{"total":199,"rows":[{"id":"2111.08897","title":"ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Data","created":"2021-11-17","cited_by_count":454,"area":null},{"id":"2202.07123","title":"Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework","created":"2022-02-15","cited_by_count":379,"area":null},{"id":"2210.03105","title":"Mask3D: Mask Transformer for 3D Semantic Instance Segmentation","created":"2022-10-06","cited_by_count":303,"area":null},{"id":"2212.05171","title":"ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understanding","created":"2022-12-10","cited_by_count":267,"area":null},{"id":"2305.08275","title":"ULIP-2: Towards Scalable Multimodal Pre-training for 3D Understanding","created":"2023-05-14","cited_by_count":202,"area":null},{"id":"2309.00615","title":"Point-Bind & Point-LLM: Aligning Point Cloud with Multi-modality for 3D Understanding, Generation, and Instruction Following","created":"2023-09-01","cited_by_count":194,"area":null},{"id":"2203.14508","title":"Stratified Transformer for 3D Point Cloud Segmentation","created":"2022-03-28","cited_by_count":167,"area":null},{"id":"2207.13080","title":"DETRs with Hybrid Matching","created":"2022-07-26","cited_by_count":150,"area":null},{"id":"2312.16170","title":"EmbodiedScan: A Holistic Multi-Modal 3D Perception Suite Towards Embodied AI","created":"2023-12-26","cited_by_count":147,"area":null},{"id":"2204.08721","title":"Multimodal Token Fusion for Vision Transformers","created":"2022-04-19","cited_by_count":136,"area":null},{"id":"2206.09474","title":"3D Object Detection for Autonomous Driving: A Comprehensive Survey","created":"2022-06-19","cited_by_count":132,"area":null},{"id":"2112.08879","title":"Bottom Up Top Down Detection Transformers for Language Grounding in Images and Point Clouds","created":"2021-12-16","cited_by_count":128,"area":null},{"id":"2209.05324","title":"Delving into the Devils of Bird's-eye-view Perception: A Review, Evaluation and Recipe","created":"2022-09-12","cited_by_count":122,"area":null},{"id":"2211.09646","title":"Language Conditioned Spatial Relation Reasoning for 3D Object Grounding","created":"2022-11-17","cited_by_count":122,"area":null},{"id":"2301.06051","title":"DSVT: Dynamic Sparse Voxel Transformer with Rotated Sets","created":"2023-01-15","cited_by_count":122,"area":null},{"id":"2111.06091","title":"A Survey of Visual Transformers","created":"2021-11-11","cited_by_count":117,"area":null},{"id":"2405.10370","title":"Grounded 3D-LLM with Referent Tokens","created":"2024-05-16","cited_by_count":115,"area":null},{"id":"2203.13250","title":"Global Tracking Transformers","created":"2022-03-24","cited_by_count":110,"area":null},{"id":"2204.06272","title":"3D-SPS: Single-Stage 3D Visual Grounding via Referred Point Progressive Selection","created":"2022-04-13","cited_by_count":110,"area":null},{"id":"2305.03045","title":"OctFormer: Octree-based Transformers for 3D Point Clouds","created":"2023-05-04","cited_by_count":109,"area":null},{"id":"2203.10314","title":"Voxel Set Transformer: A Set-to-Set Approach to 3D Object Detection from Point Clouds","created":"2022-03-19","cited_by_count":102,"area":null},{"id":"2206.08356","title":"OmniMAE: Single Model Masked Pretraining on Images and Videos","created":"2022-06-16","cited_by_count":99,"area":null},{"id":"2209.05588","title":"CenterFormer: Center-based Transformer for 3D Object Detection","created":"2022-09-12","cited_by_count":99,"area":null},{"id":"2209.14941","title":"EDA: Explicit Text-Decoupling and Dense Alignment for 3D Visual Grounding","created":"2022-09-29","cited_by_count":99,"area":null},{"id":"2112.00322","title":"FCAF3D: Fully Convolutional Anchor-Free 3D Object Detection","created":"2021-12-01","cited_by_count":97,"area":null},{"id":"2205.05740","title":"Surface Representation for Point Clouds","created":"2022-05-11","cited_by_count":84,"area":null},{"id":"2301.02508","title":"End-to-End 