{"list":"other","total":73,"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":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"2111.02114","title":"LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs","created":"2021-11-03","cited_by_count":1555},{"id":"2203.05557","title":"Conditional Prompt Learning for Vision-Language Models","created":"2022-03-10","cited_by_count":1433},{"id":"1612.08242","title":"YOLO9000: Better, Faster, Stronger","created":"2016-12-25","cited_by_count":1431},{"id":"1805.04687","title":"BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning","created":"2018-05-12","cited_by_count":1288},{"id":"1908.03195","title":"LVIS: A Dataset for Large Vocabulary Instance Segmentation","created":"2019-08-08","cited_by_count":1217},{"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":"2304.00685","title":"Vision-Language Models for Vision Tasks: A Survey","created":"2023-04-03","cited_by_count":839},{"id":"2111.11432","title":"Florence: A New Foundation Model for Computer Vision","created":"2021-11-22","cited_by_count":804},{"id":"2103.02503","title":"Domain Generalization: A Survey","created":"2021-03-03","cited_by_count":764},{"id":"2201.03546","title":"Language-driven Semantic Segmentation","created":"2022-01-10","cited_by_count":717},{"id":"1802.03601","title":"Deep Visual Domain Adaptation: A Survey","created":"2018-02-10","cited_by_count":635},{"id":"2201.02605","title":"Detecting Twenty-thousand Classes using Image-level Supervision","created":"2022-01-07","cited_by_count":614},{"id":"2104.10972","title":"ImageNet-21K Pretraining for the Masses","created":"2021-04-22","cited_by_count":613},{"id":"2011.10678","title":"Open-Vocabulary Object Detection Using Captions","created":"2020-11-20","cited_by_count":427},{"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":"2005.04757","title":"A Simple Semi-Supervised Learning Framework for Object Detection","created":"2020-05-10","cited_by_count":282},{"id":"2206.05836","title":"GLIPv2: Unifying Localization and Vision-Language Understanding","created":"2022-06-12","cited_by_count":275},{"id":"2101.10979","title":"Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentation","created":"2021-01-26","cited_by_count":268},{"id":"2203.11876","title":"Open-Vocabulary DETR with Conditional Matching","created":"2022-03-22","cited_by_count":220},{"id":"1804.00518","title":"The Unmanned Aerial Vehicle Benchmark: Object Detection and Tracking","created":"2018-03-26","cited_by_count":208},{"id":"2103.16370","title":"Distribution Alignment: A Unified Framework for Long-tail Visual Recognition","created":"2021-03-30","cited_by_count":198},{"id":"1804.04340","title":"Zero-Shot Object Detection","created":"2018-04-12","cited_by_count":189},{"id":"1511.02853","title":"Weakly Supervised Deep Detection Networks","created":"2015-11-09","cited_by_count":183},{"id":"2209.09407","title":"DetCLIP: Dictionary-Enriched Visual-Concept Paralleled Pre-training for Open-world Detection","created":"2022-09-20","cited_by_count":176},{"id":"2103.02370","title":"FSDR: Frequency Space Domain Randomization for Domain Generalization","created":"2021-03-03","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":"2110.03374","title":"Model Adaptation: Historical Contrastive Learning for Unsupervised Domain Adaptation without Source Data","created":"2021-10-07","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":"2102.13086","title":"Simple multi-dataset detection","created":"2021-02-25","cited_by_count":127},{"id":"1704.00138","title":"Multiple Instance Detection Network with Online Instance Classifier Refinement","created":"2017-04-01","cited_by_count":117},{"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":"1511.04136","title":"UA-DETRAC: A New Benchmark and Protocol for Multi-Object Detection and Tracking","created":"2015-11-13","cited_by_count":98},{"id":"1807.03342","title":"PCL: Proposal Cluster Learning for Weakly Supervised Object Detection","created":"2018-07-09","cited_by_count":97},{"id":"1904.05647","title":"C-MIL: Continuation Multiple Instance Learning for Weakly Supervised Object Detection","created":"2019-04-11","cited_by_count":71},{"id":"2106.02885","title":"Category Contrast for Unsupervised Domain Adaptation in Visual