{"list":"other","total":78,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"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":"2206.00364","title":"Elucidating the Design Space of Diffusion-Based Generative Models","created":"2022-06-01","cited_by_count":3045},{"id":"2208.01626","title":"Prompt-to-Prompt Image Editing with Cross Attention Control","created":"2022-08-02","cited_by_count":2431},{"id":"2004.10934","title":"YOLOv4: Optimal Speed and Accuracy of Object Detection","created":"2020-04-23","cited_by_count":1630},{"id":"2203.05557","title":"Conditional Prompt Learning for Vision-Language Models","created":"2022-03-10","cited_by_count":1433},{"id":"1906.07155","title":"MMDetection: Open MMLab Detection Toolbox and Benchmark","created":"2019-06-17","cited_by_count":1385},{"id":"2111.05826","title":"Palette: Image-to-Image Diffusion Models","created":"2021-11-10","cited_by_count":1300},{"id":"1908.03195","title":"LVIS: A Dataset for Large Vocabulary Instance Segmentation","created":"2019-08-08","cited_by_count":1217},{"id":"2212.04488","title":"Multi-Concept Customization of Text-to-Image Diffusion","created":"2022-12-08","cited_by_count":1106},{"id":"1911.09070","title":"EfficientDet: Scalable and Efficient Object Detection","created":"2019-11-20","cited_by_count":1020},{"id":"2104.13921","title":"Open-vocabulary Object Detection via Vision and Language Knowledge Distillation","created":"2021-04-28","cited_by_count":906},{"id":"1511.02283","title":"Generation and Comprehension of Unambiguous Object Descriptions","created":"2015-11-07","cited_by_count":904},{"id":"2304.00685","title":"Vision-Language Models for Vision Tasks: A Survey","created":"2023-04-03","cited_by_count":839},{"id":"1608.02192","title":"Playing for Data: Ground Truth from Computer Games","created":"2016-08-07","cited_by_count":818},{"id":"2201.03546","title":"Language-driven Semantic Segmentation","created":"2022-01-10","cited_by_count":717},{"id":"2301.13826","title":"Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models","created":"2023-01-31","cited_by_count":702},{"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":"2012.07177","title":"Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation","created":"2020-12-13","cited_by_count":596},{"id":"1811.00982","title":"The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale","created":"2018-11-02","cited_by_count":544},{"id":"2302.03027","title":"Zero-shot Image-to-Image Translation","created":"2023-02-06","cited_by_count":505},{"id":"2112.12143","title":"Scaling Open-Vocabulary Image Segmentation with Image-Level Labels","created":"2021-12-22","cited_by_count":473},{"id":"2011.10678","title":"Open-Vocabulary Object Detection Using Captions","created":"2020-11-20","cited_by_count":427},{"id":"2007.10740","title":"Balanced Meta-Softmax for Long-Tailed Visual Recognition","created":"2020-07-21","cited_by_count":400},{"id":"2203.14940","title":"Learning to Prompt for Open-Vocabulary Object Detection with Vision-Language Model","created":"2022-03-28","cited_by_count":317},{"id":"2205.06230","title":"Simple Open-Vocabulary Object Detection with Vision Transformers","created":"2022-05-12","cited_by_count":305},{"id":"2003.05176","title":"Equalization Loss for Long-Tailed Object Recognition","created":"2020-03-11","cited_by_count":285},{"id":"2307.10816","title":"BoxDiff: Text-to-Image Synthesis with Training-Free Box-Constrained Diffusion","created":"2023-07-20","cited_by_count":282},{"id":"2211.12860","title":"DETRs with Collaborative Hybrid Assignments Training","created":"2022-11-22","cited_by_count":274},{"id":"2104.06490","title":"DatasetGAN: Efficient Labeled Data Factory with Minimal Human Effort","created":"2021-04-13","cited_by_count":264},{"id":"2203.11876","title":"Open-Vocabulary DETR with Conditional Matching","created":"2022-03-22","cited_by_count":220},{"id":"1708.01642","title":"Cut, Paste and Learn: Surprisingly Easy Synthesis for Instance Detection","created":"2017-08-04","cited_by_count":209},{"id":"2302.12228","title":"Encoder-based Domain Tuning for Fast Personalization of Text-to-Image Models","created":"2023-02-23","cited_by_count":203},{"id":"2103.16370","title":"Distribution Alignment: A Unified Framework for Long-tail Visual Recognition","created":"2021-03-30","cited_by_count":198},{"id":"1905.12886","title":"iSAID: