{"list":"other","total":63,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"2006.07733","title":"Bootstrap your own latent: A new approach to self-supervised Learning","created":"2020-06-13","cited_by_count":4750},{"id":"2003.04297","title":"Improved Baselines with Momentum Contrastive Learning","created":"2020-03-09","cited_by_count":2287},{"id":"1703.06868","title":"Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization","created":"2017-03-20","cited_by_count":2010},{"id":"1904.01355","title":"FCOS: Fully Convolutional One-Stage Object Detection","created":"2019-04-02","cited_by_count":1577},{"id":"1607.08022","title":"Instance Normalization: The Missing Ingredient for Fast Stylization","created":"2016-07-27","cited_by_count":1198},{"id":"2112.03857","title":"Grounded Language-Image Pre-training","created":"2021-12-07","cited_by_count":1156},{"id":"2104.13921","title":"Open-vocabulary Object Detection via Vision and Language Knowledge Distillation","created":"2021-04-28","cited_by_count":906},{"id":"2203.16527","title":"Exploring Plain Vision Transformer Backbones for Object Detection","created":"2022-03-30","cited_by_count":724},{"id":"1711.10398","title":"DOTA: A Large-scale Dataset for Object Detection in Aerial Images","created":"2017-11-28","cited_by_count":623},{"id":"1912.02424","title":"Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection","created":"2019-12-05","cited_by_count":540},{"id":"2011.10678","title":"Open-Vocabulary Object Detection Using Captions","created":"2020-11-20","cited_by_count":427},{"id":"2006.06666","title":"VirTex: Learning Visual Representations from Textual Annotations","created":"2020-06-11","cited_by_count":339},{"id":"2003.13216","title":"Learning to Learn Single Domain Generalization","created":"2020-03-30","cited_by_count":296},{"id":"2007.03304","title":"Learning to Generate Novel Domains for Domain Generalization","created":"2020-07-07","cited_by_count":296},{"id":"2206.05836","title":"GLIPv2: Unifying Localization and Vision-Language Understanding","created":"2022-06-12","cited_by_count":275},{"id":"2105.06086","title":"HINet: Half Instance Normalization Network for Image Restoration","created":"2021-05-13","cited_by_count":237},{"id":"2108.05699","title":"Oriented R-CNN for Object Detection","created":"2021-08-12","cited_by_count":231},{"id":"2006.07500","title":"Domain Generalization using Causal Matching","created":"2020-06-12","cited_by_count":225},{"id":"2103.15597","title":"RobustNet: Improving Domain Generalization in Urban-Scene Segmentation via Instance Selective Whitening","created":"2021-03-29","cited_by_count":215},{"id":"2102.12219","title":"Object Detection in Aerial Images: A Large-Scale Benchmark and Challenges","created":"2021-02-24","cited_by_count":204},{"id":"2103.07733","title":"ReDet: A Rotation-equivariant Detector for Aerial Object Detection","created":"2021-03-13","cited_by_count":203},{"id":"2112.00374","title":"CLIPstyler: Image Style Transfer with a Single Text Condition","created":"2021-12-01","cited_by_count":203},{"id":"1908.05612","title":"R3Det: Refined Single-Stage Detector with Feature Refinement for Rotating Object","created":"2019-08-15","cited_by_count":194},{"id":"2008.09397","title":"Align Deep Features for Oriented Object Detection","created":"2020-08-21","cited_by_count":187},{"id":"2006.09214","title":"FCOS: A simple and strong anchor-free object detector","created":"2020-06-14","cited_by_count":171},{"id":"2101.11952","title":"Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Loss","created":"2021-01-28","cited_by_count":156},{"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":"2103.05569","title":"FAIR1M: A Benchmark Dataset for Fine-grained Object Recognition in High-Resolution Remote Sensing Imagery","created":"2021-03-09","cited_by_count":143},{"id":"2003.12815","title":"Efficient Domain Generalization via Common-Specific Low-Rank Decomposition","created":"2020-03-28","cited_by_count":134},{"id":"2106.01883","title":"Learning High-Precision Bounding Box for Rotated Object Detection via Kullback-Leibler