Tasks","created":"2021-06-05","cited_by_count":65},{"id":"2109.15163","title":"HSVA: Hierarchical Semantic-Visual Adaptation for Zero-Shot Learning","created":"2021-09-30","cited_by_count":57},{"id":"2108.07507","title":"Exploring Classification Equilibrium in Long-Tailed Object Detection","created":"2021-08-17","cited_by_count":51},{"id":"2010.12023","title":"Comprehensive Attention Self-Distillation for Weakly-Supervised Object Detection","created":"2020-10-22","cited_by_count":50},{"id":"2106.02874","title":"RDA: Robust Domain Adaptation via Fourier Adversarial Attacking","created":"2021-06-05","cited_by_count":48},{"id":"2010.01653","title":"An Empirical Study on Large-Scale Multi-Label Text Classification Including Few and Zero-Shot Labels","created":"2020-10-04","cited_by_count":44},{"id":"2106.11118","title":"SODA10M: A Large-Scale 2D Self/Semi-Supervised Object Detection Dataset for Autonomous Driving","created":"2021-06-21","cited_by_count":43},{"id":"1911.12148","title":"Towards Precise End-to-end Weakly Supervised Object Detection Network","created":"2019-11-27","cited_by_count":41},{"id":"2008.05402","title":"DAWN: Vehicle Detection in Adverse Weather Nature Dataset","created":"2020-08-12","cited_by_count":41},{"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":"2103.02584","title":"Cross-View Regularization for Domain Adaptive Panoptic Segmentation","created":"2021-03-03","cited_by_count":41},{"id":"2106.06112","title":"Spectral Unsupervised Domain Adaptation for Visual Recognition","created":"2021-06-11","cited_by_count":40},{"id":"2107.02170","title":"On Model Calibration for Long-Tailed Object Detection and Instance Segmentation","created":"2021-07-05","cited_by_count":39},{"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":"2007.07986","title":"Boosting Weakly Supervised Object Detection with Progressive Knowledge Transfer","created":"2020-07-15","cited_by_count":28},{"id":"2104.05702","title":"Image-Level or Object-Level? A Tale of Two Resampling Strategies for Long-Tailed Detection","created":"2021-04-12","cited_by_count":27},{"id":"1708.06128","title":"Revisiting knowledge transfer for training object class detectors","created":"2017-08-21","cited_by_count":26},{"id":"1904.00551","title":"Weakly Supervised Object Detection with Segmentation Collaboration","created":"2019-04-01","cited_by_count":26},{"id":"2103.17084","title":"DA-DETR: Domain Adaptive Detection Transformer with Information Fusion","created":"2021-03-31","cited_by_count":24},{"id":"2203.01386","title":"Exploring Hierarchical Graph Representation for Large-Scale Zero-Shot Image Classification","created":"2022-03-02","cited_by_count":21},{"id":"2108.01499","title":"Boosting Weakly Supervised Object Detection via Learning Bounding Box Adjusters","created":"2021-08-03","cited_by_count":20},{"id":"2105.14370","title":"BAAI-VANJEE Roadside Dataset: Towards the Connected Automated Vehicle Highway technologies in Challenging Environments of China","created":"2021-05-29","cited_by_count":19},{"id":"1908.05217","title":"Detecting 11K Classes: Large Scale Object Detection without Fine-Grained Bounding Boxes","created":"2019-08-14","cited_by_count":17},{"id":"1712.01802","title":"R-FCN-3000 at 30fps: Decoupling Detection and Classification","created":"2017-12-05","cited_by_count":15},{"id":"1802.09778","title":"Mixed Supervised Object Detection with Robust Objectness Transfer","created":"2018-02-27","cited_by_count":14},{"id":"2110.14191","title":"Mixed Supervised Object Detection by Transferring Mask Prior and Semantic Similarity","created":"2021-10-27","cited_by_count":11},{"id":"1702.08740","title":"Weakly- and Semi-Supervised Object Detection with Expectation-Maximization Algorithm","created":"2017-02-28","cited_by_count":10},{"id":"2104.01666","title":"Improving Pretrained Models for Zero-shot Multi-label Text Classification through Reinforced Label Hierarchy Reasoning","created":"2021-04-04","cited_by_count":9},{"id":"1804.01077","title":"DOCK: Detecting Objects by transferring Common-sense Knowledge","created":"2018-04-03","cited_by_count":8},{"id":"2105.11293","title":"WSSOD: A New Pipeline for Weakly- and Semi-Supervised Object Detection","created":"2021-05-21","cited_by_count":7}],"next_cursor":null}