{"list":"other","total":77,"rows":[{"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":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"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":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"id":"1605.07146","title":"Wide Residual Networks","created":"2016-05-23","cited_by_count":3070},{"id":"1409.3215","title":"Sequence to Sequence Learning with Neural Networks","created":"2014-09-10","cited_by_count":2986},{"id":"1504.08083","title":"Fast R-CNN","created":"2015-04-30","cited_by_count":2933},{"id":"1804.02767","title":"YOLOv3: An Incremental Improvement","created":"2018-04-08","cited_by_count":2659},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"1908.02265","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","created":"2019-08-06","cited_by_count":2222},{"id":"2107.07651","title":"Align before Fuse: Vision and Language Representation Learning with Momentum Distillation","created":"2021-07-16","cited_by_count":1619},{"id":"1908.07490","title":"LXMERT: Learning Cross-Modality Encoder Representations from Transformers","created":"2019-08-20","cited_by_count":1553},{"id":"1506.02025","title":"Spatial Transformer Networks","created":"2015-06-05","cited_by_count":1429},{"id":"1505.04870","title":"Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models","created":"2015-05-19","cited_by_count":1362},{"id":"1409.1259","title":"On the Properties of Neural Machine Translation: Encoder-Decoder Approaches","created":"2014-09-03","cited_by_count":1304},{"id":"1712.00726","title":"Cascade R-CNN: Delving into High Quality Object Detection","created":"2017-12-03","cited_by_count":1276},{"id":"1904.07850","title":"Objects as Points","created":"2019-04-16","cited_by_count":1175},{"id":"1608.00272","title":"Modeling Context in Referring Expressions","created":"2016-07-31","cited_by_count":1063},{"id":"1704.00675","title":"The 2017 DAVIS Challenge on Video Object Segmentation","created":"2017-04-03","cited_by_count":957},{"id":"2104.12763","title":"MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding","created":"2021-04-26","cited_by_count":819},{"id":"1803.01534","title":"Path Aggregation Network for Instance Segmentation","created":"2018-03-05","cited_by_count":798},{"id":"2202.03052","title":"OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework","created":"2022-02-07","cited_by_count":745},{"id":"2108.10904","title":"SimVLM: Simple Visual Language Model Pretraining with Weak Supervision","created":"2021-08-24","cited_by_count":647},{"id":"2106.04803","title":"CoAtNet: Marrying Convolution and Attention for All Data Sizes","created":"2021-06-09","cited_by_count":569},{"id":"1901.07518","title":"Hybrid Task Cascade for Instance Segmentation","created":"2019-01-22","cited_by_count":481},{"id":"1904.02689","title":"YOLACT: Real-time Instance Segmentation","created":"2019-04-04","cited_by_count":443},{"id":"1801.08186","title":"MAttNet: Modular Attention Network for Referring Expression Comprehension","created":"2018-01-24","cited_by_count":431},{"id":"2206.08916","title":"Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Tasks","created":"2022-06-17","cited_by_count":421},{"id":"2111.15174","title":"CRIS: CLIP-Driven Referring Image Segmentation","created":"2021-11-30","cited_by_count":353},{"id":"2109.10852","title":"Pix2seq: A Language Modeling Framework for Object Detection","created":"2021-09-22","cited_by_count":349},{"id":"2112.02244","title":"LAVT: Language-Aware Vision Transformer for Referring Image Segmentation","created":"2021-12-04","cited_by_count":348},{"id":"2006.06195","title":"Large-Scale Adversarial Training for Vision-and-Language Representation Learning","created":"2020-06-11","cited_by_count":327},{"id":"1912.02315","title":"12-in-1: Multi-Task Vision and Language Representation Learning","created":"2019-12-05","cited_by_count":278},{"id":"1904.04745","title":"Cross-Modal Self-Attention Network for Referring Image Segmentation","created":"2019-04-09","cited_by_count":263},{"id":"1603.06180","title":"Segmentation from Natural Language Expressions","created":"2016-03-20","cited_by_count":257},{"id":"1608.00525","title":"Modeling Context Between Objects for Referring Expression Understanding","created":"2016-08-01","cited_by_count":251},{"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":"2006.15595","title":"Rethinking