Divergence","created":"2021-06-03","cited_by_count":130},{"id":"2008.12839","title":"Learning to Balance Specificity and Invariance for In and Out of Domain Generalization","created":"2020-08-28","cited_by_count":128},{"id":"2111.13216","title":"Cross-Domain Adaptive Teacher for Object Detection","created":"2021-11-25","cited_by_count":126},{"id":"2207.14096","title":"Towards Large-Scale Small Object Detection: Survey and Benchmarks","created":"2022-07-28","cited_by_count":122},{"id":"2007.09316","title":"Learning from Extrinsic and Intrinsic Supervisions for Domain Generalization","created":"2020-07-18","cited_by_count":108},{"id":"2105.11111","title":"Oriented RepPoints for Aerial Object Detection","created":"2021-05-24","cited_by_count":102},{"id":"2301.05499","title":"CLIP the Gap: A Single Domain Generalization Approach for Object Detection","created":"2023-01-13","cited_by_count":87},{"id":"2011.09670","title":"Dense Label Encoding for Boundary Discontinuity Free Rotation Detection","created":"2020-11-19","cited_by_count":79},{"id":"2204.01446","title":"WildNet: Learning Domain Generalized Semantic Segmentation from the Wild","created":"2022-04-04","cited_by_count":76},{"id":"1911.08299","title":"Learning Modulated Loss for Rotated Object Detection","created":"2019-11-19","cited_by_count":73},{"id":"2201.12558","title":"The KFIoU Loss for Rotated Object Detection","created":"2022-01-29","cited_by_count":73},{"id":"2307.15199","title":"PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalization","created":"2023-07-27","cited_by_count":59},{"id":"2011.12672","title":"Batch Normalization Embeddings for Deep Domain Generalization","created":"2020-11-25","cited_by_count":57},{"id":"2303.07820","title":"Adaptive Rotated Convolution for Rotated Object Detection","created":"2023-03-14","cited_by_count":51},{"id":"2112.04764","title":"3D-VField: Adversarial Augmentation of Point Clouds for Domain Generalization in 3D Object Detection","created":"2021-12-09","cited_by_count":43},{"id":"2304.08876","title":"Dynamic Coarse-to-Fine Learning for Oriented Tiny Object Detection","created":"2023-04-18","cited_by_count":43},{"id":"2203.15345","title":"Task-specific Inconsistency Alignment for Domain Adaptive Object Detection","created":"2022-03-29","cited_by_count":38},{"id":"2112.02300","title":"Unsupervised Domain Generalization by Learning a Bridge Across Domains","created":"2021-12-04","cited_by_count":33},{"id":"2307.00371","title":"Learning Content-enhanced Mask Transformer for Domain Generalized Urban-Scene Segmentation","created":"2023-07-01","cited_by_count":30},{"id":"1804.01720","title":"Finding beans in burgers: Deep semantic-visual embedding with localization","created":"2018-04-05","cited_by_count":28},{"id":"2303.01686","title":"Towards Domain Generalization for Multi-view 3D Object Detection in Bird-Eye-View","created":"2023-03-03","cited_by_count":27},{"id":"2311.13930","title":"Periodically Exchange Teacher-Student for Source-Free Object Detection","created":"2023-11-23","cited_by_count":24},{"id":"2212.09068","title":"Style-Hallucinated Dual Consistency Learning: A Unified Framework for Visual Domain Generalization","created":"2022-12-18","cited_by_count":22},{"id":"2205.11796","title":"G-Rep: Gaussian Representation for Arbitrary-Oriented Object Detection","created":"2022-05-24","cited_by_count":20},{"id":"2207.09721","title":"Feature Representation Learning for Unsupervised Cross-domain Image Retrieval","created":"2022-07-20","cited_by_count":17},{"id":"1908.08156","title":"Multiple instance dense connected convolution neural network for aerial image scene classification","created":"2019-08-22","cited_by_count":15},{"id":"2304.02199","title":"Knowledge Combination to Learn Rotated Detection Without Rotated Annotation","created":"2023-04-05","cited_by_count":12},{"id":"2205.03371","title":"All Grains, One Scheme (AGOS): Learning Multi-grain Instance Representation for Aerial Scene Classification","created":"2022-05-06","cited_by_count":6},{"id":"2112.10474","title":"Reciprocal Normalization for Domain Adaptation","created":"2021-12-20","cited_by_count":3}],"next_cursor":null}