3D Dense Captioning with Vote2Cap-DETR","created":"2023-01-06","cited_by_count":78,"area":null},{"id":"2311.15383","title":"Visual Programming for Zero-shot Open-Vocabulary 3D Visual Grounding","created":"2023-11-26","cited_by_count":64,"area":null},{"id":"2210.04264","title":"CAGroup3D: Class-Aware Grouping for 3D Object Detection on Point Clouds","created":"2022-10-09","cited_by_count":58,"area":null},{"id":"2308.04556","title":"FocalFormer3D : Focusing on Hard Instance for 3D Object Detection","created":"2023-08-08","cited_by_count":58,"area":null},{"id":"2212.03010","title":"GD-MAE: Generative Decoder for MAE Pre-training on LiDAR Point Clouds","created":"2022-12-06","cited_by_count":57,"area":null},{"id":"2303.08129","title":"PiMAE: Point Cloud and Image Interactive Masked Autoencoders for 3D Object Detection","created":"2023-03-14","cited_by_count":53,"area":null},{"id":"2310.02960","title":"CoDA: Collaborative Novel Box Discovery and Cross-modal Alignment for Open-vocabulary 3D Object Detection","created":"2023-10-04","cited_by_count":52,"area":null},{"id":"2112.11088","title":"EPNet++: Cascade Bi-directional Fusion for Multi-Modal 3D Object Detection","created":"2021-12-21","cited_by_count":49,"area":null},{"id":"2203.11937","title":"4D-OR: Semantic Scene Graphs for OR Domain Modeling","created":"2022-03-22","cited_by_count":49,"area":null},{"id":"2405.07784","title":"Generating Human Motion in 3D Scenes from Text Descriptions","created":"2024-05-13","cited_by_count":49,"area":null},{"id":"2403.13129","title":"Better Call SAL: Towards Learning to Segment Anything in Lidar","created":"2024-03-19","cited_by_count":47,"area":null},{"id":"2201.00785","title":"Implicit Autoencoder for Point-Cloud Self-Supervised Representation Learning","created":"2022-01-03","cited_by_count":46,"area":null},{"id":"2211.11646","title":"NeRF-RPN: A general framework for object detection in NeRFs","created":"2022-11-21","cited_by_count":46,"area":null},{"id":"2309.01692","title":"Mask-Attention-Free Transformer for 3D Instance Segmentation","created":"2023-09-04","cited_by_count":46,"area":null},{"id":"2311.17707","title":"SAMPro3D: Locating SAM Prompts in 3D for Zero-Shot Instance Segmentation","created":"2023-11-29","cited_by_count":44,"area":null},{"id":"2112.08359","title":"3D Question Answering","created":"2021-12-15","cited_by_count":41,"area":null},{"id":"2204.02251","title":"RBGNet: Ray-based Grouping for 3D Object Detection","created":"2022-04-05","cited_by_count":40,"area":null},{"id":"2204.10688","title":"Spatiality-guided Transformer for 3D Dense Captioning on Point Clouds","created":"2022-04-22","cited_by_count":40,"area":null},{"id":"2309.02999","title":"Vote2Cap-DETR++: Decoupling Localization and Describing for End-to-End 3D Dense Captioning","created":"2023-09-06","cited_by_count":39,"area":null},{"id":"2308.04409","title":"V-DETR: DETR with Vertex Relative Position Encoding for 3D Object Detection","created":"2023-08-08","cited_by_count":35,"area":null},{"id":"2203.01252","title":"A Unified Query-based Paradigm for Point Cloud Understanding","created":"2022-03-02","cited_by_count":32,"area":null},{"id":"2204.00325","title":"CAT-Det: Contrastively Augmented Transformer for Multi-modal 3D Object Detection","created":"2022-04-01","cited_by_count":32,"area":null},{"id":"2302.02858","title":"TR3D: Towards Real-Time Indoor 3D Object Detection","created":"2023-02-06","cited_by_count":32,"area":null},{"id":"2205.07417","title":"Transformers in 3D Point Clouds: A Survey","created":"2022-05-16","cited_by_count":31,"area":null},{"id":"2303.13357","title":"POTTER: Pooling Attention Transformer for Efficient Human Mesh Recovery","created":"2023-03-23","cited_by_count":31,"area":null},{"id":"2211.08542","title":"CXTrack: Improving 3D Point Cloud Tracking with Contextual