{"list":"other","total":58,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"2502.14786","title":"SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features","created":"2025-02-20","cited_by_count":1188},{"id":"1612.00603","title":"A Point Set Generation Network for 3D Object Reconstruction from a Single Image","created":"2016-12-02","cited_by_count":979},{"id":"2303.15389","title":"EVA-CLIP: Improved Training Techniques for CLIP at Scale","created":"2023-03-27","cited_by_count":798},{"id":"2308.11417","title":"ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes","created":"2023-08-22","cited_by_count":764},{"id":"2109.08238","title":"Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AI","created":"2021-09-16","cited_by_count":592},{"id":"1911.10127","title":"BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networks","created":"2019-11-22","cited_by_count":490},{"id":"2112.02413","title":"PointCLIP: Point Cloud Understanding by CLIP","created":"2021-12-04","cited_by_count":463},{"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":"1912.08830","title":"ScanRefer: 3D Object Localization in RGB-D Scans using Natural Language","created":"2019-12-18","cited_by_count":452},{"id":"2312.16084","title":"LangSplat: 3D Language Gaussian Splatting","created":"2023-12-26","cited_by_count":415},{"id":"2206.06994","title":"ProcTHOR: Large-Scale Embodied AI Using Procedural Generation","created":"2022-06-14","cited_by_count":380},{"id":"2112.10482","title":"ScanQA: 3D Question Answering for Spatial Scene Understanding","created":"2021-12-20","cited_by_count":346},{"id":"2210.07474","title":"SQA3D: Situated Question Answering in 3D Scenes","created":"2022-10-14","cited_by_count":314},{"id":"1908.00222","title":"Structured3D: A Large Photo-realistic Dataset for Structured 3D Modeling","created":"2019-08-01","cited_by_count":286},{"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},{"id":"2103.04918","title":"A Survey of Embodied AI: From Simulators to Research Tasks","created":"2021-03-08","cited_by_count":261},{"id":"2309.17425","title":"Data Filtering Networks","created":"2023-09-29","cited_by_count":250},{"id":"2310.06773","title":"Uni3D: Exploring Unified 3D Representation at Scale","created":"2023-10-10","cited_by_count":237},{"id":"2012.02206","title":"Scan2Cap: Context-aware Dense Captioning in RGB-D Scans","created":"2020-12-03","cited_by_count":218},{"id":"2012.09165","title":"Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts","created":"2020-12-16","cited_by_count":210},{"id":"2308.04352","title":"3D-VisTA: Pre-trained Transformer for 3D Vision and Text Alignment","created":"2023-08-08","cited_by_count":204},{"id":"2305.08275","title":"ULIP-2: Towards Scalable Multimodal Pre-training for 3D Understanding","created":"2023-05-14","cited_by_count":202},{"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},{"id":"1908.06109","title":"RIO: 3D Object Instance Re-Localization in Changing Indoor Environments","created":"2019-08-16","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":"2305.10764","title":"OpenShape: Scaling Up 3D Shape Representation Towards Open-World Understanding","created":"2023-05-18","cited_by_count":184},{"id":"2301.04926","title":"CLIP2Scene: Towards Label-efficient 3D Scene Understanding by CLIP","created":"2023-01-12","cited_by_count":181},{"id":"1710.07563","title":"SEGCloud: Semantic Segmentation of 3D Point Clouds","created":"2017-10-20","cited_by_count":179},{"id":"2211.16312","title":"PLA: Language-Driven Open-Vocabulary 3D Scene Understanding","created":"2022-11-29","cited_by_count":177},{"id":"2210.01055","title":"CLIP2Point: Transfer CLIP to Point Cloud Classification with Image-Depth Pre-training","created":"2022-10-03","cited_by_count":160},{"id":"2412.00493","title":"Video-3D LLM: Learning Position-Aware Video Representation for 3D Scene Understanding","created":"2024-11-30","cited_by_count":138},{"id":"2401.09340","title":"SceneVerse: Scaling 3D Vision-Language Learning for Grounded Scene Understanding","created":"2024-01-17","cited_by_count":133},{"id":"2304.00962","title":"RegionPLC: Regional Point-Language Contrastive Learning for Open-World 3D Scene Understanding","created":"2023-04-03","cited_by_count":94},{"id":"2505.05071","title":"FG-CLIP: Fine-Grained Visual and Textual Alignment","created":"2025-05-08","cited_by_count":81},{"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":"2503.18052","title":"SceneSplat: Gaussian Splatting-based Scene Understanding with Vision-Language Pretraining","created":"2025-03-23","cited_by_count":52},{"id":"2507.07136","title":"LangSplatV2: High-dimensional 3D Language Gaussian Splatting with 450+ FPS","created":"2025-07-09","cited_by_count":41},{"id":"2412.08802","title":"jina-clip-v2: Multilingual Multimodal Embeddings for Text and Images","created":"2024-12-11","cited_by_count":37},{"id":"2103.05423","title":"Deep Learning Based 3D Segmentation: A Survey","created":"2021-03-09","cited_by_count":30},{"id":"2504.14151","title":"Locate 3D: Real-World Object Localization via Self-Supervised Learning in 3D","created":"2025-04-19","cited_by_count":23},{"id":"2310.17914","title":"3D-Aware Visual Question Answering about Parts, Poses and Occlusions","created":"2023-10-27","cited_by_count":16},{"id":"2404.14249","title":"CLIP-GS: CLIP-Informed Gaussian Splatting for View-Consistent 3D Indoor Semantic Understanding","created":"2024-04-22","cited_by_count":16},{"id":"2404.14565","title":"\"Where am I?\" Scene Retrieval with Language","created":"2024-04-22","cited_by_count":15},{"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},{"id":"2406.11579","title":"Duoduo CLIP: Efficient 3D Understanding with Multi-View Images","created":"2024-06-17","cited_by_count":12},{"id":"2502.15011","title":"CrossOver: 3D Scene Cross-Modal Alignment","created":"2025-02-20","cited_by_count":12},{"id":"2502.00342","title":"Embodied Intelligence for 3D Understanding: A Survey on 3D Scene Question Answering","created":"2025-02-01","cited_by_count":11},{"id":"2404.16538","title":"OpenDlign: Open-World Point Cloud Understanding with Depth-Aligned Images","created":"2024-04-25","cited_by_count":9},{"id":"2407.10200","title":"Shape2Scene: 3D Scene Representation Learning Through Pre-training on Shape Data","created":"2024-07-14","cited_by_count":8},{"id":"2412.19142","title":"CLIP-GS: Unifying Vision-Language Representation with 3D Gaussian Splatting","created":"2024-12-26","cited_by_count":7},{"id":"2502.00954","title":"Hypo3D: Exploring Hypothetical Reasoning in 3D","created":"2025-02-02","cited_by_count":5},{"id":"2511.16567","title":"POMA-3D: The Point Map Way to 3D Scene Understanding","created":"2025-11-20","cited_by_count":4},{"id":"2502.10674","title":"Occlusion-aware Text-Image-Point Cloud Pretraining for Open-World 3D Object Recognition","created":"2025-02-15","cited_by_count":2},{"id":"2603.27455","title":"From None to All: Self-Supervised 3D Reconstruction via Novel View Synthesis","created":"2026-03-29","cited_by_count":2},{"id":"2412.05274","title":"SimC3D: A Simple Contrastive 3D Pretraining Framework Using RGB Images","created":"2024-12-06","cited_by_count":1}],"next_cursor":null}