{"list":"other","total":52,"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"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":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627},{"id":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"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":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"1504.00325","title":"Microsoft COCO Captions: Data Collection and Evaluation Server","created":"2015-04-01","cited_by_count":1462},{"id":"1612.08242","title":"YOLO9000: Better, Faster, Stronger","created":"2016-12-25","cited_by_count":1431},{"id":"2205.01917","title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","created":"2022-05-04","cited_by_count":1274},{"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":"2111.11432","title":"Florence: A New Foundation Model for Computer Vision","created":"2021-11-22","cited_by_count":804},{"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":"2011.12450","title":"Sparse R-CNN: End-to-End Object Detection with Learnable Proposals","created":"2020-11-25","cited_by_count":495},{"id":"2011.10678","title":"Open-Vocabulary Object Detection Using Captions","created":"2020-11-20","cited_by_count":427},{"id":"2303.11331","title":"EVA-02: A Visual Representation for Neon Genesis","created":"2023-03-20","cited_by_count":381},{"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":"2101.11939","title":"Exploring Cross-Image Pixel Contrast for Semantic Segmentation","created":"2021-01-28","cited_by_count":242},{"id":"2203.08414","title":"Unsupervised Semantic Segmentation by Distilling Feature Correspondences","created":"2022-03-16","cited_by_count":241},{"id":"2203.11876","title":"Open-Vocabulary DETR with Conditional Matching","created":"2022-03-22","cited_by_count":220},{"id":"2303.06674","title":"Universal Instance Perception as Object Discovery and Retrieval","created":"2023-03-12","cited_by_count":192},{"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":"2103.17070","title":"PiCIE: Unsupervised Semantic Segmentation using Invariance and Equivariance in Clustering","created":"2021-03-30","cited_by_count":163},{"id":"2203.15102","title":"Rethinking Semantic Segmentation: A Prototype View","created":"2022-03-28","cited_by_count":140},{"id":"2203.16513","title":"PromptDet: Towards Open-vocabulary Detection using Uncurated Images","created":"2022-03-30","cited_by_count":133},{"id":"2103.07461","title":"Probabilistic two-stage detection","created":"2021-03-12","cited_by_count":130},{"id":"2302.13996","title":"Aligning Bag of Regions for Open-Vocabulary Object Detection","created":"2023-02-27","cited_by_count":119},{"id":"2206.07045","title":"ReCo: Retrieve and Co-segment for Zero-shot Transfer","created":"2022-06-14","cited_by_count":117},{"id":"2106.02637","title":"Aligning Pretraining for Detection via Object-Level Contrastive Learning","created":"2021-06-04","cited_by_count":110},{"id":"2003.10658","title":"CRNet: Cross-Reference Networks for Few-Shot Segmentation","created":"2020-03-24","cited_by_count":101},{"id":"2211.14843","title":"Learning Object-Language Alignments for Open-Vocabulary Object Detection","created":"2022-11-27","cited_by_count":96},{"id":"2304.04514","title":"DetCLIPv2: Scalable Open-Vocabulary Object Detection Pre-training via Word-Region Alignment","created":"2023-04-10","cited_by_count":90},{"id":"2203.08777","title":"Object discovery and representation networks","created":"2022-03-16","cited_by_count":80},{"id":"1904.05647","title":"C-MIL: Continuation Multiple Instance Learning for Weakly Supervised Object Detection","created":"2019-04-11","cited_by_count":71},{"id":"2111.09452","title":"Open Vocabulary Object Detection with Pseudo Bounding-Box Labels","created":"2021-11-18","cited_by_count":71},{"id":"2205.15288","title":"Self-Supervised Visual Representation Learning with Semantic Grouping","created":"2022-05-30","cited_by_count":70},{"id":"1911.07933","title":"Dont Even Look Once: Synthesizing Features for Zero-Shot Detection","created":"2019-11-18","cited_by_count":58},{"id":"2202.04639","title":"Point-Level Region Contrast for Object Detection Pre-Training","created":"2022-02-09","cited_by_count":41},{"id":"1503.00949","title":"Weakly Supervised Object Localization with Multi-fold Multiple Instance Learning","created":"2015-03-03","cited_by_count":39},{"id":"1805.06157","title":"Zero-Shot Object Detection by Hybrid Region Embedding","created":"2018-05-16","cited_by_count":32},{"id":"2001.06812","title":"GTNet: Generative Transfer Network for Zero-Shot Object Detection","created":"2020-01-19","cited_by_count":25},{"id":"2206.11134","title":"Open Vocabulary Object Detection with Proposal Mining and Prediction Equalization","created":"2022-06-22","cited_by_count":23}],"next_cursor":null}