{"list":"other","total":52,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1706.02413","title":"PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space","created":"2017-06-07","cited_by_count":4401},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"1912.04838","title":"Scalability in Perception for Autonomous Driving: Waymo Open Dataset","created":"2019-12-10","cited_by_count":2451},{"id":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"id":"2111.12077","title":"Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields","created":"2021-11-23","cited_by_count":2032},{"id":"2103.13415","title":"Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields","created":"2021-03-24","cited_by_count":1964},{"id":"1904.08755","title":"4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks","created":"2019-04-18","cited_by_count":1208},{"id":"2104.13921","title":"Open-vocabulary Object Detection via Vision and Language Knowledge Distillation","created":"2021-04-28","cited_by_count":906},{"id":"1906.05797","title":"The Replica Dataset: A Digital Replica of Indoor Spaces","created":"2019-06-13","cited_by_count":904},{"id":"1612.03716","title":"COCO-Stuff: Thing and Stuff Classes in Context","created":"2016-12-12","cited_by_count":864},{"id":"1801.00868","title":"Panoptic Segmentation","created":"2018-01-03","cited_by_count":802},{"id":"2011.12100","title":"GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fields","created":"2020-11-24","cited_by_count":785},{"id":"2110.06922","title":"DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queries","created":"2021-10-13","cited_by_count":658},{"id":"2011.02523","title":"Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding","created":"2020-11-04","cited_by_count":604},{"id":"2112.01071","title":"Extract Free Dense Labels from CLIP","created":"2021-12-02","cited_by_count":583},{"id":"2109.13410","title":"KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D","created":"2021-09-28","cited_by_count":575},{"id":"2211.15654","title":"OpenScene: 3D Scene Understanding with Open Vocabularies","created":"2022-11-28","cited_by_count":559},{"id":"2112.10003","title":"Image Segmentation Using Text and Image Prompts","created":"2021-12-18","cited_by_count":512},{"id":"2112.12143","title":"Scaling Open-Vocabulary Image Segmentation with Image-Level Labels","created":"2021-12-22","cited_by_count":473},{"id":"1912.08830","title":"ScanRefer: 3D Object Localization in RGB-D Scans using Natural Language","created":"2019-12-18","cited_by_count":452},{"id":"2103.15875","title":"In-Place Scene Labelling and Understanding with Implicit Scene Representation","created":"2021-03-29","cited_by_count":415},{"id":"1702.01105","title":"Joint 2D-3D-Semantic Data for Indoor Scene Understanding","created":"2017-02-03","cited_by_count":406},{"id":"2206.02777","title":"Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentation","created":"2022-06-06","cited_by_count":344},{"id":"2205.04334","title":"Panoptic Neural Fields: A Semantic Object-Aware Neural Scene Representation","created":"2022-05-09","cited_by_count":243},{"id":"2003.06537","title":"OccuSeg: Occupancy-aware 3D Instance Segmentation","created":"2020-03-14","cited_by_count":177},{"id":"2212.09802","title":"Panoptic Lifting for 3D Scene Understanding with Neural Fields","created":"2022-12-19","cited_by_count":174},{"id":"2203.15224","title":"Panoptic NeRF: 3D-to-2D Label Transfer for Panoptic Urban Scene Segmentation","created":"2022-03-29","cited_by_count":152},{"id":"2012.05522","title":"Synthesizing Long-Term 3D Human Motion and Interaction in 3D Scenes","created":"2020-12-10","cited_by_count":135},{"id":"2110.02210","title":"Mix3D: Out-of-Context Data Augmentation for 3D Scenes","created":"2021-10-05","cited_by_count":126},{"id":"2203.16258","title":"Image-to-Lidar Self-Supervised Distillation for Autonomous Driving Data","created":"2022-03-30","cited_by_count":126},{"id":"2103.16397","title":"3D AffordanceNet: A Benchmark for Visual Object Affordance Understanding","created":"2021-03-30","cited_by_count":100},{"id":"2007.13138","title":"Virtual Multi-view Fusion for 3D Semantic Segmentation","created":"2020-07-26","cited_by_count":99},{"id":"1808.08378","title":"Fusion++: Volumetric Object-Level SLAM","created":"2018-08-25","cited_by_count":98},{"id":"1903.01177","title":"PanopticFusion: Online Volumetric Semantic Mapping at the Level of Stuff and Things","created":"2019-03-04","cited_by_count":98},{"id":"1804.09194","title":"MaskFusion: Real-Time Recognition, Tracking and Reconstruction of Multiple Moving Objects","created":"2018-04-24","cited_by_count":95},{"id":"2103.14326","title":"Bidirectional Projection Network for Cross Dimension Scene Understanding","created":"2021-03-26","cited_by_count":95},{"id":"2207.11514","title":"Semantic Abstraction: Open-World 3D Scene Understanding from 2D Vision-Language Models","created":"2022-07-23","cited_by_count":95},{"id":"1903.05690","title":"Putting Humans in a Scene: Learning Affordance in 3D Indoor Environments","created":"2019-03-13","cited_by_count":72},{"id":"2208.07227","title":"DM-NeRF: 3D Scene Geometry Decomposition and Manipulation from 2D Images","created":"2022-08-15","cited_by_count":69},{"id":"2110.11325","title":"Learning 3D Semantic Segmentation with only 2D Image Supervision","created":"2021-10-21","cited_by_count":60},{"id":"2205.07002","title":"Panoptic-PHNet: Towards Real-Time and High-Precision LiDAR Panoptic Segmentation via Clustering Pseudo Heatmap","created":"2022-05-14","cited_by_count":59},{"id":"2204.07548","title":"Learning Multi-View Aggregation In the Wild for Large-Scale 3D Semantic Segmentation","created":"2022-04-15","cited_by_count":47},{"id":"1812.00020","title":"TextureNet: Consistent Local Parametrizations for Learning from High-Resolution Signals on Meshes","created":"2018-11-30","cited_by_count":45},{"id":"2107.02575","title":"Contrastive Multimodal Fusion with TupleInfoNCE","created":"2021-07-06","cited_by_count":43},{"id":"2004.01002","title":"DualConvMesh-Net: Joint Geodesic and Euclidean Convolutions on 3D Meshes","created":"2020-04-02","cited_by_count":42},{"id":"2210.15138","title":"Open-vocabulary Semantic Segmentation with Frozen Vision-Language Models","created":"2022-10-27","cited_by_count":39},{"id":"2207.01887","title":"Open-Vocabulary Multi-Label Classification via Multi-Modal Knowledge Transfer","created":"2022-07-05","cited_by_count":33}],"next_cursor":null}