{"list":"other","total":70,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"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":"1612.03144","title":"Feature Pyramid Networks for Object Detection","created":"2016-12-09","cited_by_count":5036},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"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":"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":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"2312.14132","title":"DUSt3R: Geometric 3D Vision Made Easy","created":"2023-12-21","cited_by_count":1567},{"id":"1907.01341","title":"Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer","created":"2019-07-02","cited_by_count":1495},{"id":"2401.10891","title":"Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data","created":"2024-01-19","cited_by_count":1360},{"id":"2203.17270","title":"BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers","created":"2022-03-31","cited_by_count":1218},{"id":"2401.14159","title":"Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks","created":"2024-01-25","cited_by_count":929},{"id":"1912.13192","title":"PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection","created":"2019-12-31","cited_by_count":891},{"id":"1904.09664","title":"Deep Hough Voting for 3D Object Detection in Point Clouds","created":"2019-04-21","cited_by_count":648},{"id":"2211.15654","title":"OpenScene: 3D Scene Understanding with Open Vocabularies","created":"2022-11-28","cited_by_count":559},{"id":"2303.09553","title":"LERF: Language Embedded Radiance Fields","created":"2023-03-16","cited_by_count":543},{"id":"1812.07179","title":"Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Driving","created":"2018-12-18","cited_by_count":457},{"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},{"id":"1707.06484","title":"Deep Layer Aggregation","created":"2017-07-20","cited_by_count":436},{"id":"2403.18913","title":"UniDepth: Universal Monocular Metric Depth Estimation","created":"2024-03-27","cited_by_count":382},{"id":"2307.10984","title":"Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image","created":"2023-07-20","cited_by_count":365},{"id":"2109.08141","title":"An End-to-End Transformer Model for 3D Object Detection","created":"2021-09-16","cited_by_count":329},{"id":"2303.11926","title":"Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object Detection","created":"2023-03-21","cited_by_count":315},{"id":"2211.10439","title":"BEVFormer v2: Adapting Modern Image Backbones to Bird's-Eye-View Recognition via Perspective Supervision","created":"2022-11-18","cited_by_count":302},{"id":"2306.13631","title":"OpenMask3D: Open-Vocabulary 3D Instance Segmentation","created":"2023-06-23","cited_by_count":289},{"id":"1612.00496","title":"3D Bounding Box Estimation Using Deep Learning and Geometry","created":"2016-12-01","cited_by_count":278},{"id":"1907.06038","title":"M3D-RPN: Monocular 3D Region Proposal Network for Object Detection","created":"2019-07-13","cited_by_count":252},{"id":"2108.06417","title":"Is Pseudo-Lidar needed for Monocular 3D Object detection?","created":"2021-08-13","cited_by_count":249},{"id":"2012.11409","title":"3D Object Detection with Pointformer","created":"2020-12-21","cited_by_count":194},{"id":"1906.06310","title":"Pseudo-LiDAR++: Accurate Depth for 3D Object Detection in Autonomous Driving","created":"2019-06-14","cited_by_count":188},{"id":"2211.11682","title":"PointCLIP V2: Prompting CLIP and GPT for Powerful 3D Open-world Learning","created":"2022-11-21","cited_by_count":187},{"id":"2301.04926","title":"CLIP2Scene: Towards Label-efficient 3D Scene Understanding by CLIP","created":"2023-01-12","cited_by_count":181},{"id":"2211.16312","title":"PLA: Language-Driven Open-Vocabulary 3D Scene Understanding","created":"2022-11-29","cited_by_count":177},{"id":"2207.10660","title":"Omni3D: A Large Benchmark and Model for 3D Object Detection in the Wild","created":"2022-07-21","cited_by_count":160},{"id":"2106.01178","title":"ImVoxelNet: Image to Voxels Projection for Monocular and Multi-View General-Purpose 3D Object Detection","created":"2021-06-02","cited_by_count":157},{"id":"2103.10039","title":"RangeDet:In Defense of Range View for LiDAR-based 3D Object Detection","created":"2021-03-18","cited_by_count":140},{"id":"2103.15297","title":"LiDAR