Information","created":"2022-11-12","cited_by_count":28,"area":null},{"id":"2310.05699","title":"Uni3DETR: Unified 3D Detection Transformer","created":"2023-10-09","cited_by_count":27,"area":null},{"id":"2109.05566","title":"PQ-Transformer: Jointly Parsing 3D Objects and Layouts from Point Clouds","created":"2021-09-12","cited_by_count":26,"area":null},{"id":"2307.13363","title":"3DRP-Net: 3D Relative Position-aware Network for 3D Visual Grounding","created":"2023-07-25","cited_by_count":25,"area":null},{"id":"2406.05785","title":"A Survey on Text-guided 3D Visual Grounding: Elements, Recent Advances, and Future Directions","created":"2024-06-09","cited_by_count":25,"area":null},{"id":"2407.18244","title":"RefMask3D: Language-Guided Transformer for 3D Referring Segmentation","created":"2024-07-25","cited_by_count":25,"area":null},{"id":"2309.09456","title":"Object2Scene: Putting Objects in Context for Open-Vocabulary 3D Detection","created":"2023-09-18","cited_by_count":24,"area":null},{"id":"2111.13087","title":"BoxeR: Box-Attention for 2D and 3D Transformers","created":"2021-11-25","cited_by_count":23,"area":null},{"id":"2207.01987","title":"Open-Vocabulary 3D Detection via Image-level Class and Debiased Cross-modal Contrastive Learning","created":"2022-07-05","cited_by_count":23,"area":null},{"id":"2111.12608","title":"Cerberus Transformer: Joint Semantic, Affordance and Attribute Parsing","created":"2021-11-24","cited_by_count":22,"area":null},{"id":"2111.15363","title":"Voint Cloud: Multi-View Point Cloud Representation for 3D Understanding","created":"2021-11-30","cited_by_count":22,"area":null},{"id":"2204.13630","title":"Rotationally Equivariant 3D Object Detection","created":"2022-04-28","cited_by_count":21,"area":null},{"id":"2208.04309","title":"3D Vision with Transformers: A Survey","created":"2022-08-08","cited_by_count":21,"area":null},{"id":"2210.12755","title":"LCPFormer: Towards Effective 3D Point Cloud Analysis via Local Context Propagation in Transformers","created":"2022-10-23","cited_by_count":21,"area":null},{"id":"2305.06621","title":"PVT-SSD: Single-Stage 3D Object Detector with Point-Voxel Transformer","created":"2023-05-11","cited_by_count":21,"area":null},{"id":"2203.16832","title":"Point Scene Understanding via Disentangled Instance Mesh Reconstruction","created":"2022-03-31","cited_by_count":20,"area":null},{"id":"2210.01391","title":"Bridged Transformer for Vision and Point Cloud 3D Object Detection","created":"2022-10-04","cited_by_count":20,"area":null},{"id":"2407.05363","title":"Multi-branch Collaborative Learning Network for 3D Visual Grounding","created":"2024-07-07","cited_by_count":20,"area":null},{"id":"2409.04234","title":"UniDet3D: Multi-dataset Indoor 3D Object Detection","created":"2024-09-06","cited_by_count":20,"area":null},{"id":"2305.12497","title":"PanoContext-Former: Panoramic Total Scene Understanding with a Transformer","created":"2023-05-21","cited_by_count":19,"area":null},{"id":"2312.14465","title":"FM-OV3D: Foundation Model-based Cross-modal Knowledge Blending for Open-Vocabulary 3D Detection","created":"2023-12-22","cited_by_count":19,"area":null},{"id":"2403.19580","title":"OV-Uni3DETR: Towards Unified Open-Vocabulary 3D Object Detection via Cycle-Modality Propagation","created":"2024-03-28","cited_by_count":19,"area":null},{"id":"2204.11911","title":"DArch: Dental Arch Prior-assisted 3D Tooth Instance Segmentation","created":"2022-04-25","cited_by_count":18,"area":null},{"id":"2210.03925","title":"Contextual Modeling for 3D Dense Captioning on Point Clouds","created":"2022-10-08","cited_by_count":18,"area":null},{"id":"2307.09267","title":"Distilling Coarse-to-Fine Semantic Matching Knowledge for Weakly Supervised 3D Visual Grounding","created":"2023-07-18","cited_by_count":18,"area":null},{"id":"2407.20664","title":"3D-GRES: Generalized 3D Referring Expression