{"list":"other","total":52,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"1612.00593","title":"PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation","created":"2016-12-02","cited_by_count":5248},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2201.05989","title":"Instant Neural Graphics Primitives with a Multiresolution Hash Encoding","created":"2022-01-16","cited_by_count":3723},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"2111.12077","title":"Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields","created":"2021-11-23","cited_by_count":2032},{"id":"2103.13415","title":"Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields","created":"2021-03-24","cited_by_count":1964},{"id":"2203.09517","title":"TensoRF: Tensorial Radiance Fields","created":"2022-03-17","cited_by_count":1280},{"id":"2212.07143","title":"Reproducible scaling laws for contrastive language-image learning","created":"2022-12-14","cited_by_count":1173},{"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":"2304.06706","title":"Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fields","created":"2023-04-13","cited_by_count":671},{"id":"2201.02605","title":"Detecting Twenty-thousand Classes using Image-level Supervision","created":"2022-01-07","cited_by_count":614},{"id":"2210.04150","title":"Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP","created":"2022-10-09","cited_by_count":565},{"id":"2303.09553","title":"LERF: Language Embedded Radiance Fields","created":"2023-03-16","cited_by_count":543},{"id":"2112.10003","title":"Image Segmentation Using Text and Image Prompts","created":"2021-12-18","cited_by_count":512},{"id":"2201.08845","title":"Point-NeRF: Point-based Neural Radiance Fields","created":"2022-01-21","cited_by_count":503},{"id":"2112.02413","title":"PointCLIP: Point Cloud Understanding by CLIP","created":"2021-12-04","cited_by_count":463},{"id":"2012.09760","title":"End-to-End Human Pose and Mesh Reconstruction with Transformers","created":"2020-12-17","cited_by_count":418},{"id":"2312.16084","title":"LangSplat: 3D Language Gaussian Splatting","created":"2023-12-26","cited_by_count":415},{"id":"2312.02126","title":"SplaTAM: Splat, Track & Map 3D Gaussians for Dense RGB-D SLAM","created":"2023-12-04","cited_by_count":388},{"id":"2205.15585","title":"Decomposing NeRF for Editing via Feature Field Distillation","created":"2022-05-31","cited_by_count":371},{"id":"2309.16650","title":"ConceptGraphs: Open-Vocabulary 3D Scene Graphs for Perception and Planning","created":"2023-09-28","cited_by_count":365},{"id":"2312.03203","title":"Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fields","created":"2023-12-06","cited_by_count":364},{"id":"2111.15174","title":"CRIS: CLIP-Driven Referring Image Segmentation","created":"2021-11-30","cited_by_count":353},{"id":"2112.10482","title":"ScanQA: 3D Question Answering for Spatial Scene Understanding","created":"2021-12-20","cited_by_count":346},{"id":"2112.05814","title":"Deep ViT Features as Dense Visual Descriptors","created":"2021-12-10","cited_by_count":330},{"id":"2205.06230","title":"Simple Open-Vocabulary Object Detection with Vision Transformers","created":"2022-05-12","cited_by_count":305},{"id":"2302.07241","title":"ConceptFusion: Open-set Multimodal 3D Mapping","created":"2023-02-14","cited_by_count":304},{"id":"2306.13631","title":"OpenMask3D: Open-Vocabulary 3D Instance Segmentation","created":"2023-06-23","cited_by_count":289},{"id":"2104.00681","title":"NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Video","created":"2021-04-01","cited_by_count":241},{"id":"1906.04173","title":"Differentiable Surface Splatting for Point-based Geometry Processing","created":"2019-06-10","cited_by_count":239},{"id":"2311.18482","title":"Language Embedded 3D Gaussians for Open-Vocabulary Scene Understanding","created":"2023-11-30","cited_by_count":208},{"id":"2305.08275","title":"ULIP-2: Towards Scalable Multimodal Pre-training for 3D Understanding","created":"2023-05-14","cited_by_count":202},{"id":"2209.03494","title":"Neural Feature Fusion Fields: 3D Distillation of Self-Supervised 2D Image Representations","created":"2022-09-07","cited_by_count":196},{"id":"2210.05663","title":"CLIP-Fields: Weakly Supervised Semantic Fields for Robotic Memory","created":"2022-10-11","cited_by_count":165},{"id":"1712.03316","title":"IQA: Visual Question Answering in Interactive Environments","created":"2017-12-09","cited_by_count":155},{"id":"2305.14093","title":"Weakly Supervised 3D Open-vocabulary Segmentation","created":"2023-05-23","cited_by_count":135},{"id":"2308.16891","title":"GNFactor: Multi-Task Real Robot Learning with Generalizable Neural Feature Fields","created":"2023-08-31","cited_by_count":99},{"id":"1903.01177","title":"PanopticFusion: Online Volumetric Semantic Mapping at the Level of Stuff and Things","created":"2019-03-04","cited_by_count":98},{"id":"2304.00788","title":"Open-Vocabulary Point-Cloud Object Detection without 3D Annotation","created":"2023-04-03","cited_by_count":81},{"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":"1903.00268","title":"Volumetric Instance-Aware Semantic Mapping and 3D Object Discovery","created":"2019-03-01","cited_by_count":80},{"id":"2107.12514","title":"Language Grounding with 3D Objects","created":"2021-07-26","cited_by_count":43},{"id":"2105.07593","title":"Differentiable SLAM-net: Learning Particle SLAM for Visual Navigation","created":"2021-05-17","cited_by_count":34},{"id":"1810.00729","title":"SurfelMeshing: Online Surfel-Based Mesh Reconstruction","created":"2018-10-01","cited_by_count":29},{"id":"2305.12427","title":"VL-Fields: Towards Language-Grounded Neural Implicit Spatial Representations","created":"2023-05-21","cited_by_count":23},{"id":"2309.05448","title":"Panoptic Vision-Language Feature Fields","created":"2023-09-11","cited_by_count":17},{"id":"2205.09710","title":"Voxel-informed Language Grounding","created":"2022-05-19","cited_by_count":11}],"next_cursor":null}