R-CNN: An Efficient and Universal 3D Object Detector","created":"2021-03-29","cited_by_count":129},{"id":"1903.09847","title":"Monocular 3D Object Detection with Pseudo-LiDAR Point Cloud","created":"2019-03-23","cited_by_count":113},{"id":"2306.17253","title":"Towards Zero-Shot Scale-Aware Monocular Depth Estimation","created":"2023-06-29","cited_by_count":101},{"id":"2405.04390","title":"DriveWorld: 4D Pre-trained Scene Understanding via World Models for Autonomous Driving","created":"2024-05-07","cited_by_count":93},{"id":"2307.01848","title":"Embodied Task Planning with Large Language Models","created":"2023-07-04","cited_by_count":84},{"id":"2304.00788","title":"Open-Vocabulary Point-Cloud Object Detection without 3D Annotation","created":"2023-04-03","cited_by_count":81},{"id":"2004.03080","title":"End-to-End Pseudo-LiDAR for Image-Based 3D Object Detection","created":"2020-04-07","cited_by_count":80},{"id":"2004.05679","title":"MLCVNet: Multi-Level Context VoteNet for 3D Object Detection","created":"2020-04-12","cited_by_count":80},{"id":"2303.12417","title":"CLIP$^2$: Contrastive Language-Image-Point Pretraining from Real-World Point Cloud Data","created":"2023-03-22","cited_by_count":69},{"id":"2102.00690","title":"Ground-aware Monocular 3D Object Detection for Autonomous Driving","created":"2021-02-01","cited_by_count":65},{"id":"2312.17232","title":"Segment3D: Learning Fine-Grained Class-Agnostic 3D Segmentation without Manual Labels","created":"2023-12-28","cited_by_count":64},{"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},{"id":"2112.01001","title":"SEAL: Self-supervised Embodied Active Learning using Exploration and 3D Consistency","created":"2021-12-02","cited_by_count":48},{"id":"2404.03181","title":"MonoCD: Monocular 3D Object Detection with Complementary Depths","created":"2024-04-04","cited_by_count":39},{"id":"2206.07372","title":"MonoGround: Detecting Monocular 3D Objects from the Ground","created":"2022-06-15","cited_by_count":37},{"id":"2305.15694","title":"Learning Occupancy for Monocular 3D Object Detection","created":"2023-05-25","cited_by_count":36},{"id":"2308.04409","title":"V-DETR: DETR with Vertex Relative Position Encoding for 3D Object Detection","created":"2023-08-08","cited_by_count":35},{"id":"2309.09456","title":"Object2Scene: Putting Objects in Context for Open-Vocabulary 3D Detection","created":"2023-09-18","cited_by_count":24},{"id":"2312.08876","title":"OpenSight: A Simple Open-Vocabulary Framework for LiDAR-Based Object Detection","created":"2023-12-12","cited_by_count":22},{"id":"2403.13556","title":"Find n' Propagate: Open-Vocabulary 3D Object Detection in Urban Environments","created":"2024-03-20","cited_by_count":21},{"id":"1910.01210","title":"Embodied Language Grounding with 3D Visual Feature Representations","created":"2019-10-02","cited_by_count":20},{"id":"2101.06594","title":"PLUMENet: Efficient 3D Object Detection from Stereo Images","created":"2021-01-17","cited_by_count":19},{"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},{"id":"2203.08332","title":"WeakM3D: Towards Weakly Supervised Monocular 3D Object Detection","created":"2022-03-16","cited_by_count":18},{"id":"2303.08686","title":"Weakly Supervised Monocular 3D Object Detection using Multi-View Projection and Direction Consistency","created":"2023-03-15","cited_by_count":18},{"id":"2403.17387","title":"Decoupled Pseudo-labeling for Semi-Supervised Monocular 3D Object Detection","created":"2024-03-26","cited_by_count":11},{"id":"1912.12101","title":"A 3D-Deep-Learning-based Augmented Reality Calibration Method for Robotic Environments using Depth Sensor Data","created":"2019-12-27","cited_by_count":10},{"id":"2201.08812","title":"DeepMix: Mobility-aware, Lightweight, and Hybrid 3D Object Detection for Headsets","created":"2022-01-15","cited_by_count":10},{"id":"2402.19144","title":"Weakly Supervised Monocular 3D Detection with a Single-View Image","created":"2024-02-29","cited_by_count":10},{"id":"2303.13561","title":"MoGDE: Boosting Mobile Monocular 3D Object Detection with Ground Depth Estimation","created":"2023-03-23","cited_by_count":9},{"id":"2306.05418","title":"Weakly Supervised 3D Object Detection with Multi-Stage Generalization","created":"2023-06-08","cited_by_count":2}],"next_cursor":null}