Segmentation","created":"2024-07-30","cited_by_count":18,"area":null},{"id":"2203.05238","title":"Back to Reality: Weakly-supervised 3D Object Detection with Shape-guided Label Enhancement","created":"2022-03-10","cited_by_count":17,"area":null},{"id":"2406.00830","title":"Collaborative Novel Object Discovery and Box-Guided Cross-Modal Alignment for Open-Vocabulary 3D Object Detection","created":"2024-06-02","cited_by_count":17,"area":null},{"id":"2410.24001","title":"ImOV3D: Learning Open-Vocabulary Point Clouds 3D Object Detection from Only 2D Images","created":"2024-10-31","cited_by_count":17,"area":null},{"id":"2502.10392","title":"TSP3D: Text-guided Sparse Voxel Pruning for Efficient 3D Visual Grounding","created":"2025-02-14","cited_by_count":17,"area":null},{"id":"2207.01821","title":"Toward Explainable and Fine-Grained 3D Grounding through Referring Textual Phrases","created":"2022-07-05","cited_by_count":16,"area":null},{"id":"2303.15654","title":"Few-Shot 3D Point Cloud Semantic Segmentation via Stratified Class-Specific Attention Based Transformer Network","created":"2023-03-28","cited_by_count":16,"area":null},{"id":"2304.13031","title":"DQS3D: Densely-matched Quantization-aware Semi-supervised 3D Detection","created":"2023-04-25","cited_by_count":16,"area":null},{"id":"2312.11112","title":"ConDaFormer: Disassembled Transformer with Local Structure Enhancement for 3D Point Cloud Understanding","created":"2023-12-18","cited_by_count":16,"area":null},{"id":"2405.18295","title":"Intent3D: 3D Object Detection in RGB-D Scans Based on Human Intention","created":"2024-05-28","cited_by_count":16,"area":null},{"id":"2305.07299","title":"An Object SLAM Framework for Association, Mapping, and High-Level Tasks","created":"2023-05-12","cited_by_count":15,"area":null},{"id":"2309.02224","title":"Dense Object Grounding in 3D Scenes","created":"2023-09-05","cited_by_count":15,"area":null},{"id":"2408.11567","title":"Positional Prompt Tuning for Efficient 3D Representation Learning","created":"2024-08-21","cited_by_count":15,"area":null},{"id":"2204.05599","title":"HyperDet3D: Learning a Scene-conditioned 3D Object Detector","created":"2022-04-12","cited_by_count":14,"area":null},{"id":"2210.05593","title":"Prototypical VoteNet for Few-Shot 3D Point Cloud Object Detection","created":"2022-10-11","cited_by_count":14,"area":null},{"id":"2211.06004","title":"A Comprehensive Survey of Transformers for Computer Vision","created":"2022-11-11","cited_by_count":14,"area":null},{"id":"2211.09375","title":"3D-QueryIS: A Query-based Framework for 3D Instance Segmentation","created":"2022-11-17","cited_by_count":14,"area":null},{"id":"2305.19623","title":"Point-GCC: Universal Self-supervised 3D Scene Pre-training via Geometry-Color Contrast","created":"2023-05-31","cited_by_count":14,"area":null},{"id":"2307.16605","title":"VPP: Efficient Conditional 3D Generation via Voxel-Point Progressive Representation","created":"2023-07-28","cited_by_count":14,"area":null},{"id":"2308.09098","title":"ImGeoNet: Image-induced Geometry-aware Voxel Representation for Multi-view 3D Object Detection","created":"2023-08-17","cited_by_count":14,"area":null},{"id":"2407.05256","title":"Unlocking Textual and Visual Wisdom: Open-Vocabulary 3D Object Detection Enhanced by Comprehensive Guidance from Text and Image","created":"2024-07-07","cited_by_count":14,"area":null},{"id":"2305.05026","title":"Self-supervised Pre-training with Masked Shape Prediction for 3D Scene Understanding","created":"2023-05-08","cited_by_count":13,"area":null},{"id":"2402.19463","title":"SeMoLi: What Moves Together Belongs Together","created":"2024-02-29","cited_by_count":13,"area":null},{"id":"2212.09948","title":"MM-3DScene: 3D Scene Understanding by Customizing Masked Modeling with Informative-Preserved Reconstruction and Self-Distilled Consistency","created":"2022-12-20","cited_by_count":12,"area":null}],"next_cursor":"100"}