{"list":"other","total":78,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"1505.00468","title":"VQA: Visual Question Answering","created":"2015-05-03","cited_by_count":2506},{"id":"1711.03938","title":"CARLA: An Open Urban Driving Simulator","created":"2017-11-10","cited_by_count":2449},{"id":"2004.10964","title":"Don't Stop Pretraining: Adapt Language Models to Domains and Tasks","created":"2020-04-23","cited_by_count":1565},{"id":"1905.02249","title":"MixMatch: A Holistic Approach to Semi-Supervised Learning","created":"2019-05-06","cited_by_count":1391},{"id":"2401.10891","title":"Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data","created":"2024-01-19","cited_by_count":1360},{"id":"1502.00956","title":"ORB-SLAM: a Versatile and Accurate Monocular SLAM System","created":"2015-02-03","cited_by_count":988},{"id":"2007.11898","title":"ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAM","created":"2020-07-23","cited_by_count":878},{"id":"1610.06475","title":"ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Cameras","created":"2016-10-20","cited_by_count":806},{"id":"1704.07813","title":"Unsupervised Learning of Depth and Ego-Motion from Video","created":"2017-04-25","cited_by_count":782},{"id":"2108.10869","title":"DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras","created":"2021-08-24","cited_by_count":687},{"id":"2003.14338","title":"TartanAir: A Dataset to Push the Limits of Visual SLAM","created":"2020-03-31","cited_by_count":506},{"id":"1607.02565","title":"Direct Sparse Odometry","created":"2016-07-09","cited_by_count":485},{"id":"1812.07179","title":"Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Driving","created":"2018-12-18","cited_by_count":457},{"id":"1606.05830","title":"Past, Present, and Future of Simultaneous Localization And Mapping: Towards the Robust-Perception Age","created":"2016-06-19","cited_by_count":411},{"id":"2404.15506","title":"Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation","created":"2024-03-22","cited_by_count":395},{"id":"2403.18913","title":"UniDepth: Universal Monocular Metric Depth Estimation","created":"2024-03-27","cited_by_count":382},{"id":"2307.10984","title":"Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image","created":"2023-07-20","cited_by_count":365},{"id":"1911.09785","title":"ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring","created":"2019-11-21","cited_by_count":349},{"id":"1803.02276","title":"GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose","created":"2018-03-06","cited_by_count":342},{"id":"1907.07484","title":"Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Coming","created":"2019-07-17","cited_by_count":336},{"id":"2101.06329","title":"In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learning","created":"2021-01-15","cited_by_count":301},{"id":"1603.03925","title":"Image Captioning with Semantic Attention","created":"2016-03-12","cited_by_count":260},{"id":"2103.00550","title":"A Survey on Deep Semi-supervised Learning","created":"2021-02-28","cited_by_count":251},{"id":"1908.10553","title":"Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Video","created":"2019-08-28","cited_by_count":244},{"id":"1905.00546","title":"Billion-scale semi-supervised learning for image classification","created":"2019-05-02","cited_by_count":232},{"id":"1704.00390","title":"Geometric Loss Functions for Camera Pose Regression with Deep Learning","created":"2017-04-02","cited_by_count":224},{"id":"2003.01060","title":"D3VO: Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual Odometry","created":"2020-03-02","cited_by_count":206},{"id":"2204.03610","title":"Unified Contrastive Learning in Image-Text-Label Space","created":"2022-04-07","cited_by_count":194},{"id":"2311.05437","title":"LLaVA-Plus: Learning to Use Tools for Creating Multimodal Agents","created":"2023-11-09","cited_by_count":193},{"id":"2208.04726","title":"Deep Patch Visual Odometry","created":"2022-08-08","cited_by_count":190},{"id":"1802.05522","title":"Unsupervised Learning of Depth and Ego-Motion from Monocular Video Using 3D Geometric Constraints","created":"2018-02-15","cited_by_count":179},{"id":"1709.08429","title":"DeepVO: Towards End-to-End Visual Odometry with Deep Recurrent Convolutional Neural Networks","created":"2017-09-25","cited_by_count":175},{"id":"1806.04807","title":"BA-Net: Dense Bundle Adjustment Network","created":"2018-06-13","cited_by_count":175},{"id":"2405.14793","title":"SEA-RAFT: Simple, Efficient, Accurate RAFT for Optical Flow","created":"2024-05-23","cited_by_count":174},{"id":"2302.03594","title":"NICER-SLAM: Neural Implicit Scene Encoding for RGB SLAM","created":"2023-02-07","cited_by_count":164},{"id":"1803.03893","title":"Unsupervised Learning of Monocular Depth Estimation and Visual Odometry with Deep Feature Reconstruction","created":"2018-03-11","cited_by_count":159},{"id":"2403.09630","title":"GenAD: