{"list":"other","total":88,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"1706.02413","title":"PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space","created":"2017-06-07","cited_by_count":4401},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2011.10566","title":"Exploring Simple Siamese Representation Learning","created":"2020-11-20","cited_by_count":2866},{"id":"2106.10689","title":"NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction","created":"2021-06-20","cited_by_count":1712},{"id":"1911.11763","title":"SuperGlue: Learning Feature Matching with Graph Neural Networks","created":"2019-11-26","cited_by_count":1443},{"id":"2006.10029","title":"Big Self-Supervised Models are Strong Semi-Supervised Learners","created":"2020-06-17","cited_by_count":1380},{"id":"2106.12052","title":"Volume Rendering of Neural Implicit Surfaces","created":"2021-06-22","cited_by_count":996},{"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":"2309.16588","title":"Vision Transformers Need Registers","created":"2023-09-28","cited_by_count":871},{"id":"1904.09664","title":"Deep Hough Voting for 3D Object Detection in Point Clouds","created":"2019-04-21","cited_by_count":648},{"id":"2112.12130","title":"NICE-SLAM: Neural Implicit Scalable Encoding for SLAM","created":"2021-12-22","cited_by_count":589},{"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":"2111.11426","title":"Neural Fields in Visual Computing and Beyond","created":"2021-11-22","cited_by_count":540},{"id":"2007.10985","title":"PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding","created":"2020-07-21","cited_by_count":504},{"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":"2306.03881","title":"Emergent Correspondence from Image Diffusion","created":"2023-06-06","cited_by_count":446},{"id":"2204.07118","title":"DeiT III: Revenge of the ViT","created":"2022-04-14","cited_by_count":419},{"id":"2103.15875","title":"In-Place Scene Labelling and Understanding with Implicit Scene Representation","created":"2021-03-29","cited_by_count":415},{"id":"2011.09127","title":"3D-FRONT: 3D Furnished Rooms with layOuts and semaNTics","created":"2020-11-18","cited_by_count":380},{"id":"2310.17596","title":"MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrations","created":"2023-10-26","cited_by_count":327},{"id":"2009.09633","title":"3D-FUTURE: 3D Furniture shape with TextURE","created":"2020-09-21","cited_by_count":311},{"id":"2208.00277","title":"MobileNeRF: Exploiting the Polygon Rasterization Pipeline for Efficient Neural Field Rendering on Mobile Architectures","created":"2022-07-30","cited_by_count":311},{"id":"2104.12229","title":"Vector Neurons: A General Framework for SO(3)-Equivariant Networks","created":"2021-04-25","cited_by_count":305},{"id":"2210.03105","title":"Mask3D: Mask Transformer for 3D Semantic Instance Segmentation","created":"2022-10-06","cited_by_count":303},{"id":"1910.02527","title":"3D Scene Graph: A Structure for Unified Semantics, 3D Space, and Camera","created":"2019-10-06","cited_by_count":281},{"id":"2112.05124","title":"Neural Descriptor Fields: SE(3)-Equivariant Object Representations for Manipulation","created":"2021-12-09","cited_by_count":209},{"id":"2004.03967","title":"Learning 3D Semantic Scene Graphs from 3D Indoor Reconstructions","created":"2020-04-08","cited_by_count":208},{"id":"1908.06109","title":"RIO: 3D Object Instance Re-Localization in Changing Indoor Environments","created":"2019-08-16","cited_by_count":188},{"id":"2304.14377","title":"Co-SLAM: Joint Coordinate and Sparse Parametric Encodings for Neural Real-Time SLAM","created":"2023-04-27","cited_by_count":184},{"id":"2404.08636","title":"Probing the 3D Awareness of Visual Foundation Models","created":"2024-04-12","cited_by_count":177},{"id":"2210.05663","title":"CLIP-Fields: Weakly Supervised Semantic Fields for Robotic Memory","created":"2022-10-11","cited_by_count":165},{"id":"2306.03908","title":"SAM3D: Segment Anything in 3D Scenes","created":"2023-06-06","cited_by_count":157},{"id":"1908.10543","title":"SPair-71k: A Large-scale Benchmark for Semantic Correspondence","created":"2019-08-28","cited_by_count":146},{"id":"2407.01512","title":"Open-TeleVision: Teleoperation with Immersive Active Visual Feedback","created":"2024-07-01","cited_by_count":145},{"id":"1811.11187","title":"Scan2CAD: Learning CAD Model Alignment in RGB-D Scans","created":"2018-11-27","cited_by_count":142},{"id":"2401.09340","title":"SceneVerse: Scaling 3D Vision-Language Learning for Grounded Scene Understanding","created":"2024-01-17","cited_by_count":133},{"id":"2308.07931","title":"Distilled Feature Fields Enable Few-Shot Language-Guided Manipulation","created":"2023-07-27","cited_by_count":130},{"id":"2410.07408","title":"Automated Creation of Digital Cousins for Robust Policy Learning","created":"2024-10-09","cited_by_count":91},{"id":"2311.17034","title":"Telling Left from Right: Identifying Geometry-Aware Semantic Correspondence","created":"2023-11-28","cited_by_count":86},{"id":"2401.17053","title":"BlockFusion: Expandable 3D Scene Generation using Latent Tri-plane Extrapolation","created":"2024-01-30","cited_by_count":83},{"id":"2004.05679","title":"MLCVNet: