{"list":"other","total":64,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024},{"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":"2308.00692","title":"LISA: Reasoning Segmentation via Large Language Model","created":"2023-08-01","cited_by_count":776},{"id":"2308.11417","title":"ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes","created":"2023-08-22","cited_by_count":764},{"id":"2201.03546","title":"Language-driven Semantic Segmentation","created":"2022-01-10","cited_by_count":717},{"id":"2112.01071","title":"Extract Free Dense Labels from CLIP","created":"2021-12-02","cited_by_count":583},{"id":"2211.15654","title":"OpenScene: 3D Scene Understanding with Open Vocabularies","created":"2022-11-28","cited_by_count":559},{"id":"2304.06718","title":"Segment Everything Everywhere All at Once","created":"2023-04-13","cited_by_count":548},{"id":"2303.09553","title":"LERF: Language Embedded Radiance Fields","created":"2023-03-16","cited_by_count":543},{"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":"2311.12871","title":"An Embodied Generalist Agent in 3D World","created":"2023-11-18","cited_by_count":365},{"id":"2302.07241","title":"ConceptFusion: Open-set Multimodal 3D Mapping","created":"2023-02-14","cited_by_count":304},{"id":"2210.03105","title":"Mask3D: Mask Transformer for 3D Semantic Instance Segmentation","created":"2022-10-06","cited_by_count":303},{"id":"2312.02228","title":"PixelLM: Pixel Reasoning with Large Multimodal Model","created":"2023-12-04","cited_by_count":222},{"id":"2308.04352","title":"3D-VisTA: Pre-trained Transformer for 3D Vision and Text Alignment","created":"2023-08-08","cited_by_count":204},{"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":"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":"2312.08168","title":"Chat-Scene: Bridging 3D Scene and Large Language Models with Object Identifiers","created":"2023-12-13","cited_by_count":175},{"id":"2309.05251","title":"Multi3DRefer: Grounding Text Description to Multiple 3D Objects","created":"2023-09-11","cited_by_count":146},{"id":"2011.13244","title":"MVTN: Multi-View Transformation Network for 3D Shape Recognition","created":"2020-11-26","cited_by_count":140},{"id":"2309.12311","title":"LLM-Grounder: Open-Vocabulary 3D Visual Grounding with Large Language Model as an Agent","created":"2023-09-21","cited_by_count":135},{"id":"2308.08769","title":"Chat-3D: Data-efficiently Tuning Large Language Model for Universal Dialogue of 3D Scenes","created":"2023-08-17","cited_by_count":129},{"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},{"id":"2407.11325","title":"VISA: Reasoning Video Object Segmentation via Large Language Models","created":"2024-07-16","cited_by_count":127},{"id":"2306.09347","title":"Segment Any Point Cloud Sequences by Distilling Vision Foundation Models","created":"2023-06-15","cited_by_count":125},{"id":"2312.10671","title":"Open3DIS: Open-Vocabulary 3D Instance Segmentation with 2D Mask Guidance","created":"2023-12-17","cited_by_count":124},{"id":"2405.10370","title":"Grounded 3D-LLM with Referent Tokens","created":"2024-05-16","cited_by_count":115},{"id":"2501.01428","title":"GPT4Scene: Understand 3D Scenes from Videos with Vision-Language Models","created":"2025-01-02","cited_by_count":109},{"id":"2409.19603","title":"One Token to Seg Them All: Language Instructed Reasoning Segmentation in Videos","created":"2024-09-29","cited_by_count":100},{"id":"2209.14941","title":"EDA: Explicit Text-Decoupling and Dense Alignment for 3D Visual Grounding","created":"2022-09-29","cited_by_count":99},{"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":"2303.04748","title":"CLIP-FO3D: Learning Free Open-world 3D Scene Representations from 2D Dense CLIP","created":"2023-03-08","cited_by_count":89},{"id":"2311.02873","title":"OVIR-3D: Open-Vocabulary 3D Instance Retrieval Without Training on 3D Data","created":"2023-11-06","cited_by_count":81},{"id":"2401.07745","title":"MaskClustering: View Consensus based Mask Graph Clustering for Open-Vocabulary 3D Instance Segmentation","created":"2024-01-15","cited_by_count":56},{"id":"2306.03899","title":"Towards Label-free Scene Understanding by Vision Foundation Models","created":"2023-06-06","cited_by_count":54},{"id":"2408.08862","title":"Visual Agents as Fast and Slow Thinkers","created":"2024-08-16","cited_by_count":53},{"id":"2404.08767","title":"LLM-Seg: Bridging Image Segmentation and Large Language Model Reasoning","created":"2024-04-12","cited_by_count":52},{"id":"2405.10255","title":"When LLMs step into the 3D World: A Survey and Meta-Analysis of 3D Tasks via Multi-modal Large Language Models","created":"2024-05-16","cited_by_count":43},{"id":"2308.00353","title":"Lowis3D: Language-Driven Open-World Instance-Level 3D Scene Understanding","created":"2023-08-01","cited_by_count":38},{"id":"2308.16632","title":"3D-STMN: Dependency-Driven Superpoint-Text Matching Network for End-to-End 3D Referring Expression Segmentation","created":"2023-08-31","cited_by_count":36},{"id":"2407.13761","title":"SegPoint: Segment Any Point Cloud via Large Language Model","created":"2024-07-18","cited_by_count":35},{"id":"2312.02546","title":"Machine Vision Therapy: Multimodal Large Language Models Can Enhance Visual Robustness via Denoising In-Context Learning","created":"2023-12-05","cited_by_count":27},{"id":"2111.15363","title":"Voint Cloud: Multi-View Point Cloud Representation for 3D Understanding","created":"2021-11-30","cited_by_count":22},{"id":"2307.10782","title":"See More and Know More: Zero-shot Point Cloud Segmentation via Multi-modal Visual Data","created":"2023-07-20","cited_by_count":21},{"id":"2411.11505","title":"LaVin-DiT: Large Vision Diffusion Transformer","created":"2024-11-18","cited_by_count":21},{"id":"2405.18295","title":"Intent3D: 3D Object Detection in RGB-D Scans Based on Human Intention","created":"2024-05-28","cited_by_count":16},{"id":"2210.09923","title":"Zero-shot point cloud segmentation by transferring geometric primitives","created":"2022-10-18","cited_by_count":9},{"id":"2404.03836","title":"PARIS3D: Reasoning-based 3D Part Segmentation Using Large Multimodal Model","created":"2024-04-04","cited_by_count":9},{"id":"2411.13927","title":"Multimodal 3D Reasoning Segmentation with Complex Scenes","created":"2024-11-21","cited_by_count":8},{"id":"2411.17017","title":"TED-VITON: Transformer-Empowered Diffusion Models for Virtual Try-On","created":"2024-11-26","cited_by_count":8},{"id":"2501.00326","title":"OVGaussian: Generalizable 3D Gaussian Segmentation with Open Vocabularies","created":"2024-12-31","cited_by_count":8},{"id":"2412.03473","title":"UrbanGS: Semantic-Guided Gaussian Splatting for Urban Scene Reconstruction","created":"2024-12-04","cited_by_count":7},{"id":"2407.19988","title":"HeadsetOff: Enabling Photorealistic Video Conferencing on Economical VR Headsets","created":"2024-07-29","cited_by_count":1}],"next_cursor":null}