Improved baselines for vision-language pre-training","created":"2023-05-15","cited_by_count":20},{"id":"2312.02253","title":"Diversify, Don't Fine-Tune: Scaling Up Visual Recognition Training with Synthetic Images","created":"2023-12-04","cited_by_count":20}],"next_cursor":null}