{"list":"other","total":66,"rows":[{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1512.03012","title":"ShapeNet: An Information-Rich 3D Model Repository","created":"2015-12-09","cited_by_count":2897},{"id":"2003.12039","title":"RAFT: Recurrent All-Pairs Field Transforms for Optical Flow","created":"2020-03-26","cited_by_count":2415},{"id":"1911.11763","title":"SuperGlue: Learning Feature Matching with Graph Neural Networks","created":"2019-11-26","cited_by_count":1443},{"id":"1904.01201","title":"Habitat: A Platform for Embodied AI Research","created":"2019-04-02","cited_by_count":1191},{"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":"1612.01925","title":"FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks","created":"2016-12-06","cited_by_count":784},{"id":"1912.01734","title":"ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks","created":"2019-12-03","cited_by_count":783},{"id":"1909.12271","title":"RLBench: The Robot Learning Benchmark & Learning Environment","created":"2019-09-26","cited_by_count":689},{"id":"2109.12098","title":"CLIPort: What and Where Pathways for Robotic Manipulation","created":"2021-09-24","cited_by_count":622},{"id":"2003.08515","title":"SAPIEN: A SimulAted Part-based Interactive ENvironment","created":"2020-03-19","cited_by_count":595},{"id":"1808.10654","title":"Gibson Env: Real-World Perception for Embodied Agents","created":"2018-08-31","cited_by_count":481},{"id":"1812.11788","title":"PVNet: Pixel-wise Voting Network for 6DoF Pose Estimation","created":"2018-12-31","cited_by_count":385},{"id":"1901.04780","title":"DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusion","created":"2019-01-15","cited_by_count":355},{"id":"2010.14406","title":"Transporter Networks: Rearranging the Visual World for Robotic Manipulation","created":"2020-10-27","cited_by_count":344},{"id":"1711.11543","title":"Embodied Question Answering","created":"2017-11-30","cited_by_count":336},{"id":"1905.03561","title":"D2-Net: A Trainable CNN for Joint Detection and Description of Local Features","created":"2019-05-09","cited_by_count":326},{"id":"2010.01083","title":"Integrated Task and Motion Planning","created":"2020-10-02","cited_by_count":290},{"id":"2008.08465","title":"CosyPose: Consistent multi-view multi-object 6D pose estimation","created":"2020-08-19","cited_by_count":287},{"id":"1804.00175","title":"DeepIM: Deep Iterative Matching for 6D Pose Estimation","created":"2018-03-31","cited_by_count":283},{"id":"1703.09312","title":"Dex-Net 2.0: Deep Learning to Plan Robust Grasps with Synthetic Point Clouds and Analytic Grasp Metrics","created":"2017-03-27","cited_by_count":264},{"id":"1806.01411","title":"FlowNet3D: Learning Scene Flow in 3D Point Clouds","created":"2018-06-04","cited_by_count":242},{"id":"1905.10520","title":"6-DOF GraspNet: Variational Grasp Generation for Object Manipulation","created":"2019-05-25","cited_by_count":242},{"id":"2104.02409","title":"Learning to Estimate Hidden Motions with Global Motion Aggregation","created":"2021-04-06","cited_by_count":224},{"id":"2103.14127","title":"Contact-GraspNet: Efficient 6-DoF Grasp Generation in Cluttered Scenes","created":"2021-03-25","cited_by_count":218},{"id":"2004.06799","title":"RoboTHOR: An Open Simulation-to-Real Embodied AI Platform","created":"2020-04-14","cited_by_count":193},{"id":"1711.05971","title":"Learning to Find Good Correspondences","created":"2017-11-16","cited_by_count":176},{"id":"1902.01275","title":"Implicit 3D Orientation Learning for 6D Object Detection from RGB Images","created":"2019-02-04","cited_by_count":170},{"id":"2011.01975","title":"Rearrangement: A Challenge for Embodied AI","created":"2020-11-03","cited_by_count":155},{"id":"1806.08756","title":"Dense Object Nets: Learning Dense Visual Object Descriptors By and For Robotic Manipulation","created":"2018-06-22","cited_by_count":142},{"id":"1904.05290","title":"Iterative Residual Refinement for Joint Optical Flow and Occlusion Estimation","created":"2019-04-10","cited_by_count":131},{"id":"2012.01909","title":"Patch2Pix: Epipolar-Guided Pixel-Level Correspondences","created":"2020-12-03","cited_by_count":129},{"id":"2012.00726","title":"RAFT-3D: Scene Flow using Rigid-Motion Embeddings","created":"2020-12-01","cited_by_count":122},{"id":"1804.05172","title":"Closing the Loop for Robotic Grasping: A