{"list":"other","total":101,"rows":[{"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"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":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"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":"2006.07733","title":"Bootstrap your own latent: A new approach to self-supervised Learning","created":"2020-06-13","cited_by_count":4750},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"2006.09882","title":"Unsupervised Learning of Visual Features by Contrasting Cluster Assignments","created":"2020-06-17","cited_by_count":2857},{"id":"2003.12039","title":"RAFT: Recurrent All-Pairs Field Transforms for Optical Flow","created":"2020-03-26","cited_by_count":2415},{"id":"2003.04297","title":"Improved Baselines with Momentum Contrastive Learning","created":"2020-03-09","cited_by_count":2287},{"id":"2103.13413","title":"Vision Transformers for Dense Prediction","created":"2021-03-24","cited_by_count":1803},{"id":"2104.02057","title":"An Empirical Study of Training Self-Supervised Vision Transformers","created":"2021-04-05","cited_by_count":1616},{"id":"2012.02190","title":"pixelNeRF: Neural Radiance Fields from One or Few Images","created":"2020-12-03","cited_by_count":1584},{"id":"1606.06650","title":"3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation","created":"2016-06-21","cited_by_count":1476},{"id":"1603.09246","title":"Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles","created":"2016-03-30","cited_by_count":1382},{"id":"1805.04687","title":"BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning","created":"2018-05-12","cited_by_count":1288},{"id":"1808.06670","title":"Learning deep representations by mutual information estimation and maximization","created":"2018-08-20","cited_by_count":1273},{"id":"1505.05192","title":"Unsupervised Visual Representation Learning by Context Prediction","created":"2015-05-19","cited_by_count":1066},{"id":"1807.05520","title":"Deep Clustering for Unsupervised Learning of Visual Features","created":"2018-07-15","cited_by_count":1028},{"id":"2007.11898","title":"ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAM","created":"2020-07-23","cited_by_count":878},{"id":"1609.03677","title":"Unsupervised Monocular Depth Estimation with Left-Right Consistency","created":"2016-09-13","cited_by_count":820},{"id":"1906.00910","title":"Learning Representations by Maximizing Mutual Information Across Views","created":"2019-06-03","cited_by_count":734},{"id":"1905.09272","title":"Data-Efficient Image Recognition with Contrastive Predictive Coding","created":"2019-05-22","cited_by_count":673},{"id":"2005.04966","title":"Prototypical Contrastive Learning of Unsupervised Representations","created":"2020-05-11","cited_by_count":640},{"id":"2112.09133","title":"Masked Feature Prediction for Self-Supervised Visual Pre-Training","created":"2021-12-16","cited_by_count":576},{"id":"2109.13410","title":"KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D","created":"2021-09-28","cited_by_count":575},{"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":"1911.05371","title":"Self-labelling via simultaneous clustering and representation learning","created":"2019-11-13","cited_by_count":528},{"id":"1611.08974","title":"Semantic Scene Completion from a Single Depth Image","created":"2016-11-28","cited_by_count":472},{"id":"1807.06653","title":"Invariant Information Clustering for Unsupervised Image Classification and Segmentation","created":"2018-07-17","cited_by_count":455},{"id":"2302.07817","title":"Tri-Perspective View for Vision-Based 3D Semantic Occupancy Prediction","created":"2023-02-15","cited_by_count":409},{"id":"2404.15506","title":"Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation","created":"2024-03-22","cited_by_count":395},{"id":"2205.15585","title":"Decomposing NeRF for Editing via Feature Field Distillation","created":"2022-05-31","cited_by_count":371},{"id":"2112.00726","title":"MonoScene: Monocular 3D Semantic Scene Completion","created":"2021-12-01","cited_by_count":363},{"id":"2302.12251","title":"VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completion","created":"2023-02-23","cited_by_count":313},{"id":"2304.05316","title":"OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Prediction","created":"2023-04-11","cited_by_count":293},{"id":"2306.13631","title":"OpenMask3D: Open-Vocabulary 3D Instance Segmentation","created":"2023-06-23","cited_by_count":289},{"id":"2203.08414","title":"Unsupervised Semantic Segmentation by Distilling Feature Correspondences","created":"2022-03-16","cited_by_count":241},{"id":"2012.03762","title":"Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene Completion","created":"2020-12-07","cited_by_count":223},{"id":"2311.02077","title":"EmerNeRF: Emergent Spatial-Temporal Scene Decomposition via Self-Supervision","created":"2023-11-03","cited_by_count":217},{"id":"2306.02851","title":"Scene