{"list":"other","total":92,"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":"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":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"2001.07685","title":"FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence","created":"2020-01-21","cited_by_count":2085},{"id":"2102.04306","title":"TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation","created":"2021-02-08","cited_by_count":1558},{"id":"1502.03044","title":"Show, Attend and Tell: Neural Image Caption Generation with Visual Attention","created":"2015-02-10","cited_by_count":1423},{"id":"1905.02249","title":"MixMatch: A Holistic Approach to Semi-Supervised Learning","created":"2019-05-06","cited_by_count":1391},{"id":"1705.07115","title":"Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics","created":"2017-05-19","cited_by_count":1358},{"id":"2004.06165","title":"Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks","created":"2020-04-13","cited_by_count":1214},{"id":"1504.06852","title":"FlowNet: Learning Optical Flow with Convolutional Networks","created":"2015-04-26","cited_by_count":1059},{"id":"1609.04747","title":"An overview of gradient descent optimization algorithms","created":"2016-09-15","cited_by_count":1033},{"id":"1705.09406","title":"Multimodal Machine Learning: A Survey and Taxonomy","created":"2017-05-26","cited_by_count":1013},{"id":"1502.00956","title":"ORB-SLAM: a Versatile and Accurate Monocular SLAM System","created":"2015-02-03","cited_by_count":988},{"id":"1709.02371","title":"PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume","created":"2017-09-07","cited_by_count":968},{"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":"1707.08114","title":"A Survey on Multi-Task Learning","created":"2017-07-25","cited_by_count":840},{"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":"2301.00493","title":"Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecasting","created":"2023-01-02","cited_by_count":707},{"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":"1804.08328","title":"Taskonomy: Disentangling Task Transfer Learning","created":"2018-04-23","cited_by_count":634},{"id":"2005.00341","title":"Jukebox: A Generative Model for Music","created":"2020-04-30","cited_by_count":542},{"id":"1906.12340","title":"Using Self-Supervised Learning Can Improve Model Robustness and Uncertainty","created":"2019-06-28","cited_by_count":514},{"id":"1607.02565","title":"Direct Sparse Odometry","created":"2016-07-09","cited_by_count":485},{"id":"1604.03539","title":"Cross-stitch Networks for Multi-task Learning","created":"2016-04-12","cited_by_count":467},{"id":"1905.13736","title":"Unlabeled Data Improves Adversarial Robustness","created":"2019-05-31","cited_by_count":416},{"id":"1803.02276","title":"GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose","created":"2018-03-06","cited_by_count":342},{"id":"1809.02108","title":"Deep Audio-Visual Speech Recognition","created":"2018-09-06","cited_by_count":322},{"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":"2204.01678","title":"MultiMAE: Multi-modal Multi-task Masked Autoencoders","created":"2022-04-04","cited_by_count":291},{"id":"1605.07725","title":"Adversarial Training Methods for Semi-Supervised Text Classification","created":"2016-05-25","cited_by_count":280},{"id":"2103.00550","title":"A Survey on Deep Semi-supervised Learning","created":"2021-02-28","cited_by_count":251},{"id":"1805.09806","title":"Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentation","created":"2018-05-24","cited_by_count":222},{"id":"2203.03884","title":"Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labels","created":"2022-03-08","cited_by_count":218},{"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":"1609.02132","title":"UberNet: Training a `Universal' Convolutional Neural Network for Low-, Mid-, and High-Level Vision using Diverse Datasets and Limited Memory","created":"2016-09-07","cited_by_count":200},{"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":"1904.04998","title":"Depth from Videos in the Wild: Unsupervised Monocular Depth Learning from Unknown Cameras","created":"2019-04-10","cited_by_count":170},{"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":"2103.05346","title":"ST3D: Self-training for Unsupervised Domain Adaptation on 3D Object Detection","created":"2021-03-09","cited_by_count":159},{"id":"1809.01649","title":"DF-Net: Unsupervised Joint Learning of Depth and Flow using Cross-Task Consistency","created":"2018-09-05","cited_by_count":148},{"id":"2003.10955","title":"MaskFlownet: Asymmetric Feature Matching with Learnable Occlusion Mask","created":"2020-03-24","cited_by_count":117},{"id":"1805.06334","title":"Auxiliary Tasks in Multi-task Learning","created":"2018-05-16","cited_by_count":108},{"id":"2011.00359","title":"TartanVO: A Generalizable Learning-based VO","created":"2020-10-31","cited_by_count":108},{"id":"2006.04096","title":"Robust Learning Through Cross-Task Consistency","created":"2020-06-07","cited_by_count":105},{"id":"1712.01393","title":"Visual to Sound: Generating Natural Sound for Videos in the Wild","created":"2017-12-04","cited_by_count":98},{"id":"1912.11684","title":"Look, Listen, and Act: Towards Audio-Visual Embodied Navigation","created":"2019-12-25","cited_by_count":96},{"id":"1709.06841","title":"UnDeepVO: Monocular