{"list":"other","total":52,"rows":[{"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":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"2003.12039","title":"RAFT: Recurrent All-Pairs Field Transforms for Optical Flow","created":"2020-03-26","cited_by_count":2415},{"id":"1709.06158","title":"Matterport3D: Learning from RGB-D Data in Indoor Environments","created":"2017-09-18","cited_by_count":1376},{"id":"1908.03195","title":"LVIS: A Dataset for Large Vocabulary Instance Segmentation","created":"2019-08-08","cited_by_count":1217},{"id":"1804.02748","title":"Scaling Egocentric Vision: The EPIC-KITCHENS Dataset","created":"2018-04-08","cited_by_count":795},{"id":"2007.08501","title":"Accelerating 3D Deep Learning with PyTorch3D","created":"2020-07-16","cited_by_count":784},{"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":"1811.10830","title":"From Recognition to Cognition: Visual Commonsense Reasoning","created":"2018-11-27","cited_by_count":556},{"id":"1604.01753","title":"Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding","created":"2016-04-06","cited_by_count":537},{"id":"2106.14405","title":"Habitat 2.0: Training Home Assistants to Rearrange their Habitat","created":"2021-06-28","cited_by_count":511},{"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":"1701.01370","title":"Learning from Synthetic Humans","created":"2017-01-05","cited_by_count":359},{"id":"2104.08527","title":"PARE: Part Attention Regressor for 3D Human Body Estimation","created":"2021-04-17","cited_by_count":337},{"id":"2006.06669","title":"Understanding Human Hands in Contact at Internet Scale","created":"2020-06-11","cited_by_count":281},{"id":"1704.07333","title":"Detecting and Recognizing Human-Object Interactions","created":"2017-04-24","cited_by_count":199},{"id":"2101.02692","title":"Where2Act: From Pixels to Actions for Articulated 3D Objects","created":"2021-01-07","cited_by_count":182},{"id":"1603.08637","title":"Learning a Predictable and Generative Vector Representation for Objects","created":"2016-03-29","cited_by_count":173},{"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":"1912.11913","title":"Category-Level Articulated Object Pose Estimation","created":"2019-12-26","cited_by_count":159},{"id":"2011.01975","title":"Rearrangement: A Challenge for Embodied AI","created":"2020-11-03","cited_by_count":155},{"id":"1903.03911","title":"Shape2Motion: Joint Analysis of Motion Parts and Attributes from 3D Shapes","created":"2019-03-10","cited_by_count":119},{"id":"2104.07645","title":"A-SDF: Learning Disentangled Signed Distance Functions for Articulated Shape Representation","created":"2021-04-15","cited_by_count":114},{"id":"2004.03686","title":"Exemplar Fine-Tuning for 3D Human Model Fitting Towards In-the-Wild 3D Human Pose Estimation","created":"2020-04-07","cited_by_count":113},{"id":"1812.04072","title":"PlaneRCNN: 3D Plane Detection and Reconstruction from a Single Image","created":"2018-12-10","cited_by_count":105},{"id":"2004.00614","title":"Articulation-aware Canonical Surface Mapping","created":"2020-04-01","cited_by_count":81},{"id":"1804.06278","title":"PlaneNet: Piece-wise Planar Reconstruction from a Single RGB Image","created":"2018-04-17","cited_by_count":77},{"id":"1801.05746","title":"TernausNet: U-Net with VGG11 Encoder Pre-Trained on ImageNet for Image Segmentation","created":"2018-01-17","cited_by_count":76},{"id":"2008.10518","title":"ScrewNet: Category-Independent Articulation Model Estimation From Depth Images Using Screw Theory","created":"2020-08-24","cited_by_count":70},{"id":"2007.13215","title":"OASIS: A Large-Scale Dataset for Single Image 3D in the Wild","created":"2020-07-26","cited_by_count":62},{"id":"1411.4958","title":"Designing Deep Networks for Surface Normal Estimation","created":"2014-11-18","cited_by_count":59},{"id":"1902.09777","title":"Single-Image Piece-wise Planar 3D Reconstruction via Associative Embedding","created":"2019-02-26","cited_by_count":56},{"id":"1908.04781","title":"Predicting 3D Human Dynamics from Video","created":"2019-08-13","cited_by_count":51},{"id":"1712.01812","title":"Factoring Shape, Pose, and Layout from the 2D Image of a 3D Scene","created":"2017-12-05","cited_by_count":50},{"id":"2003.04676","title":"Deep Hough Transform for Semantic Line Detection","created":"2020-03-10","cited_by_count":44},{"id":"1712.02310","title":"From Lifestyle Vlogs to Everyday Interactions","created":"2017-12-06","cited_by_count":42},{"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":"2105.03260","title":"Towards Real-World Category-level Articulation Pose Estimation","created":"2021-05-07","cited_by_count":39},{"id":"2108.08420","title":"D3D-HOI: Dynamic 3D Human-Object Interactions from Videos","created":"2021-08-19","cited_by_count":39},{"id":"1512.00795","title":"Actions ~ Transformations","created":"2015-12-02","cited_by_count":30},{"id":"2008.06046","title":"Full-Body Awareness from Partial Observations","created":"2020-08-13","cited_by_count":29},{"id":"1906.02729","title":"3D-RelNet: Joint Object and Relational Network for 3D Prediction","created":"2019-06-06","cited_by_count":28},{"id":"2007.13727","title":"Associative3D: Volumetric Reconstruction from Sparse Views","created":"2020-07-27","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":"1610.04871","title":"Probabilistic Articulated Real-Time Tracking for Robot Manipulation","created":"2016-10-16","cited_by_count":13}],"next_cursor":null}