Positional Encoding in Language Pre-training","created":"2020-06-28","cited_by_count":197},{"id":"1908.06354","title":"A Fast and Accurate One-Stage Approach to Visual Grounding","created":"2019-08-18","cited_by_count":195},{"id":"1909.13226","title":"PolarMask: Single Shot Instance Segmentation with Polar Representation","created":"2019-09-29","cited_by_count":188},{"id":"2201.00487","title":"Language as Queries for Referring Video Object Segmentation","created":"2022-01-03","cited_by_count":182},{"id":"1803.08006","title":"Video Object Segmentation with Language Referring Expressions","created":"2018-03-21","cited_by_count":162},{"id":"2206.07669","title":"A Unified Sequence Interface for Vision Tasks","created":"2022-06-15","cited_by_count":152},{"id":"2106.03089","title":"Referring Transformer: A One-step Approach to Multi-task Visual Grounding","created":"2021-06-06","cited_by_count":143},{"id":"2203.16265","title":"SeqTR: A Simple yet Universal Network for Visual Grounding","created":"2022-03-30","cited_by_count":139},{"id":"2010.00514","title":"Referring Image Segmentation via Cross-Modal Progressive Comprehension","created":"2020-10-01","cited_by_count":131},{"id":"1703.07939","title":"Recurrent Multimodal Interaction for Referring Image Segmentation","created":"2017-03-23","cited_by_count":125},{"id":"2111.12085","title":"UniTAB: Unifying Text and Box Outputs for Grounded Vision-Language Modeling","created":"2021-11-23","cited_by_count":122},{"id":"1512.04412","title":"Instance-aware Semantic Segmentation via Multi-task Network Cascades","created":"2015-12-14","cited_by_count":121},{"id":"1803.09693","title":"Efficient Interactive Annotation of Segmentation Datasets with Polygon-RNN++","created":"2018-03-26","cited_by_count":120},{"id":"2001.01629","title":"Deep Snake for Real-Time Instance Segmentation","created":"2020-01-06","cited_by_count":112},{"id":"2203.16768","title":"ReSTR: Convolution-free Referring Image Segmentation Using Transformers","created":"2022-03-31","cited_by_count":112},{"id":"1909.07072","title":"A Real-Time Cross-modality Correlation Filtering Method for Referring Expression Comprehension","created":"2019-09-16","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":"1611.09978","title":"Modeling Relationships in Referential Expressions with Compositional Modular Networks","created":"2016-11-30","cited_by_count":106},{"id":"2105.07175","title":"Cross-Modal Progressive Comprehension for Referring Segmentation","created":"2021-05-15","cited_by_count":102},{"id":"1906.01784","title":"Learning to Compose and Reason with Language Tree Structures for Visual Grounding","created":"2019-06-05","cited_by_count":98},{"id":"2103.16284","title":"Locate then Segment: A Strong Pipeline for Referring Image Segmentation","created":"2021-03-30","cited_by_count":98},{"id":"1912.02801","title":"PolyTransform: Deep Polygon Transformer for Instance Segmentation","created":"2019-12-05","cited_by_count":92},{"id":"1704.05548","title":"Annotating Object Instances with a Polygon-RNN","created":"2017-04-18","cited_by_count":88},{"id":"1807.02257","title":"Dynamic Multimodal Instance Segmentation guided by natural language queries","created":"2018-07-06","cited_by_count":83},{"id":"1712.01892","title":"Grounding Referring Expressions in Images by Variational Context","created":"2017-12-05","cited_by_count":82},{"id":"1711.06370","title":"Parallel Attention: A Unified Framework for Visual Object Discovery through Dialogs and Queries","created":"2017-11-17","cited_by_count":56},{"id":"1910.04748","title":"Referring Expression Object Segmentation with Caption-Aware Consistency","created":"2019-10-10","cited_by_count":46},{"id":"2204.05626","title":"X-DETR: A Versatile Architecture for Instance-wise Vision-Language Tasks","created":"2022-04-12","cited_by_count":43},{"id":"2106.01061","title":"Rethinking Cross-modal Interaction from a Top-down Perspective for Referring Video Object Segmentation","created":"2021-06-02","cited_by_count":42},{"id":"1511.07763","title":"LocNet: Improving Localization Accuracy for Object Detection","created":"2015-11-24","cited_by_count":14},{"id":"1802.01777","title":"Brute-Force Facial Landmark Analysis With A 140,000-Way Classifier","created":"2018-02-06","cited_by_count":1}],"next_cursor":null}