Real-time, Generative Grasp Synthesis Approach","created":"2018-04-14","cited_by_count":120},{"id":"1906.05332","title":"HPLFlowNet: Hierarchical Permutohedral Lattice FlowNet for Scene Flow Estimation on Large-scale Point Clouds","created":"2019-06-12","cited_by_count":109},{"id":"2103.16544","title":"Visual Room Rearrangement","created":"2021-03-30","cited_by_count":102},{"id":"2104.11213","title":"ManipulaTHOR: A Framework for Visual Object Manipulation","created":"2021-04-22","cited_by_count":102},{"id":"2104.14544","title":"AutoFlow: Learning a Better Training Set for Optical Flow","created":"2021-04-29","cited_by_count":102},{"id":"1912.00497","title":"Just Go with the Flow: Self-Supervised Scene Flow Estimation","created":"2019-12-01","cited_by_count":98},{"id":"2012.03385","title":"Learning to Rearrange Deformable Cables, Fabrics, and Bags with Goal-Conditioned Transporter Networks","created":"2020-12-06","cited_by_count":78},{"id":"2105.07014","title":"SMURF: Self-Teaching Multi-Frame Unsupervised RAFT with Full-Image Warping","created":"2021-05-14","cited_by_count":74},{"id":"2004.04143","title":"Self-Supervised Monocular Scene Flow Estimation","created":"2020-04-08","cited_by_count":64},{"id":"2007.15157","title":"Learning RGB-D Feature Embeddings for Unseen Object Instance Segmentation","created":"2020-07-30","cited_by_count":64},{"id":"1911.04577","title":"Online Replanning in Belief Space for Partially Observable Task and Motion Problems","created":"2019-11-11","cited_by_count":61},{"id":"2102.08945","title":"Weakly Supervised Learning of Rigid 3D Scene Flow","created":"2021-02-17","cited_by_count":60},{"id":"2110.10189","title":"StructFormer: Learning Spatial Structure for Language-Guided Semantic Rearrangement of Novel Objects","created":"2021-10-19","cited_by_count":59},{"id":"1904.08913","title":"Deep Rigid Instance Scene Flow","created":"2019-04-18","cited_by_count":54},{"id":"2012.00212","title":"UPFlow: Upsampling Pyramid for Unsupervised Optical Flow Learning","created":"2020-12-01","cited_by_count":49},{"id":"2006.05398","title":"Deep Visual Reasoning: Learning to Predict Action Sequences for Task and Motion Planning from an Initial Scene Image","created":"2020-06-09","cited_by_count":48},{"id":"2011.10726","title":"Object Rearrangement Using Learned Implicit Collision Functions","created":"2020-11-21","cited_by_count":43},{"id":"1804.04259","title":"Learning Rigidity in Dynamic Scenes with a Moving Camera for 3D Motion Field Estimation","created":"2018-04-12","cited_by_count":38},{"id":"1910.12361","title":"SENSE: a Shared Encoder Network for Scene-flow Estimation","created":"2019-10-27","cited_by_count":38},{"id":"2106.01352","title":"NeRP: Neural Rearrangement Planning for Unknown Objects","created":"2021-06-02","cited_by_count":34},{"id":"2012.01634","title":"Rel3D: A Minimally Contrastive Benchmark for Grounding Spatial Relations in 3D","created":"2020-12-03","cited_by_count":30},{"id":"2105.02216","title":"Self-Supervised Multi-Frame Monocular Scene Flow","created":"2021-05-05","cited_by_count":29},{"id":"2104.03965","title":"Learning optical flow from still images","created":"2021-04-08","cited_by_count":28},{"id":"2111.03112","title":"My House, My Rules: Learning Tidying Preferences with Graph Neural Networks","created":"2021-11-04","cited_by_count":27},{"id":"2010.06491","title":"Broadly-Exploring, Local-Policy Trees for Long-Horizon Task Planning","created":"2020-10-13","cited_by_count":26},{"id":"1904.10348","title":"Monte-Carlo Tree Search for Efficient Visually Guided Rearrangement Planning","created":"2019-04-23","cited_by_count":24},{"id":"2104.11446","title":"OCRTOC: A Cloud-Based Competition and Benchmark for Robotic Grasping and Manipulation","created":"2021-04-23","cited_by_count":24},{"id":"2105.13962","title":"NViSII: A Scriptable Tool for Photorealistic Image Generation","created":"2021-05-28","cited_by_count":24},{"id":"2108.12062","title":"Predicting Stable Configurations for Semantic Placement of Novel Objects","created":"2021-08-26","cited_by_count":24},{"id":"2011.08177","title":"A Long Horizon Planning Framework for Manipulating Rigid Pointcloud Objects","created":"2020-11-16","cited_by_count":23},{"id":"2007.11121","title":"PackIt: A Virtual Environment for Geometric Planning","created":"2020-07-21","cited_by_count":10}],"next_cursor":null}