{"list":"other","total":57,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"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":"1709.06158","title":"Matterport3D: Learning from RGB-D Data in Indoor Environments","created":"2017-09-18","cited_by_count":1376},{"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":"2201.03546","title":"Language-driven Semantic Segmentation","created":"2022-01-10","cited_by_count":717},{"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":"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":"2210.04150","title":"Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP","created":"2022-10-09","cited_by_count":565},{"id":"2112.01518","title":"DenseCLIP: Language-Guided Dense Prediction with Context-Aware Prompting","created":"2021-12-02","cited_by_count":532},{"id":"2202.11094","title":"GroupViT: Semantic Segmentation Emerges from Text Supervision","created":"2022-02-22","cited_by_count":531},{"id":"1812.02713","title":"PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understanding","created":"2018-12-06","cited_by_count":526},{"id":"2112.02413","title":"PointCLIP: Point Cloud Understanding by CLIP","created":"2021-12-04","cited_by_count":463},{"id":"1912.08830","title":"ScanRefer: 3D Object Localization in RGB-D Scans using Natural Language","created":"2019-12-18","cited_by_count":452},{"id":"1702.01105","title":"Joint 2D-3D-Semantic Data for Indoor Scene Understanding","created":"2017-02-03","cited_by_count":406},{"id":"2204.07761","title":"Language-Grounded Indoor 3D Semantic Segmentation in the Wild","created":"2022-04-16","cited_by_count":246},{"id":"2004.03967","title":"Learning 3D Semantic Scene Graphs from 3D Indoor Reconstructions","created":"2020-04-08","cited_by_count":208},{"id":"1908.06109","title":"RIO: 3D Object Instance Re-Localization in Changing Indoor Environments","created":"2019-08-16","cited_by_count":188},{"id":"2003.06537","title":"OccuSeg: Occupancy-aware 3D Instance Segmentation","created":"2020-03-14","cited_by_count":177},{"id":"1807.02443","title":"Tangent Convolutions for Dense Prediction in 3D","created":"2018-07-06","cited_by_count":173},{"id":"2210.05663","title":"CLIP-Fields: Weakly Supervised Semantic Fields for Robotic Memory","created":"2022-10-11","cited_by_count":165},{"id":"2209.15639","title":"F-VLM: Open-Vocabulary Object Detection upon Frozen Vision and Language Models","created":"2022-09-30","cited_by_count":150},{"id":"1609.05130","title":"SemanticFusion: Dense 3D Semantic Mapping with Convolutional Neural Networks","created":"2016-09-16","cited_by_count":135},{"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":"2112.13762","title":"MSeg: A Composite Dataset for Multi-domain Semantic Segmentation","created":"2021-12-27","cited_by_count":122},{"id":"1712.10215","title":"ScanComplete: Large-Scale Scene Completion and Semantic Segmentation for 3D Scans","created":"2017-12-29","cited_by_count":103},{"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":"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":"2209.09385","title":"LidarMultiNet: Towards a Unified Multi-Task Network for LiDAR Perception","created":"2022-09-19","cited_by_count":74},{"id":"1903.05690","title":"Putting Humans in a Scene: Learning Affordance in 3D Indoor Environments","created":"2019-03-13","cited_by_count":72},{"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":"2108.06230","title":"Generative Zero-Shot Learning for Semantic Segmentation of 3D Point Clouds","created":"2021-08-13","cited_by_count":55},{"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":"1912.07161","title":"Transductive Zero-Shot Learning for 3D Point Cloud Classification","created":"2019-12-16","cited_by_count":39},{"id":"2210.15138","title":"Open-vocabulary Semantic Segmentation with Frozen Vision-Language Models","created":"2022-10-27","cited_by_count":39},{"id":"2104.04980","title":"Zero-Shot Learning on 3D Point Cloud Objects and Beyond","created":"2021-04-11","cited_by_count":38},{"id":"1902.10272","title":"Zero-shot Learning of 3D Point Cloud Objects","created":"2019-02-27","cited_by_count":34},{"id":"2207.01887","title":"Open-Vocabulary Multi-Label Classification via Multi-Modal Knowledge Transfer","created":"2022-07-05","cited_by_count":33},{"id":"1907.06371","title":"Mitigating the Hubness Problem for Zero-Shot Learning of 3D Objects","created":"2019-07-15","cited_by_count":24},{"id":"2112.03185","title":"Semantic Segmentation In-the-Wild Without Seeing Any Segmentation Examples","created":"2021-12-06","cited_by_count":24},{"id":"2107.00430","title":"Language-Level Semantics Conditioned 3D Point Cloud Segmentation","created":"2021-07-01","cited_by_count":7}],"next_cursor":null}