{"list":"other","total":71,"rows":[{"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":"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":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1606.04797","title":"V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation","created":"2016-06-15","cited_by_count":2292},{"id":"2006.10739","title":"Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains","created":"2020-06-18","cited_by_count":2200},{"id":"2103.13413","title":"Vision Transformers for Dense Prediction","created":"2021-03-24","cited_by_count":1803},{"id":"1902.09630","title":"Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression","created":"2019-02-25","cited_by_count":1368},{"id":"1908.03195","title":"LVIS: A Dataset for Large Vocabulary Instance Segmentation","created":"2019-08-08","cited_by_count":1217},{"id":"1812.07035","title":"On the Continuity of Rotation Representations in Neural Networks","created":"2018-12-17","cited_by_count":1214},{"id":"2107.06278","title":"Per-Pixel Classification is Not All You Need for Semantic Segmentation","created":"2021-07-13","cited_by_count":1152},{"id":"1801.00868","title":"Panoptic Segmentation","created":"2018-01-03","cited_by_count":802},{"id":"2007.08501","title":"Accelerating 3D Deep Learning with PyTorch3D","created":"2020-07-16","cited_by_count":784},{"id":"1808.01244","title":"CornerNet: Detecting Objects as Paired Keypoints","created":"2018-08-03","cited_by_count":763},{"id":"1708.02002","title":"Focal Loss for Dense Object Detection","created":"2017-08-07","cited_by_count":752},{"id":"1804.00607","title":"MegaDepth: Learning Single-View Depth Prediction from Internet Photos","created":"2018-04-02","cited_by_count":737},{"id":"1804.08328","title":"Taskonomy: Disentangling Task Transfer Learning","created":"2018-04-23","cited_by_count":634},{"id":"2003.08515","title":"SAPIEN: A SimulAted Part-based Interactive ENvironment","created":"2020-03-19","cited_by_count":595},{"id":"1604.00449","title":"3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction","created":"2016-04-02","cited_by_count":588},{"id":"2006.13256","title":"Rescaling Egocentric Vision","created":"2020-06-23","cited_by_count":540},{"id":"1411.4734","title":"Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecture","created":"2014-11-18","cited_by_count":483},{"id":"1912.08193","title":"PointRend: Image Segmentation as Rendering","created":"2019-12-17","cited_by_count":440},{"id":"2110.04994","title":"Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets from 3D Scans","created":"2021-10-11","cited_by_count":336},{"id":"2006.06669","title":"Understanding Human Hands in Contact at Internet Scale","created":"2020-06-11","cited_by_count":281},{"id":"1810.01566","title":"Learning Particle Dynamics for Manipulating Rigid Bodies, Deformable Objects, and Fluids","created":"2018-10-03","cited_by_count":220},{"id":"2012.09365","title":"Learning to Recover 3D Scene Shape from a Single Image","created":"2020-12-17","cited_by_count":216},{"id":"1704.07333","title":"Detecting and Recognizing Human-Object Interactions","created":"2017-04-24","cited_by_count":199},{"id":"1604.03605","title":"What do different evaluation metrics tell us about saliency models?","created":"2016-04-12","cited_by_count":185},{"id":"2101.02692","title":"Where2Act: From Pixels to Actions for Articulated 3D Objects","created":"2021-01-07","cited_by_count":182},{"id":"2002.12212","title":"Total3DUnderstanding: Joint Layout, Object Pose and Mesh Reconstruction for Indoor Scenes from a Single Image","created":"2020-02-27","cited_by_count":172},{"id":"2207.09450","title":"Human-to-Robot Imitation in the Wild","created":"2022-07-19","cited_by_count":161},{"id":"2207.10660","title":"Omni3D: A Large Benchmark and Model for 3D Object Detection in the Wild","created":"2022-07-21","cited_by_count":160},{"id":"1912.11913","title":"Category-Level Articulated Object Pose Estimation","created":"2019-12-26","cited_by_count":159},{"id":"2202.08227","title":"Ditto: Building Digital Twins of Articulated Objects from Interaction","created":"2022-02-16","cited_by_count":156},{"id":"1812.04558","title":"Grounded Human-Object Interaction Hotspots from Video","created":"2018-12-11","cited_by_count":129},{"id":"2104.07645","title":"A-SDF: Learning Disentangled Signed Distance Functions for Articulated Shape