Multi-Level Context VoteNet for 3D Object Detection","created":"2020-04-12","cited_by_count":80},{"id":"2402.12259","title":"Open3DSG: Open-Vocabulary 3D Scene Graphs from Point Clouds with Queryable Objects and Open-Set Relationships","created":"2024-02-19","cited_by_count":80},{"id":"2303.10598","title":"StyleRF: Zero-shot 3D Style Transfer of Neural Radiance Fields","created":"2023-03-19","cited_by_count":79},{"id":"2301.09629","title":"LEGO-Net: Learning Regular Rearrangements of Objects in Rooms","created":"2023-01-23","cited_by_count":76},{"id":"2401.07487","title":"Robo-ABC: Affordance Generalization Beyond Categories via Semantic Correspondence for Robot Manipulation","created":"2024-01-15","cited_by_count":71},{"id":"2206.14735","title":"GO-Surf: Neural Feature Grid Optimization for Fast, High-Fidelity RGB-D Surface Reconstruction","created":"2022-06-29","cited_by_count":61},{"id":"2105.06464","title":"DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box Supervision","created":"2021-05-13","cited_by_count":59},{"id":"1908.06537","title":"Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Features","created":"2019-08-18","cited_by_count":56},{"id":"2406.02537","title":"TopViewRS: Vision-Language Models as Top-View Spatial Reasoners","created":"2024-06-04","cited_by_count":49},{"id":"2407.20727","title":"SceneTeller: Language-to-3D Scene Generation","created":"2024-07-30","cited_by_count":43},{"id":"1702.00926","title":"FCSS: Fully Convolutional Self-Similarity for Dense Semantic Correspondence","created":"2017-02-03","cited_by_count":42},{"id":"2211.01600","title":"nerf2nerf: Pairwise Registration of Neural Radiance Fields","created":"2022-11-03","cited_by_count":39},{"id":"2309.16118","title":"D$^3$Fields: Dynamic 3D Descriptor Fields for Zero-Shot Generalizable Rearrangement","created":"2023-09-28","cited_by_count":35},{"id":"2103.16942","title":"Neural Surface Maps","created":"2021-03-31","cited_by_count":34},{"id":"2412.05268","title":"DenseMatcher: Learning 3D Semantic Correspondence for Category-Level Manipulation from a Single Demo","created":"2024-12-06","cited_by_count":34},{"id":"1810.12155","title":"Recurrent Transformer Networks for Semantic Correspondence","created":"2018-10-29","cited_by_count":32},{"id":"2210.02689","title":"Neural Matching Fields: Implicit Representation of Matching Fields for Visual Correspondence","created":"2022-10-06","cited_by_count":32},{"id":"2304.14880","title":"SGAligner : 3D Scene Alignment with Scene Graphs","created":"2023-04-28","cited_by_count":30},{"id":"2205.11634","title":"TransforMatcher: Match-to-Match Attention for Semantic Correspondence","created":"2022-05-23","cited_by_count":29},{"id":"2404.00469","title":"SceneGraphLoc: Cross-Modal Coarse Visual Localization on 3D Scene Graphs","created":"2024-03-30","cited_by_count":29},{"id":"1807.02939","title":"PARN: Pyramidal Affine Regression Networks for Dense Semantic Correspondence","created":"2018-07-09","cited_by_count":26},{"id":"2310.16838","title":"SparseDFF: Sparse-View Feature Distillation for One-Shot Dexterous Manipulation","created":"2023-10-25","cited_by_count":22},{"id":"2305.19094","title":"Diffusion Model for Dense Matching","created":"2023-05-30","cited_by_count":21},{"id":"2303.16527","title":"Understanding and Improving Features Learned in Deep Functional Maps","created":"2023-03-29","cited_by_count":20},{"id":"2102.12093","title":"PRIN/SPRIN: On Extracting Point-wise Rotation Invariant Features","created":"2021-02-24","cited_by_count":15},{"id":"2309.04836","title":"Neural Semantic Surface Maps","created":"2023-09-09","cited_by_count":13},{"id":"1707.05471","title":"DCTM: Discrete-Continuous Transformation Matching for Semantic Flow","created":"2017-07-18","cited_by_count":12},{"id":"2109.05221","title":"Convolutional Hough Matching Networks for Robust and Efficient Visual Correspondence","created":"2021-09-11","cited_by_count":12},{"id":"2402.08622","title":"NeRF Analogies: Example-Based Visual Attribute Transfer for NeRFs","created":"2024-02-13","cited_by_count":11},{"id":"2403.19474","title":"SG-PGM: Partial Graph Matching Network with Semantic Geometric Fusion for 3D Scene Graph Alignment and Its Downstream Tasks","created":"2024-03-28","cited_by_count":10},{"id":"2410.23039","title":"Neural Attention Field: Emerging Point Relevance in 3D Scenes for One-Shot Dexterous Grasping","created":"2024-10-30","cited_by_count":5},{"id":"2305.02398","title":"Learning-based Relational Object Matching Across Views","created":"2023-05-03","cited_by_count":4},{"id":"2204.00161","title":"Mutual Scene Synthesis for Mixed Reality Telepresence","created":"2022-04-01","cited_by_count":3},{"id":"2404.11156","title":"Learning SO(3)-Invariant Semantic Correspondence via Local Shape Transform","created":"2024-04-17","cited_by_count":3},{"id":"1512.06963","title":"Multi-Instance Visual-Semantic Embedding","created":"2015-12-22","cited_by_count":1},{"id":"2206.05522","title":"The Effects of Spatial Configuration on Relative Translation Gain Thresholds in Redirected Walking","created":"2022-06-11","cited_by_count":1}],"next_cursor":null}