{"list":"other","total":60,"rows":[{"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":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"2303.05499","title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","created":"2023-03-09","cited_by_count":3332},{"id":"2312.14132","title":"DUSt3R: Geometric 3D Vision Made Easy","created":"2023-12-21","cited_by_count":1567},{"id":"2303.11328","title":"Zero-1-to-3: Zero-shot One Image to 3D Object","created":"2023-03-20","cited_by_count":1489},{"id":"2212.07143","title":"Reproducible scaling laws for contrastive language-image learning","created":"2022-12-14","cited_by_count":1173},{"id":"1906.03327","title":"HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips","created":"2019-06-07","cited_by_count":950},{"id":"1711.00199","title":"PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenes","created":"2017-11-01","cited_by_count":775},{"id":"2310.15008","title":"Wonder3D: Single Image to 3D using Cross-Domain Diffusion","created":"2023-10-23","cited_by_count":689},{"id":"2302.12288","title":"ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth","created":"2023-02-23","cited_by_count":657},{"id":"2111.14819","title":"Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling","created":"2021-11-29","cited_by_count":653},{"id":"2204.11918","title":"Google Scanned Objects: A High-Quality Dataset of 3D Scanned Household Items","created":"2022-04-25","cited_by_count":612},{"id":"2006.13256","title":"Rescaling Egocentric Vision","created":"2020-06-23","cited_by_count":540},{"id":"2307.07635","title":"CoTracker: It is Better to Track Together","created":"2023-07-14","cited_by_count":522},{"id":"1901.02970","title":"Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimation","created":"2019-01-09","cited_by_count":495},{"id":"1704.06888","title":"Time-Contrastive Networks: Self-Supervised Learning from Video","created":"2017-04-23","cited_by_count":459},{"id":"2312.08344","title":"FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects","created":"2023-12-13","cited_by_count":429},{"id":"1904.05767","title":"Learning joint reconstruction of hands and manipulated objects","created":"2019-04-11","cited_by_count":378},{"id":"2306.01567","title":"Segment Anything in High Quality","created":"2023-06-02","cited_by_count":376},{"id":"2312.13150","title":"Splatter Image: Ultra-Fast Single-View 3D Reconstruction","created":"2023-12-20","cited_by_count":364},{"id":"2112.05814","title":"Deep ViT Features as Dense Visual Descriptors","created":"2021-12-10","cited_by_count":330},{"id":"2306.12156","title":"Fast Segment Anything","created":"2023-06-21","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":"1701.05498","title":"T-LESS: An RGB-D Dataset for 6D Pose Estimation of Texture-less Objects","created":"2017-01-19","cited_by_count":210},{"id":"2212.06870","title":"MegaPose: 6D Pose Estimation of Novel Objects via Render & Compare","created":"2022-12-13","cited_by_count":201},{"id":"2009.07378","title":"BOP Challenge 2020 on 6D Object Localization","created":"2020-09-15","cited_by_count":193},{"id":"2305.10764","title":"OpenShape: Scaling Up 3D Shape Representation Towards Open-World Understanding","created":"2023-05-18","cited_by_count":184},{"id":"2205.12257","title":"OnePose: One-Shot Object Pose Estimation without CAD Models","created":"2022-05-24","cited_by_count":157},{"id":"2007.15649","title":"Perceiving 3D Human-Object Spatial Arrangements from a Single Image in the Wild","created":"2020-07-30","cited_by_count":152},{"id":"2102.12145","title":"GDRNPP: A Geometry-guided and Fully Learning-based Object Pose Estimator","created":"2021-02-24","cited_by_count":148},{"id":"2303.14158","title":"BundleSDF: Neural 6-DoF Tracking and 3D Reconstruction of Unknown Objects","created":"2023-03-24","cited_by_count":148},{"id":"2012.09856","title":"Reconstructing