Visual Odometry through Unsupervised Deep Learning","created":"2017-09-20","cited_by_count":95},{"id":"1901.08933","title":"Self-Supervised Generalisation with Meta Auxiliary Learning","created":"2019-01-25","cited_by_count":88},{"id":"2004.01314","title":"Towards Better Generalization: Joint Depth-Pose Learning without PoseNet","created":"2020-04-03","cited_by_count":85},{"id":"2012.11583","title":"Semantic Audio-Visual Navigation","created":"2020-12-21","cited_by_count":82},{"id":"2301.11757","title":"Mo\\^usai: Text-to-Music Generation with Long-Context Latent Diffusion","created":"2023-01-27","cited_by_count":78},{"id":"2107.11787","title":"Leveraging Auxiliary Tasks with Affinity Learning for Weakly Supervised Semantic Segmentation","created":"2021-07-25","cited_by_count":77},{"id":"2211.13222","title":"SVFormer: Semi-supervised Video Transformer for Action Recognition","created":"2022-11-23","cited_by_count":68},{"id":"1909.09803","title":"Visual Odometry Revisited: What Should Be Learnt?","created":"2019-09-21","cited_by_count":57},{"id":"2111.08380","title":"Video Background Music Generation with Controllable Music Transformer","created":"2021-11-16","cited_by_count":56},{"id":"1908.04051","title":"Semi-Supervised Video Salient Object Detection Using Pseudo-Labels","created":"2019-08-12","cited_by_count":54},{"id":"1901.09993","title":"Label Efficient Semi-Supervised Learning via Graph Filtering","created":"2019-01-28","cited_by_count":46},{"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":"1505.06289","title":"Text to 3D Scene Generation with Rich Lexical Grounding","created":"2015-05-23","cited_by_count":36},{"id":"2006.09740","title":"Probabilistic orientation estimation with matrix Fisher distributions","created":"2020-06-17","cited_by_count":36},{"id":"2005.10091","title":"Label Efficient Visual Abstractions for Autonomous Driving","created":"2020-05-20","cited_by_count":33},{"id":"2103.02093","title":"Pseudo-labeling for Scalable 3D Object Detection","created":"2021-03-02","cited_by_count":32},{"id":"1905.07512","title":"SplitNet: Sim2Sim and Task2Task Transfer for Embodied Visual Navigation","created":"2019-05-18","cited_by_count":29},{"id":"1904.01892","title":"Beyond Tracking: Selecting Memory and Refining Poses for Deep Visual Odometry","created":"2019-04-03","cited_by_count":27},{"id":"2010.00824","title":"Goal-Auxiliary Actor-Critic for 6D Robotic Grasping with Point Clouds","created":"2020-10-02","cited_by_count":24},{"id":"2006.08476","title":"Improving Adversarial Robustness via Unlabeled Out-of-Domain Data","created":"2020-06-15","cited_by_count":23},{"id":"2007.11319","title":"Real-Time Instrument Segmentation in Robotic Surgery using Auxiliary Supervised Deep Adversarial Learning","created":"2020-07-22","cited_by_count":23},{"id":"2106.05966","title":"Learning by Watching","created":"2021-06-10","cited_by_count":22},{"id":"2103.15279","title":"Generalizing to the Open World: Deep Visual Odometry with Online Adaptation","created":"2021-03-29","cited_by_count":19},{"id":"2306.10014","title":"Coaching a Teachable Student","created":"2023-06-16","cited_by_count":19},{"id":"1908.08704","title":"Sequential Adversarial Learning for Self-Supervised Deep Visual Odometry","created":"2019-08-23","cited_by_count":18},{"id":"2204.10320","title":"SelfD: Self-Learning Large-Scale Driving Policies From the Web","created":"2022-04-21","cited_by_count":18},{"id":"1810.01011","title":"CNN-SVO: Improving the Mapping in Semi-Direct Visual Odometry Using Single-Image Depth Prediction","created":"2018-10-01","cited_by_count":17},{"id":"2203.15765","title":"FisherMatch: Semi-Supervised Rotation Regression via Entropy-based Filtering","created":"2022-03-29","cited_by_count":16},{"id":"1910.04755","title":"Measuring robustness of Visual SLAM","created":"2019-10-10","cited_by_count":14},{"id":"2203.03582","title":"Improving CTC-based speech recognition via knowledge transferring from pre-trained language models","created":"2022-02-22","cited_by_count":14},{"id":"2209.15383","title":"Semi-Supervised Single-View 3D Reconstruction via Prototype Shape Priors","created":"2022-09-30","cited_by_count":14},{"id":"2205.14082","title":"AANG: Automating Auxiliary Learning","created":"2022-05-27","cited_by_count":12},{"id":"1804.03789","title":"Geometric Consistency for Self-Supervised End-to-End Visual Odometry","created":"2018-04-11","cited_by_count":11},{"id":"2104.02487","title":"Neural Process for Black-Box Model Optimization Under Bayesian Framework","created":"2021-04-03","cited_by_count":11},{"id":"1811.09935","title":"Guided Feature Selection for Deep Visual Odometry","created":"2018-11-25","cited_by_count":10},{"id":"1812.11971","title":"Mid-Level Visual Representations Improve Generalization and Sample Efficiency for Learning Visuomotor Policies","created":"2018-12-31","cited_by_count":6},{"id":"2112.04011","title":"Auxiliary Learning for Self-Supervised Video Representation via Similarity-based Knowledge Distillation","created":"2021-12-07","cited_by_count":3},{"id":"1907.00276","title":"Stereo relative pose from line and point feature triplets","created":"2019-06-29","cited_by_count":2},{"id":"2008.01942","title":"A feature-supervised generative adversarial network for environmental monitoring during hazy days","created":"2020-08-05","cited_by_count":2}],"next_cursor":null}