Generalized Predictive Model for Autonomous Driving","created":"2024-03-14","cited_by_count":150},{"id":"2003.10955","title":"MaskFlownet: Asymmetric Feature Matching with Learnable Occlusion Mask","created":"2020-03-24","cited_by_count":117},{"id":"2106.10456","title":"Humble Teachers Teach Better Students for Semi-Supervised Object Detection","created":"2021-06-19","cited_by_count":116},{"id":"2011.00359","title":"TartanVO: A Generalizable Learning-based VO","created":"2020-10-31","cited_by_count":108},{"id":"2306.17253","title":"Towards Zero-Shot Scale-Aware Monocular Depth Estimation","created":"2023-06-29","cited_by_count":101},{"id":"1804.06120","title":"The TUM VI Benchmark for Evaluating Visual-Inertial Odometry","created":"2018-04-17","cited_by_count":99},{"id":"1709.06841","title":"UnDeepVO: Monocular Visual Odometry through Unsupervised Deep Learning","created":"2017-09-20","cited_by_count":95},{"id":"2012.04355","title":"3DIoUMatch: Leveraging IoU Prediction for Semi-Supervised 3D Object Detection","created":"2020-12-08","cited_by_count":89},{"id":"1809.08370","title":"Semi-Supervised Sequence Modeling with Cross-View Training","created":"2018-09-22","cited_by_count":75},{"id":"2408.01654","title":"Deep Patch Visual SLAM","created":"2024-08-03","cited_by_count":71},{"id":"1903.02749","title":"Deep Visual MPC-Policy Learning for Navigation","created":"2019-03-07","cited_by_count":56},{"id":"2407.00959","title":"Tokenize the World into Object-level Knowledge to Address Long-tail Events in Autonomous Driving","created":"2024-07-01","cited_by_count":56},{"id":"1710.02534","title":"Contrastive Learning for Image Captioning","created":"2017-10-06","cited_by_count":54},{"id":"2311.00571","title":"LLaVA-Interactive: An All-in-One Demo for Image Chat, Segmentation, Generation and Editing","created":"2023-11-01","cited_by_count":47},{"id":"1901.09993","title":"Label Efficient Semi-Supervised Learning via Graph Filtering","created":"2019-01-28","cited_by_count":46},{"id":"1906.02242","title":"Variational Pretraining for Semi-supervised Text Classification","created":"2019-06-05","cited_by_count":41},{"id":"2208.08988","title":"The 8-Point Algorithm as an Inductive Bias for Relative Pose Prediction by ViTs","created":"2022-08-18","cited_by_count":38},{"id":"1812.00124","title":"NOTE-RCNN: NOise Tolerant Ensemble RCNN for Semi-Supervised Object Detection","created":"2018-12-01","cited_by_count":37},{"id":"2006.09740","title":"Probabilistic orientation estimation with matrix Fisher distributions","created":"2020-06-17","cited_by_count":36},{"id":"2005.06136","title":"Self-Supervised Deep Visual Odometry with Online Adaptation","created":"2020-05-13","cited_by_count":35},{"id":"2306.10988","title":"Tame a Wild Camera: In-the-Wild Monocular Camera Calibration","created":"2023-06-19","cited_by_count":34},{"id":"2404.03635","title":"WorDepth: Variational Language Prior for Monocular Depth Estimation","created":"2024-04-04","cited_by_count":34},{"id":"2103.02093","title":"Pseudo-labeling for Scalable 3D Object Detection","created":"2021-03-02","cited_by_count":32},{"id":"2203.15089","title":"Learning Optical Flow, Depth, and Scene Flow without Real-World Labels","created":"2022-03-28","cited_by_count":31},{"id":"1904.01892","title":"Beyond Tracking: Selecting Memory and Refining Poses for Deep Visual Odometry","created":"2019-04-03","cited_by_count":27},{"id":"2207.01610","title":"PVO: Panoptic Visual Odometry","created":"2022-07-04","cited_by_count":26},{"id":"2103.00933","title":"DF-VO: What Should Be Learnt for Visual Odometry?","created":"2021-03-01","cited_by_count":22},{"id":"2002.11281","title":"Generalized Product Quantization Network for Semi-supervised Image Retrieval","created":"2020-02-26","cited_by_count":20},{"id":"2204.10320","title":"SelfD: Self-Learning Large-Scale Driving Policies From the Web","created":"2022-04-21","cited_by_count":18},{"id":"2309.16772","title":"XVO: Generalized Visual Odometry via Cross-Modal Self-Training","created":"2023-09-28","cited_by_count":18},{"id":"2305.13002","title":"Rethinking Semi-supervised Learning with Language Models","created":"2023-05-22","cited_by_count":17},{"id":"2407.15626","title":"Reinforcement Learning Meets Visual Odometry","created":"2024-07-22","cited_by_count":14},{"id":"2008.05938","title":"RGB cameras failures and their effects in autonomous driving applications","created":"2020-08-13","cited_by_count":12},{"id":"2309.12295","title":"Learning to Drive Anywhere","created":"2023-09-21","cited_by_count":10},{"id":"2112.12812","title":"MDN-VO: Estimating Visual Odometry with Confidence","created":"2021-12-23","cited_by_count":6},{"id":"2406.00929","title":"Self-Supervised Geometry-Guided Initialization for Robust Monocular Visual Odometry","created":"2024-06-03","cited_by_count":1}],"next_cursor":null}