Hand-Object Interactions in the Wild","created":"2020-12-17","cited_by_count":144},{"id":"2007.12107","title":"Few-Shot Object Detection and Viewpoint Estimation for Objects in the Wild","created":"2020-07-23","cited_by_count":142},{"id":"1812.01537","title":"A micro Lie theory for state estimation in robotics","created":"2018-12-04","cited_by_count":124},{"id":"2301.07673","title":"OnePose++: Keypoint-Free One-Shot Object Pose Estimation without CAD Models","created":"2023-01-18","cited_by_count":115},{"id":"2311.14155","title":"GigaPose: Fast and Robust Novel Object Pose Estimation via One Correspondence","created":"2023-11-23","cited_by_count":114},{"id":"2311.18809","title":"FoundPose: Unseen Object Pose Estimation with Foundation Features","created":"2023-11-30","cited_by_count":109},{"id":"2108.00516","title":"BundleTrack: 6D Pose Tracking for Novel Objects without Instance or Category-Level 3D Models","created":"2021-08-01","cited_by_count":87},{"id":"2307.11067","title":"CNOS: A Strong Baseline for CAD-based Novel Object Segmentation","created":"2023-07-20","cited_by_count":87},{"id":"2203.05701","title":"6-DoF Pose Estimation of Household Objects for Robotic Manipulation: An Accessible Dataset and Benchmark","created":"2022-03-11","cited_by_count":86},{"id":"2203.14628","title":"FS6D: Few-Shot 6D Pose Estimation of Novel Objects","created":"2022-03-28","cited_by_count":81},{"id":"2207.13691","title":"ShAPO: Implicit Representations for Multi-Object Shape, Appearance, and Pose Optimization","created":"2022-07-27","cited_by_count":72},{"id":"2403.09799","title":"BOP Challenge 2023 on Detection, Segmentation and Pose Estimation of Seen and Unseen Rigid Objects","created":"2024-03-14","cited_by_count":60},{"id":"2203.17234","title":"Templates for 3D Object Pose Estimation Revisited: Generalization to New Objects and Robustness to Occlusions","created":"2022-03-31","cited_by_count":54},{"id":"2404.19664","title":"Towards Generalist Robot Learning from Internet Video: A Survey","created":"2024-04-30","cited_by_count":40},{"id":"2211.13225","title":"Learning to Imitate Object Interactions from Internet Videos","created":"2022-11-23","cited_by_count":34},{"id":"2404.06507","title":"Reconstructing Hand-Held Objects in 3D from Images and Videos","created":"2024-04-09","cited_by_count":24},{"id":"2311.00750","title":"Are These the Same Apple? Comparing Images Based on Object Intrinsics","created":"2023-11-01","cited_by_count":19},{"id":"2103.13539","title":"Multi-View Fusion for Multi-Level Robotic Scene Understanding","created":"2021-03-25","cited_by_count":17},{"id":"2203.08472","title":"Fusing Local Similarities for Retrieval-based 3D Orientation Estimation of Unseen Objects","created":"2022-03-16","cited_by_count":17},{"id":"2306.13266","title":"Shape-Constraint Recurrent Flow for 6D Object Pose Estimation","created":"2023-06-23","cited_by_count":17},{"id":"2405.17859","title":"Adapting Pre-Trained Vision Models for Novel Instance Detection and Segmentation","created":"2024-05-28","cited_by_count":17},{"id":"2011.06813","title":"Learning Object Manipulation Skills via Approximate State Estimation from Real Videos","created":"2020-11-13","cited_by_count":12},{"id":"2111.01591","title":"Estimating 3D Motion and Forces of Human-Object Interactions from Internet Videos","created":"2021-11-02","cited_by_count":9},{"id":"2412.01052","title":"CRISP: Object Pose and Shape Estimation with Test-Time Adaptation","created":"2024-12-02","cited_by_count":9},{"id":"1508.00835","title":"Semantic Pose using Deep Networks Trained on Synthetic RGB-D","created":"2015-08-04","cited_by_count":6},{"id":"2111.03088","title":"Learning to Manipulate Tools by Aligning Simulation to Video Demonstration","created":"2021-11-04","cited_by_count":5}],"next_cursor":null}