A Large-scale Dataset for Instance Segmentation in Aerial Images","created":"2019-05-30","cited_by_count":197},{"id":"2306.15880","title":"Towards Open Vocabulary Learning: A Survey","created":"2023-06-28","cited_by_count":166},{"id":"2306.05427","title":"Grounded Text-to-Image Synthesis with Attention Refocusing","created":"2023-06-08","cited_by_count":164},{"id":"2006.10408","title":"Overcoming Classifier Imbalance for Long-tail Object Detection with Balanced Group Softmax","created":"2020-06-18","cited_by_count":152},{"id":"2008.10032","title":"Seesaw Loss for Long-Tailed Instance Segmentation","created":"2020-08-23","cited_by_count":146},{"id":"2207.03482","title":"Bridging the Gap between Object and Image-level Representations for Open-Vocabulary Detection","created":"2022-07-07","cited_by_count":146},{"id":"2103.07461","title":"Probabilistic two-stage detection","created":"2021-03-12","cited_by_count":130},{"id":"2002.10826","title":"Deep Representation Learning on Long-tailed Data: A Learnable Embedding Augmentation Perspective","created":"2020-02-25","cited_by_count":120},{"id":"2106.02637","title":"Aligning Pretraining for Detection via Object-Level Contrastive Learning","created":"2021-06-04","cited_by_count":110},{"id":"2007.11978","title":"The Devil is in Classification: A Simple Framework for Long-tail Object Detection and Instance Segmentation","created":"2020-07-23","cited_by_count":108},{"id":"1807.07428","title":"Modeling Visual Context is Key to Augmenting Object Detection Datasets","created":"2018-07-19","cited_by_count":106},{"id":"2006.10645","title":"Online Deep Clustering for Unsupervised Representation Learning","created":"2020-06-18","cited_by_count":100},{"id":"2012.08548","title":"Equalization Loss v2: A New Gradient Balance Approach for Long-tailed Object Detection","created":"2020-12-15","cited_by_count":99},{"id":"2201.04684","title":"BigDatasetGAN: Synthesizing ImageNet with Pixel-wise Annotations","created":"2022-01-12","cited_by_count":99},{"id":"1908.07801","title":"InstaBoost: Boosting Instance Segmentation via Probability Map Guided Copy-Pasting","created":"2019-08-21","cited_by_count":95},{"id":"1505.05641","title":"Render for CNN: Viewpoint Estimation in Images Using CNNs Trained with Rendered 3D Model Views","created":"2015-05-21","cited_by_count":94},{"id":"1511.03296","title":"The Fast Bilateral Solver","created":"2015-11-10","cited_by_count":87},{"id":"2304.03752","title":"V3Det: Vast Vocabulary Visual Detection Dataset","created":"2023-04-07","cited_by_count":81},{"id":"2102.12867","title":"FASA: Feature Augmentation and Sampling Adaptation for Long-Tailed Instance Segmentation","created":"2021-02-25","cited_by_count":76},{"id":"2106.11952","title":"Unsupervised Object-Level Representation Learning from Scene Images","created":"2021-06-22","cited_by_count":72},{"id":"2111.09452","title":"Open Vocabulary Object Detection with Pseudo Bounding-Box Labels","created":"2021-11-18","cited_by_count":71},{"id":"2104.00885","title":"Adaptive Class Suppression Loss for Long-Tail Object Detection","created":"2021-04-02","cited_by_count":55},{"id":"2004.00900","title":"Learning to Segment the Tail","created":"2020-04-02","cited_by_count":54},{"id":"1710.10710","title":"On Pre-Trained Image Features and Synthetic Images for Deep Learning","created":"2017-10-29","cited_by_count":51},{"id":"2212.03863","title":"X-Paste: Revisiting Scalable Copy-Paste for Instance Segmentation using CLIP and StableDiffusion","created":"2022-12-07","cited_by_count":49},{"id":"2008.05676","title":"Forest R-CNN: Large-Vocabulary Long-Tailed Object Detection and Instance Segmentation","created":"2020-08-13","cited_by_count":41},{"id":"2008.11702","title":"Delving into Inter-Image Invariance for Unsupervised Visual Representations","created":"2020-08-26","cited_by_count":37},{"id":"2102.08884","title":"MosaicOS: A Simple and Effective Use of Object-Centric Images for Long-Tailed Object Detection","created":"2021-02-17","cited_by_count":33},{"id":"2206.11134","title":"Open Vocabulary Object Detection with Proposal Mining and Prediction Equalization","created":"2022-06-22","cited_by_count":23},{"id":"2009.01559","title":"1st Place Solution of LVIS Challenge 2020: A Good Box is not a Guarantee of a Good Mask","created":"2020-09-03","cited_by_count":15}],"next_cursor":null}