{"list":"other","total":62,"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":"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":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"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":"2105.15203","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","created":"2021-05-31","cited_by_count":2940},{"id":"1505.00468","title":"VQA: Visual Question Answering","created":"2015-05-03","cited_by_count":2506},{"id":"2109.01134","title":"Learning to Prompt for Vision-Language Models","created":"2021-09-02","cited_by_count":2281},{"id":"1904.01355","title":"FCOS: Fully Convolutional One-Stage Object Detection","created":"2019-04-02","cited_by_count":1577},{"id":"2111.09883","title":"Swin Transformer V2: Scaling Up Capacity and Resolution","created":"2021-11-18","cited_by_count":1228},{"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":"2107.06278","title":"Per-Pixel Classification is Not All You Need for Semantic Segmentation","created":"2021-07-13","cited_by_count":1152},{"id":"1608.05442","title":"Semantic Understanding of Scenes through the ADE20K Dataset","created":"2016-08-18","cited_by_count":1069},{"id":"2110.04544","title":"CLIP-Adapter: Better Vision-Language Models with Feature Adapters","created":"2021-10-09","cited_by_count":1026},{"id":"2106.04560","title":"Scaling Vision Transformers","created":"2021-06-08","cited_by_count":999},{"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":"1411.4555","title":"Show and Tell: A Neural Image Caption Generator","created":"2014-11-17","cited_by_count":879},{"id":"2105.05633","title":"Segmenter: Transformer for Semantic Segmentation","created":"2021-05-12","cited_by_count":855},{"id":"1801.00868","title":"Panoptic Segmentation","created":"2018-01-03","cited_by_count":802},{"id":"2201.03546","title":"Language-driven Semantic Segmentation","created":"2022-01-10","cited_by_count":717},{"id":"1811.10830","title":"From Recognition to Cognition: Visual Commonsense Reasoning","created":"2018-11-27","cited_by_count":556},{"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":"1511.06233","title":"Towards Open Set Deep Networks","created":"2015-11-19","cited_by_count":538},{"id":"2202.11094","title":"GroupViT: Semantic Segmentation Emerges from Text Supervision","created":"2022-02-22","cited_by_count":531},{"id":"2011.12450","title":"Sparse R-CNN: End-to-End Object Detection with Learnable Proposals","created":"2020-11-25","cited_by_count":495},{"id":"1908.06391","title":"PANet: Few-Shot Image Semantic Segmentation with Prototype Alignment","created":"2019-08-18","cited_by_count":449},{"id":"2011.10678","title":"Open-Vocabulary Object Detection Using Captions","created":"2020-11-20","cited_by_count":427},{"id":"2108.06152","title":"Conditional DETR for Fast Training Convergence","created":"2021-08-13","cited_by_count":424},{"id":"2109.10852","title":"Pix2seq: A Language Modeling Framework for Object Detection","created":"2021-09-22","cited_by_count":349},{"id":"1711.11543","title":"Embodied Question Answering","created":"2017-11-30","cited_by_count":336},{"id":"1511.03416","title":"Visual7W: Grounded Question Answering in Images","created":"2015-11-11","cited_by_count":318},{"id":"2003.05664","title":"Conditional Convolutions for Instance Segmentation","created":"2020-03-12","cited_by_count":314},{"id":"2205.06230","title":"Simple Open-Vocabulary Object Detection with Vision Transformers","created":"2022-05-12","cited_by_count":305},{"id":"2103.02603","title":"Towards Open World Object Detection","created":"2021-03-03","cited_by_count":297},{"id":"1810.04020","title":"A Comprehensive Survey of Deep Learning for Image Captioning","created":"2018-10-06","cited_by_count":214},{"id":"2106.14855","title":"K-Net: Towards Unified Image Segmentation","created":"2021-06-28","cited_by_count":212},{"id":"2104.01538","title":"Hypercorrelation Squeeze for Few-Shot Segmentation","created":"2021-04-04","cited_by_count":193},{"id":"2112.10764","title":"Mask2Former for Video Instance Segmentation","created":"2021-12-20","cited_by_count":171},{"id":"2007.06309","title":"Part-aware Prototype Network for Few-shot Semantic Segmentation","created":"2020-07-13","cited_by_count":162},{"id":"2105.01928","title":"Instances as Queries","created":"2021-05-05","cited_by_count":158},{"id":"1712.03316","title":"IQA: Visual Question Answering in Interactive Environments","created":"2017-12-09","cited_by_count":155},{"id":"1703.07939","title":"Recurrent Multimodal Interaction for Referring Image Segmentation","created":"2017-03-23","cited_by_count":125},{"id":"1511.04164","title":"Natural Language Object Retrieval","created":"2015-11-13","cited_by_count":124},{"id":"1607.05910","title":"Visual Question Answering: A Survey of Methods and Datasets","created":"2016-07-20","cited_by_count":123},{"id":"1904.03215","title":"The Fishyscapes Benchmark: Measuring Blind Spots in Semantic Segmentation","created":"2019-04-05","cited_by_count":122},{"id":"2004.02307","title":"EfficientPS: Efficient Panoptic Segmentation","created":"2020-04-05","cited_by_count":111},{"id":"2112.00933","title":"PartImageNet: A Large, High-Quality Dataset of Parts","created":"2021-12-02","cited_by_count":107},{"id":"1912.02801","title":"PolyTransform: Deep Polygon Transformer for Instance Segmentation","created":"2019-12-05","cited_by_count":92},{"id":"1812.03904","title":"Attention-guided Unified Network for Panoptic Segmentation","created":"2018-12-10","cited_by_count":71},{"id":"2106.02351","title":"SOLQ: Segmenting Objects by Learning Queries","created":"2021-06-04","cited_by_count":68},{"id":"2104.07434","title":"Points as Queries: Weakly Semi-supervised Object Detection by Points","created":"2021-04-15","cited_by_count":60},{"id":"2106.06351","title":"Part-aware Panoptic Segmentation","created":"2021-06-11","cited_by_count":56},{"id":"2104.05239","title":"Look Closer to Segment Better: Boundary Patch Refinement for Instance Segmentation","created":"2021-04-12","cited_by_count":43},{"id":"2204.04655","title":"Panoptic-PartFormer: Learning a Unified Model for Panoptic Part Segmentation","created":"2022-04-10","cited_by_count":38},{"id":"1812.01192","title":"Learning to Fuse Things and Stuff","created":"2018-12-04","cited_by_count":26},{"id":"2004.07944","title":"Cityscapes-Panoptic-Parts and PASCAL-Panoptic-Parts datasets for Scene Understanding","created":"2020-04-16","cited_by_count":14},{"id":"2105.13978","title":"What Is Considered Complete for Visual Recognition?","created":"2021-05-28","cited_by_count":3}],"next_cursor":null}