{"list":"other","total":51,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"2303.12712","title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","created":"2023-03-22","cited_by_count":2592},{"id":"1505.00468","title":"VQA: Visual Question Answering","created":"2015-05-03","cited_by_count":2506},{"id":"1802.05365","title":"Deep contextualized word representations","created":"2018-02-15","cited_by_count":2290},{"id":"1608.00272","title":"Modeling Context in Referring Expressions","created":"2016-07-31","cited_by_count":1063},{"id":"1511.02283","title":"Generation and Comprehension of Unambiguous Object Descriptions","created":"2015-11-07","cited_by_count":904},{"id":"1801.00868","title":"Panoptic Segmentation","created":"2018-01-03","cited_by_count":802},{"id":"1701.02426","title":"Scene Graph Generation by Iterative Message Passing","created":"2017-01-10","cited_by_count":462},{"id":"1801.08186","title":"MAttNet: Modular Attention Network for Referring Expression Comprehension","created":"2018-01-24","cited_by_count":431},{"id":"1711.06640","title":"Neural Motifs: Scene Graph Parsing with Global Context","created":"2017-11-17","cited_by_count":414},{"id":"2002.11949","title":"Unbiased Scene Graph Generation from Biased Training","created":"2020-02-27","cited_by_count":356},{"id":"2112.02244","title":"LAVT: Language-Aware Vision Transformer for Referring Image Segmentation","created":"2021-12-04","cited_by_count":348},{"id":"1811.10092","title":"Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language Navigation","created":"2018-11-25","cited_by_count":305},{"id":"2303.02153","title":"Unleashing Text-to-Image Diffusion Models for Visual Perception","created":"2023-03-03","cited_by_count":269},{"id":"1904.04745","title":"Cross-Modal Self-Attention Network for Referring Image Segmentation","created":"2019-04-09","cited_by_count":263},{"id":"1812.01880","title":"Learning to Compose Dynamic Tree Structures for Visual Contexts","created":"2018-12-05","cited_by_count":259},{"id":"1603.06180","title":"Segmentation from Natural Language Expressions","created":"2016-03-20","cited_by_count":257},{"id":"2108.05565","title":"Vision-Language Transformer and Query Generation for Referring Segmentation","created":"2021-08-12","cited_by_count":240},{"id":"2003.08813","title":"Multi-task Collaborative Network for Joint Referring Expression Comprehension and Segmentation","created":"2020-03-19","cited_by_count":204},{"id":"1908.06354","title":"A Fast and Accurate One-Stage Approach to Visual Grounding","created":"2019-08-18","cited_by_count":195},{"id":"2303.06674","title":"Universal Instance Perception as Object Discovery and Retrieval","created":"2023-03-12","cited_by_count":192},{"id":"2003.12962","title":"GPS-Net: Graph Property Sensing Network for Scene Graph Generation","created":"2020-03-29","cited_by_count":166},{"id":"1903.03326","title":"Knowledge-Embedded Routing Network for Scene Graph Generation","created":"2019-03-08","cited_by_count":164},{"id":"1912.06203","title":"ManiGAN: Text-Guided Image Manipulation","created":"2019-12-12","cited_by_count":156},{"id":"2008.01059","title":"Improving One-stage Visual Grounding by Recursive Sub-query Construction","created":"2020-08-03","cited_by_count":138},{"id":"1703.07939","title":"Recurrent Multimodal Interaction for Referring Image Segmentation","created":"2017-03-23","cited_by_count":125},{"id":"1609.05600","title":"Graph-Structured Representations for Visual Question Answering","created":"2016-09-19","cited_by_count":123},{"id":"1909.08164","title":"Dynamic Graph Attention for Referring Expression Comprehension","created":"2019-09-18","cited_by_count":111},{"id":"2105.01839","title":"Encoder Fusion Network with Co-Attention Embedding for Referring Image Segmentation","created":"2021-05-05","cited_by_count":111},{"id":"2103.16284","title":"Locate then Segment: A Strong Pipeline for Referring Image Segmentation","created":"2021-03-30","cited_by_count":98},{"id":"1911.03977","title":"Multimodal Intelligence: Representation Learning, Information Fusion, and Applications","created":"2019-11-10","cited_by_count":89},{"id":"2003.00387","title":"Say As You Wish: Fine-grained Control of Image Caption Generation with Abstract Scene Graphs","created":"2020-03-01","cited_by_count":87},{"id":"1807.02257","title":"Dynamic Multimodal Instance Segmentation guided by natural language queries","created":"2018-07-06","cited_by_count":83},{"id":"1906.07510","title":"Attention Guided Graph Convolutional Networks for Relation Extraction","created":"2019-06-18","cited_by_count":82},{"id":"1908.07129","title":"Zero-Shot Grounding of Objects from Natural Language Queries","created":"2019-08-20","cited_by_count":79},{"id":"2009.07526","title":"CogTree: Cognition Tree Loss for Unbiased Scene Graph Generation","created":"2020-09-16","cited_by_count":62},{"id":"2203.11654","title":"Fine-Grained Scene Graph Generation with Data Transfer","created":"2022-03-22","cited_by_count":57},{"id":"1812.03426","title":"Real-Time Referring Expression Comprehension by Single-Stage Grounding Network","created":"2018-12-09","cited_by_count":56},{"id":"1711.06288","title":"Language-Based Image Editing with Recurrent Attentive Models","created":"2017-11-16","cited_by_count":53},{"id":"2007.01072","title":"Scene Graph Reasoning for Visual Question Answering","created":"2020-07-02","cited_by_count":50},{"id":"2307.15567","title":"Panoptic Scene Graph Generation with Semantics-Prototype Learning","created":"2023-07-28","cited_by_count":42},{"id":"2108.00205","title":"Word2Pix: Word to Pixel Cross Attention Transformer in Visual Grounding","created":"2021-07-31","cited_by_count":16},{"id":"2308.10247","title":"SAR Ship Target Recognition Via Multi-Scale Feature Attention and Adaptive-Weighed Classifier","created":"2023-08-20","cited_by_count":3}],"next_cursor":null}