{"list":"other","total":52,"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":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"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":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"id":"1804.02767","title":"YOLOv3: An Incremental Improvement","created":"2018-04-08","cited_by_count":2659},{"id":"1311.2524","title":"Rich feature hierarchies for accurate object detection and semantic segmentation","created":"2013-11-11","cited_by_count":2162},{"id":"1908.07490","title":"LXMERT: Learning Cross-Modality Encoder Representations from Transformers","created":"2019-08-20","cited_by_count":1553},{"id":"2107.06278","title":"Per-Pixel Classification is Not All You Need for Semantic Segmentation","created":"2021-07-13","cited_by_count":1152},{"id":"1908.08530","title":"VL-BERT: Pre-training of Generic Visual-Linguistic Representations","created":"2019-08-22","cited_by_count":954},{"id":"2104.12763","title":"MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding","created":"2021-04-26","cited_by_count":819},{"id":"1801.08186","title":"MAttNet: Modular Attention Network for Referring Expression Comprehension","created":"2018-01-24","cited_by_count":431},{"id":"1606.00061","title":"Hierarchical Question-Image Co-Attention for Visual Question Answering","created":"2016-05-31","cited_by_count":278},{"id":"2108.05565","title":"Vision-Language Transformer and Query Generation for Referring Segmentation","created":"2021-08-12","cited_by_count":240},{"id":"1908.06354","title":"A Fast and Accurate One-Stage Approach to Visual Grounding","created":"2019-08-18","cited_by_count":195},{"id":"1803.03067","title":"Compositional Attention Networks for Machine Reasoning","created":"2018-03-08","cited_by_count":183},{"id":"1909.10838","title":"Talk2Car: Taking Control of Your Self-Driving Car","created":"2019-09-24","cited_by_count":142},{"id":"2008.01059","title":"Improving One-stage Visual Grounding by Recursive Sub-query Construction","created":"2020-08-03","cited_by_count":138},{"id":"2001.07966","title":"ImageBERT: Cross-modal Pre-training with Large-scale Weak-supervised Image-Text Data","created":"2020-01-22","cited_by_count":137},{"id":"1511.04164","title":"Natural Language Object Retrieval","created":"2015-11-13","cited_by_count":124},{"id":"1704.03470","title":"Learning Two-Branch Neural Networks for Image-Text Matching Tasks","created":"2017-04-11","cited_by_count":119},{"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":"2210.15871","title":"VLT: Vision-Language Transformer and Query Generation for Referring Segmentation","created":"2022-10-28","cited_by_count":111},{"id":"1812.04794","title":"Neighbourhood Watch: Referring Expression Comprehension via Language-guided Graph Attention Networks","created":"2018-12-12","cited_by_count":102},{"id":"2011.15124","title":"Multimodal Pretraining Unmasked: A Meta-Analysis and a Unified Framework of Vision-and-Language BERTs","created":"2020-11-30","cited_by_count":71},{"id":"2205.00272","title":"Improving Visual Grounding with Visual-Linguistic Verification and Iterative Reasoning","created":"2022-04-30","cited_by_count":69},{"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":"1812.03426","title":"Real-Time Referring Expression Comprehension by Single-Stage Grounding Network","created":"2018-12-09","cited_by_count":56},{"id":"1510.03346","title":"The social dilemma of autonomous vehicles","created":"2015-10-12","cited_by_count":48},{"id":"2307.10234","title":"SentimentGPT: Exploiting GPT for Advanced Sentiment Analysis and its Departure from Current Machine Learning","created":"2023-07-16","cited_by_count":38},{"id":"2209.11972","title":"Ground then Navigate: Language-guided Navigation in Dynamic Scenes","created":"2022-09-24","cited_by_count":20},{"id":"2305.15765","title":"Language-Guided 3D Object Detection in Point Cloud for Autonomous Driving","created":"2023-05-25","cited_by_count":20},{"id":"2009.05684","title":"AttnGrounder: Talking to Cars with Attention","created":"2020-09-11","cited_by_count":10},{"id":"2009.06066","title":"Cosine meets Softmax: A tough-to-beat baseline for visual grounding","created":"2020-09-13","cited_by_count":10},{"id":"2110.05559","title":"Development and testing of an image transformer for explainable autonomous driving systems","created":"2021-10-11","cited_by_count":9},{"id":"2106.04232","title":"Giving Commands to a Self-Driving Car: How to Deal with Uncertain Situations?","created":"2021-06-08","cited_by_count":6},{"id":"2112.13031","title":"Grounding Linguistic Commands to Navigable Regions","created":"2021-12-24","cited_by_count":6},{"id":"2308.12537","title":"HuBo-VLM: Unified Vision-Language Model designed for HUman roBOt interaction tasks","created":"2023-08-24","cited_by_count":6},{"id":"2003.08717","title":"Giving Commands to a Self-driving Car: A Multimodal Reasoner for Visual Grounding","created":"2020-03-19","cited_by_count":5},{"id":"2009.08792","title":"Commands 4 Autonomous Vehicles (C4AV) Workshop Summary","created":"2020-09-18","cited_by_count":5},{"id":"1906.11565","title":"EmotionX-KU: BERT-Max based Contextual Emotion Classifier","created":"2019-06-27","cited_by_count":4},{"id":"2004.13822","title":"A Baseline for the Commands For Autonomous Vehicles Challenge","created":"2020-04-20","cited_by_count":4},{"id":"2203.06822","title":"Grounding Commands for Autonomous Vehicles via Layer Fusion with Region-specific Dynamic Layer Attention","created":"2022-03-14","cited_by_count":4},{"id":"2112.05419","title":"Predicting Physical World Destinations for Commands Given to Self-Driving Cars","created":"2021-12-10","cited_by_count":3}],"next_cursor":null}