{"list":"other","total":54,"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":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"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":"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":"1709.06158","title":"Matterport3D: Learning from RGB-D Data in Indoor Environments","created":"2017-09-18","cited_by_count":1376},{"id":"1707.07998","title":"Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering","created":"2017-07-25","cited_by_count":1312},{"id":"1711.07280","title":"Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments","created":"2017-11-20","cited_by_count":1027},{"id":"2109.08238","title":"Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AI","created":"2021-09-16","cited_by_count":592},{"id":"1808.10654","title":"Gibson Env: Real-World Perception for Embodied Agents","created":"2018-08-31","cited_by_count":481},{"id":"2204.02610","title":"Efficient Test-Time Model Adaptation without Forgetting","created":"2022-04-06","cited_by_count":469},{"id":"2010.07954","title":"Room-Across-Room: Multilingual Vision-and-Language Navigation with Dense Spatiotemporal Grounding","created":"2020-10-15","cited_by_count":414},{"id":"1806.02724","title":"Speaker-Follower Models for Vision-and-Language Navigation","created":"2018-06-07","cited_by_count":340},{"id":"1904.10151","title":"REVERIE: Remote Embodied Visual Referring Expression in Real Indoor Environments","created":"2019-04-23","cited_by_count":333},{"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":"2011.13922","title":"A Recurrent Vision-and-Language BERT for Navigation","created":"2020-11-26","cited_by_count":302},{"id":"2110.13309","title":"History Aware Multimodal Transformer for Vision-and-Language Navigation","created":"2021-10-25","cited_by_count":271},{"id":"1904.04195","title":"Learning to Navigate Unseen Environments: Back Translation with Environmental Dropout","created":"2019-04-08","cited_by_count":244},{"id":"2002.10638","title":"Towards Learning a Generic Agent for Vision-and-Language Navigation via Pre-training","created":"2020-02-25","cited_by_count":231},{"id":"2202.11742","title":"Think Global, Act Local: Dual-scale Graph Transformer for Vision-and-Language Navigation","created":"2022-02-23","cited_by_count":193},{"id":"1911.07883","title":"Vision-Language Navigation with Self-Supervised Auxiliary Reasoning Tasks","created":"2019-11-18","cited_by_count":179},{"id":"2004.14973","title":"Improving Vision-and-Language Navigation with Image-Text Pairs from the Web","created":"2020-04-30","cited_by_count":177},{"id":"1901.03035","title":"Self-Monitoring Navigation Agent via Auxiliary Progress Estimation","created":"2019-01-10","cited_by_count":176},{"id":"1905.12255","title":"Stay on the Path: Instruction Fidelity in Vision-and-Language Navigation","created":"2019-05-29","cited_by_count":130},{"id":"2108.09105","title":"Airbert: In-domain Pretraining for Vision-and-Language Navigation","created":"2021-08-20","cited_by_count":130},{"id":"2103.17138","title":"SOON: Scenario Oriented Object Navigation with Graph-based Exploration","created":"2021-03-31","cited_by_count":119},{"id":"2105.08756","title":"Pathdreamer: A World Model for Indoor Navigation","created":"2021-05-18","cited_by_count":118},{"id":"2010.09304","title":"Language and Visual Entity Relationship Graph for Agent Navigation","created":"2020-10-19","cited_by_count":100},{"id":"2210.07506","title":"Weakly-Supervised Multi-Granularity Map Learning for Vision-and-Language Navigation","created":"2022-10-14","cited_by_count":86},{"id":"2203.15685","title":"EnvEdit: Environment Editing for Vision-and-Language Navigation","created":"2022-03-29","cited_by_count":83},{"id":"2203.11591","title":"HOP: History-and-Order Aware Pre-training for Vision-and-Language Navigation","created":"2022-03-22","cited_by_count":70},{"id":"2111.12872","title":"Less is More: Generating Grounded Navigation Instructions from Landmarks","created":"2021-11-25","cited_by_count":64},{"id":"2006.10034","title":"Semantic Visual Navigation by Watching YouTube Videos","created":"2020-06-17","cited_by_count":60},{"id":"2210.03112","title":"A New Path: Scaling Vision-and-Language Navigation with Synthetic Instructions and Imitation Learning","created":"2022-10-06","cited_by_count":60},{"id":"2110.14143","title":"SOAT: A Scene- and Object-Aware Transformer for Vision-and-Language Navigation","created":"2021-10-27","cited_by_count":53},{"id":"2208.11781","title":"Learning from Unlabeled 3D Environments for Vision-and-Language Navigation","created":"2022-08-24","cited_by_count":50},{"id":"2103.12944","title":"Scene-Intuitive Agent for Remote Embodied Visual Grounding","created":"2021-03-24","cited_by_count":49},{"id":"1908.03409","title":"Transferable Representation Learning in Vision-and-Language Navigation","created":"2019-08-09","cited_by_count":48},{"id":"2205.15509","title":"ADAPT: Vision-Language Navigation with Modality-Aligned Action Prompts","created":"2022-05-31","cited_by_count":45},{"id":"2104.09580","title":"Improving Cross-Modal Alignment in Vision Language Navigation via Syntactic Information","created":"2021-04-19","cited_by_count":31},{"id":"2301.01970","title":"CAT: LoCalization and IdentificAtion Cascade Detection Transformer for Open-World Object Detection","created":"2023-01-05","cited_by_count":28},{"id":"2202.07028","title":"One Step at a Time: Long-Horizon Vision-and-Language Navigation with Milestones","created":"2022-02-14","cited_by_count":26},{"id":"2203.04006","title":"Visual-Language Navigation Pretraining via Prompt-based Environmental Self-exploration","created":"2022-03-08","cited_by_count":25},{"id":"2203.13838","title":"Analyzing Generalization of Vision and Language Navigation to Unseen Outdoor Areas","created":"2022-03-25","cited_by_count":24},{"id":"2112.04138","title":"Contrastive Instruction-Trajectory Learning for Vision-Language Navigation","created":"2021-12-08","cited_by_count":16},{"id":"2207.02185","title":"CLEAR: Improving Vision-Language Navigation with Cross-Lingual, Environment-Agnostic Representations","created":"2022-07-05","cited_by_count":10},{"id":"2211.11116","title":"Structure-Encoding Auxiliary Tasks for Improved Visual Representation in Vision-and-Language Navigation","created":"2022-11-20","cited_by_count":9},{"id":"2304.03767","title":"Embodied Concept Learner: Self-supervised Learning of Concepts and Mapping through Instruction Following","created":"2023-04-07","cited_by_count":9}],"next_cursor":null}