Representation","created":"2021-04-15","cited_by_count":114},{"id":"1812.04072","title":"PlaneRCNN: 3D Plane Detection and Reconstruction from a Single Image","created":"2018-12-10","cited_by_count":105},{"id":"2211.12498","title":"Touch and Go: Learning from Human-Collected Vision and Touch","created":"2022-11-22","cited_by_count":87},{"id":"2203.09905","title":"Learning Affordance Grounding from Exocentric Images","created":"2022-03-18","cited_by_count":82},{"id":"2106.14440","title":"VAT-Mart: Learning Visual Action Trajectory Proposals for Manipulating 3D ARTiculated Objects","created":"2021-06-28","cited_by_count":80},{"id":"1804.06278","title":"PlaneNet: Piece-wise Planar Reconstruction from a Single RGB Image","created":"2018-04-17","cited_by_count":77},{"id":"2303.09665","title":"LOCATE: Localize and Transfer Object Parts for Weakly Supervised Affordance Grounding","created":"2023-03-16","cited_by_count":64},{"id":"1411.4958","title":"Designing Deep Networks for Surface Normal Estimation","created":"2014-11-18","cited_by_count":59},{"id":"2112.00246","title":"AdaAfford: Learning to Adapt Manipulation Affordance for 3D Articulated Objects via Few-shot Interactions","created":"2021-12-01","cited_by_count":57},{"id":"2203.16421","title":"OPD: Single-view 3D Openable Part Detection","created":"2022-03-30","cited_by_count":54},{"id":"2112.09120","title":"Human Hands as Probes for Interactive Object Understanding","created":"2021-12-16","cited_by_count":52},{"id":"2205.08525","title":"Self-supervised Neural Articulated Shape and Appearance Models","created":"2022-05-17","cited_by_count":51},{"id":"2003.04676","title":"Deep Hough Transform for Semantic Line Detection","created":"2020-03-10","cited_by_count":44},{"id":"2302.01295","title":"Ditto in the House: Building Articulation Models of Indoor Scenes through Interactive Perception","created":"2023-02-02","cited_by_count":41},{"id":"1405.7705","title":"A Probabilistic Framework for Learning Kinematic Models of Articulated Objects","created":"2014-01-16","cited_by_count":40},{"id":"2103.14644","title":"Planar Surface Reconstruction from Sparse Views","created":"2021-03-26","cited_by_count":40},{"id":"2303.14087","title":"OPDMulti: Openable Part Detection for Multiple Objects","created":"2023-03-24","cited_by_count":39},{"id":"2203.16531","title":"Understanding 3D Object Articulation in Internet Videos","created":"2022-03-30","cited_by_count":36},{"id":"2109.07107","title":"Anchor DETR: Query Design for Transformer-Based Object Detection","created":"2021-09-15","cited_by_count":30},{"id":"1806.09573","title":"Learning Single-Image Depth from Videos using Quality Assessment Networks","created":"2018-06-25","cited_by_count":25},{"id":"2203.01197","title":"DextAIRity: Deformable Manipulation Can be a Breeze","created":"2022-03-02","cited_by_count":18},{"id":"1502.01659","title":"Learning Articulated Motions From Visual Demonstration","created":"2015-02-05","cited_by_count":17},{"id":"1812.03647","title":"Factored Pose Estimation of Articulated Objects using Efficient Nonparametric Belief Propagation","created":"2018-12-10","cited_by_count":16},{"id":"2101.00733","title":"Occlusion-robust Deformable Object Tracking without Physics Simulation","created":"2021-01-04","cited_by_count":15},{"id":"2005.08165","title":"Three-Filters-to-Normal: An Accurate and Ultrafast Surface Normal Estimator","created":"2020-05-17","cited_by_count":14},{"id":"1610.04871","title":"Probabilistic Articulated Real-Time Tracking for Robot Manipulation","created":"2016-10-16","cited_by_count":13},{"id":"2011.00627","title":"Tracking Partially-Occluded Deformable Objects while Enforcing Geometric Constraints","created":"2020-11-01","cited_by_count":12},{"id":"2209.05612","title":"Articulated 3D Human-Object Interactions from RGB Videos: An Empirical Analysis of Approaches and Challenges","created":"2022-09-12","cited_by_count":8},{"id":"2207.07077","title":"Egocentric Scene Understanding via Multimodal Spatial Rectifier","created":"2022-07-14","cited_by_count":7},{"id":"2212.12952","title":"Neural Shape Compiler: A Unified Framework for Transforming between Text, Point Cloud, and Program","created":"2022-12-25","cited_by_count":6},{"id":"2303.01484","title":"Predicting Motion Plans for Articulating Everyday Objects","created":"2023-03-02","cited_by_count":5}],"next_cursor":null}