{"list":"other","total":64,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"id":"2307.01952","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","created":"2023-07-04","cited_by_count":4356},{"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":"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":"2104.08718","title":"CLIPScore: A Reference-free Evaluation Metric for Image Captioning","created":"2021-04-18","cited_by_count":2424},{"id":"1505.04870","title":"Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models","created":"2015-05-19","cited_by_count":1362},{"id":"1908.03195","title":"LVIS: A Dataset for Large Vocabulary Instance Segmentation","created":"2019-08-08","cited_by_count":1217},{"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":"2112.03857","title":"Grounded Language-Image Pre-training","created":"2021-12-07","cited_by_count":1156},{"id":"2305.01569","title":"Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation","created":"2023-05-02","cited_by_count":977},{"id":"2104.13921","title":"Open-vocabulary Object Detection via Vision and Language Knowledge Distillation","created":"2021-04-28","cited_by_count":906},{"id":"2306.09341","title":"Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis","created":"2023-06-15","cited_by_count":890},{"id":"2104.12763","title":"MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding","created":"2021-04-26","cited_by_count":819},{"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":"2304.14108","title":"DataComp: In search of the next generation of multimodal datasets","created":"2023-04-27","cited_by_count":644},{"id":"2112.09106","title":"RegionCLIP: Region-based Language-Image Pretraining","created":"2021-12-16","cited_by_count":616},{"id":"2201.02605","title":"Detecting Twenty-thousand Classes using Image-level Supervision","created":"2022-01-07","cited_by_count":614},{"id":"2210.01936","title":"When and why vision-language models behave like bags-of-words, and what to do about it?","created":"2022-10-04","cited_by_count":610},{"id":"1802.10349","title":"Learning to Adapt Structured Output Space for Semantic Segmentation","created":"2018-02-28","cited_by_count":584},{"id":"2204.03162","title":"Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality","created":"2022-04-07","cited_by_count":529},{"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":"2307.06350","title":"T2I-CompBench++: An Enhanced and Comprehensive Benchmark for Compositional Text-to-image Generation","created":"2023-07-12","cited_by_count":260},{"id":"2007.04954","title":"ThreeDWorld: A Platform for Interactive Multi-Modal Physical Simulation","created":"2020-07-09","cited_by_count":250},{"id":"2306.14610","title":"SugarCrepe: Fixing Hackable Benchmarks for Vision-Language Compositionality","created":"2023-06-26","cited_by_count":243},{"id":"2212.07796","title":"CREPE: Can Vision-Language Foundation Models Reason Compositionally?","created":"2022-12-13","cited_by_count":181},{"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":"2109.06165","title":"CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptation","created":"2021-09-13","cited_by_count":129},{"id":"2003.08040","title":"Differential Treatment for Stuff and Things: A Simple Unsupervised Domain Adaptation Method for Semantic Segmentation","created":"2020-03-18","cited_by_count":126},{"id":"2308.06160","title":"DatasetDM: Synthesizing Data with Perception Annotations Using Diffusion Models","created":"2023-08-11","cited_by_count":123},{"id":"2207.00221","title":"VL-CheckList: Evaluating Pre-trained Vision-Language Models with Objects, Attributes and Relations","created":"2022-07-01","cited_by_count":114},{"id":"2309.14303","title":"Dataset Diffusion: Diffusion-based Synthetic Dataset Generation for Pixel-Level Semantic Segmentation","created":"2023-09-25","cited_by_count":112},{"id":"2206.07643","title":"Coarse-to-Fine Vision-Language Pre-training with Fusion in the Backbone","created":"2022-06-15","cited_by_count":109},{"id":"2312.04567","title":"Scaling Laws of Synthetic Images for Model Training ... for Now","created":"2023-12-07","cited_by_count":108},{"id":"2008.08574","title":"Every Pixel Matters: Center-aware Feature Alignment for Domain Adaptive Object Detector","created":"2020-08-19","cited_by_count":107},{"id":"1810.10093","title":"Structured Domain Randomization: Bridging the Reality Gap by Context-Aware Synthetic Data","created":"2018-10-23","cited_by_count":94},{"id":"2305.07011","title":"Region-Aware Pretraining for Open-Vocabulary Object Detection with Vision Transformers","created":"2023-05-11","cited_by_count":91},{"id":"2105.03519","title":"Understanding by Understanding Not: Modeling Negation in Language Models","created":"2021-05-07","cited_by_count":73},{"id":"2305.19595","title":"Dense and Aligned Captions (DAC) Promote Compositional Reasoning in VL Models","created":"2023-05-31","cited_by_count":72},{"id":"2211.11733","title":"Teaching Structured Vision&Language Concepts to Vision&Language Models","created":"2022-11-21","cited_by_count":71},{"id":"2312.17742","title":"Learning Vision from Models Rivals Learning Vision from Data","created":"2023-12-28","cited_by_count":71},{"id":"2307.12813","title":"Described Object Detection: Liberating Object Detection with Flexible Expressions","created":"2023-07-24","cited_by_count":40},{"id":"2303.13221","title":"Explore the Power of Synthetic Data on Few-shot Object Detection","created":"2023-03-23","cited_by_count":38},{"id":"2309.13042","title":"MosaicFusion: Diffusion Models as Data Augmenters for Large Vocabulary Instance Segmentation","created":"2023-09-22","cited_by_count":35},{"id":"2112.00054","title":"Task2Sim : Towards Effective Pre-training and Transfer from Synthetic Data","created":"2021-11-30","cited_by_count":26},{"id":"2306.14060","title":"DesCo: Learning Object Recognition with Rich Language Descriptions","created":"2023-06-24","cited_by_count":25},{"id":"2110.04111","title":"Discover, Hallucinate, and Adapt: Open Compound Domain Adaptation for Semantic Segmentation","created":"2021-10-08","cited_by_count":24},{"id":"2107.11052","title":"Unsupervised Domain Adaptation for Video Semantic Segmentation","created":"2021-07-23","cited_by_count":9},{"id":"2212.08355","title":"Learning Classifiers of Prototypes and Reciprocal Points for Universal Domain Adaptation","created":"2022-12-16","cited_by_count":8},{"id":"2212.10147","title":"Bridging Images and Videos: A Simple Learning Framework for Large Vocabulary Video Object Detection","created":"2022-12-20","cited_by_count":6}],"next_cursor":null}