{"list":"other","total":60,"rows":[{"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":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1612.01105","title":"Pyramid Scene Parsing Network","created":"2016-12-04","cited_by_count":2479},{"id":"1703.04977","title":"What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?","created":"2017-03-15","cited_by_count":2352},{"id":"1709.06158","title":"Matterport3D: Learning from RGB-D Data in Indoor Environments","created":"2017-09-18","cited_by_count":1376},{"id":"2102.03334","title":"ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision","created":"2021-02-05","cited_by_count":1230},{"id":"2105.05537","title":"Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation","created":"2021-05-12","cited_by_count":1222},{"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":"1712.05474","title":"AI2-THOR: An Interactive 3D Environment for Visual AI","created":"2017-12-14","cited_by_count":869},{"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":"1807.06757","title":"On Evaluation of Embodied Navigation Agents","created":"2018-07-18","cited_by_count":547},{"id":"1911.06455","title":"Graph Transformer Networks","created":"2019-11-06","cited_by_count":523},{"id":"1808.10654","title":"Gibson Env: Real-World Perception for Embodied Agents","created":"2018-08-31","cited_by_count":481},{"id":"2207.04429","title":"LM-Nav: Robotic Navigation with Large Pre-Trained Models of Language, Vision, and Action","created":"2022-07-10","cited_by_count":439},{"id":"2007.00643","title":"Object Goal Navigation using Goal-Oriented Semantic Exploration","created":"2020-07-01","cited_by_count":429},{"id":"2206.06488","title":"Multimodal Learning with Transformers: A Survey","created":"2022-06-13","cited_by_count":400},{"id":"2206.06994","title":"ProcTHOR: Large-Scale Embodied AI Using Procedural Generation","created":"2022-06-14","cited_by_count":380},{"id":"1609.05143","title":"Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learning","created":"2016-09-16","cited_by_count":366},{"id":"1911.00357","title":"DD-PPO: Learning Near-Perfect PointGoal Navigators from 2.5 Billion Frames","created":"2019-11-01","cited_by_count":362},{"id":"2206.02777","title":"Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentation","created":"2022-06-06","cited_by_count":344},{"id":"2004.05155","title":"Learning to Explore using Active Neural SLAM","created":"2020-04-10","cited_by_count":316},{"id":"1711.11575","title":"Relation Networks for Object Detection","created":"2017-11-30","cited_by_count":305},{"id":"1910.02527","title":"3D Scene Graph: A Structure for Unified Semantics, 3D Space, and Camera","created":"2019-10-06","cited_by_count":281},{"id":"1908.10553","title":"Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Video","created":"2019-08-28","cited_by_count":244},{"id":"1904.11491","title":"Local Relation Networks for Image Recognition","created":"2019-04-25","cited_by_count":210},{"id":"2005.06209","title":"On the uncertainty of self-supervised monocular depth estimation","created":"2020-05-13","cited_by_count":182},{"id":"2206.12403","title":"ZSON: Zero-Shot Object-Goal Navigation using Multimodal Goal Embeddings","created":"2022-06-24","cited_by_count":178},{"id":"2201.10029","title":"PONI: Potential Functions for ObjectGoal Navigation with Interaction-free Learning","created":"2022-01-25","cited_by_count":150},{"id":"2311.07226","title":"Large Language Models for Robotics: A Survey","created":"2023-11-13","cited_by_count":133},{"id":"2301.13166","title":"ESC: Exploration with Soft Commonsense Constraints for Zero-shot Object Navigation","created":"2023-01-30","cited_by_count":127},{"id":"2304.05501","title":"L3MVN: Leveraging Large Language Models for Visual Target Navigation","created":"2023-04-11","cited_by_count":120},{"id":"2204.03514","title":"Habitat-Web: Learning Embodied Object-Search Strategies from Human Demonstrations at Scale","created":"2022-04-07","cited_by_count":117},{"id":"2008.09285","title":"Occupancy Anticipation for Efficient Exploration and Navigation","created":"2020-08-21","cited_by_count":106},{"id":"2212.00922","title":"Navigating to Objects in the Real World","created":"2022-12-02","cited_by_count":106},{"id":"1805.06066","title":"Visual Representations for Semantic Target Driven Navigation","created":"2018-05-15","cited_by_count":89},{"id":"2310.10103","title":"Navigation with Large Language Models: Semantic Guesswork as a Heuristic for Planning","created":"2023-10-16","cited_by_count":89},{"id":"2012.11583","title":"Semantic Audio-Visual Navigation","created":"2020-12-21","cited_by_count":82},{"id":"2104.04112","title":"Auxiliary Tasks and Exploration Enable ObjectNav","created":"2021-04-08","cited_by_count":74},{"id":"2202.02440","title":"Zero Experience Required: Plug & Play Modular Transfer Learning for Semantic Visual Navigation","created":"2022-02-05","cited_by_count":67},{"id":"1712.03931","title":"MINOS: Multimodal Indoor Simulator for Navigation in Complex Environments","created":"2017-12-11","cited_by_count":66},{"id":"1806.01054","title":"RedNet: Residual Encoder-Decoder Network for indoor RGB-D Semantic Segmentation","created":"2018-06-04","cited_by_count":66},{"id":"2309.16108","title":"Channel Vision Transformers: An Image Is Worth 1 x 16 x 16 Words","created":"2023-09-28","cited_by_count":34},{"id":"2203.07359","title":"Stubborn: A Strong Baseline for Indoor Object Navigation","created":"2022-03-14","cited_by_count":32},{"id":"1908.09073","title":"Situational Fusion of Visual Representation for Visual Navigation","created":"2019-08-24","cited_by_count":28},{"id":"2312.00360","title":"Efficient Multimodal Semantic Segmentation via Dual-Prompt Learning","created":"2023-12-01","cited_by_count":25},{"id":"2212.02497","title":"PEANUT: Predicting and Navigating to Unseen Targets","created":"2022-12-05","cited_by_count":22},{"id":"2308.05602","title":"Object Goal Navigation with Recursive Implicit Maps","created":"2023-08-10","cited_by_count":16},{"id":"2304.04959","title":"AdaTT: Adaptive Task-to-Task Fusion Network for Multitask Learning in Recommendations","created":"2023-04-11","cited_by_count":10},{"id":"2308.00219","title":"Multi-goal Audio-visual Navigation using Sound Direction Map","created":"2023-08-01","cited_by_count":6},{"id":"2304.07728","title":"TransFusionOdom: Interpretable Transformer-based LiDAR-Inertial Fusion Odometry Estimation","created":"2023-04-16","cited_by_count":4},{"id":"2203.03944","title":"An Online Semantic Mapping System for Extending and Enhancing Visual SLAM","created":"2022-03-08","cited_by_count":3},{"id":"2206.12946","title":"AFT-VO: Asynchronous Fusion Transformers for Multi-View Visual Odometry Estimation","created":"2022-06-26","cited_by_count":3},{"id":"2306.01540","title":"CLIPGraphs: Multimodal Graph Networks to Infer Object-Room Affinities","created":"2023-06-02","cited_by_count":2},{"id":"2311.16623","title":"Visual Semantic Navigation with Real Robots","created":"2023-11-28","cited_by_count":2},{"id":"2402.09189","title":"Traj-LIO: A Resilient Multi-LiDAR Multi-IMU State Estimator Through Sparse Gaussian Process","created":"2024-02-14","cited_by_count":2}],"next_cursor":null}