as Occupancy","created":"2023-06-05","cited_by_count":209},{"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":"2008.10559","title":"LMSCNet: Lightweight Multiscale 3D Semantic Completion","created":"2020-08-24","cited_by_count":188},{"id":"2301.11320","title":"Cut and Learn for Unsupervised Object Detection and Instance Segmentation","created":"2023-01-26","cited_by_count":187},{"id":"1704.05519","title":"Computer Vision for Autonomous Vehicles: Problems, Datasets and State of the Art","created":"2017-04-18","cited_by_count":182},{"id":"1704.06254","title":"Multi-view Supervision for Single-view Reconstruction via Differentiable Ray Consistency","created":"2017-04-20","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":"2307.01492","title":"FB-OCC: 3D Occupancy Prediction based on Forward-Backward View Transformation","created":"2023-07-04","cited_by_count":165},{"id":"2103.17070","title":"PiCIE: Unsupervised Semantic Segmentation using Invariance and Equivariance in Clustering","created":"2021-03-30","cited_by_count":163},{"id":"1701.08493","title":"A Survey of Structure from Motion","created":"2017-01-30","cited_by_count":158},{"id":"2105.00097","title":"Self-supervised Augmentation Consistency for Adapting Semantic Segmentation","created":"2021-04-30","cited_by_count":149},{"id":"2110.09327","title":"Self-Supervised Representation Learning: Introduction, Advances and Challenges","created":"2021-10-18","cited_by_count":148},{"id":"2311.12754","title":"SelfOcc: Self-Supervised Vision-Based 3D Occupancy Prediction","created":"2023-11-21","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":"2309.09502","title":"RenderOcc: Vision-Centric 3D Occupancy Prediction with 2D Rendering Supervision","created":"2023-09-18","cited_by_count":128},{"id":"2004.02122","title":"Anisotropic Convolutional Networks for 3D Semantic Scene Completion","created":"2020-04-05","cited_by_count":127},{"id":"2003.14052","title":"3D Sketch-aware Semantic Scene Completion via Semi-supervised Structure Prior","created":"2020-03-31","cited_by_count":126},{"id":"2210.01571","title":"VICRegL: Self-Supervised Learning of Local Visual Features","created":"2022-10-04","cited_by_count":118},{"id":"2403.10516","title":"FeatUp: A Model-Agnostic Framework for Features at Any Resolution","created":"2024-03-15","cited_by_count":116},{"id":"2406.04343","title":"Flash3D: Feed-Forward Generalisable 3D Scene Reconstruction from a Single Image","created":"2024-06-06","cited_by_count":116},{"id":"2411.04924","title":"MVSplat360: Feed-Forward 360 Scene Synthesis from Sparse Views","created":"2024-11-07","cited_by_count":116},{"id":"2012.09242","title":"S3CNet: A Sparse Semantic Scene Completion Network for LiDAR Point Clouds","created":"2020-12-16","cited_by_count":102},{"id":"2207.11514","title":"Semantic Abstraction: Open-World 3D Scene Understanding from 2D Vision-Language Models","created":"2022-07-23","cited_by_count":95},{"id":"1906.06543","title":"Image-based 3D Object Reconstruction: State-of-the-Art and Trends in the Deep Learning Era","created":"2019-06-15","cited_by_count":87},{"id":"2302.13540","title":"OccDepth: A Depth-Aware Method for 3D Semantic Scene Completion","created":"2023-02-27","cited_by_count":86},{"id":"2305.14344","title":"Siamese Masked Autoencoders","created":"2023-05-23","cited_by_count":76},{"id":"2306.09001","title":"SSCBench: A Large-Scale 3D Semantic Scene Completion Benchmark for Autonomous Driving","created":"2023-06-15","cited_by_count":75},{"id":"2011.09141","title":"Semantic Scene Completion using Local Deep Implicit Functions on LiDAR Data","created":"2020-11-18","cited_by_count":74},{"id":"2103.07466","title":"3D Semantic Scene Completion: a Survey","created":"2021-03-12","cited_by_count":74},{"id":"2407.20229","title":"Improving 2D Feature Representations by 3D-Aware Fine-Tuning","created":"2024-07-29","cited_by_count":71},{"id":"2312.17232","title":"Segment3D: Learning Fine-Grained Class-Agnostic 3D Segmentation without Manual Labels","created":"2023-12-28","cited_by_count":64},{"id":"2301.07668","title":"Behind the Scenes: Density Fields for Single View Reconstruction","created":"2023-01-18","cited_by_count":63},{"id":"1903.00620","title":"RGBD Based Dimensional Decomposition Residual Network for 3D Semantic Scene Completion","created":"2019-03-02","cited_by_count":55},{"id":"2104.03640","title":"Semantic Scene Completion via Integrating Instances and Scene in-the-Loop","created":"2021-04-08","cited_by_count":55},{"id":"2412.13193","title":"GaussTR: Foundation Model-Aligned Gaussian Transformer for Self-Supervised 3D Spatial Understanding","created":"2024-12-17","cited_by_count":46},{"id":"1908.00382","title":"Cascaded Context Pyramid for Full-Resolution 3D Semantic Scene Completion","created":"2019-08-01","cited_by_count":43},{"id":"2303.15014","title":"Leveraging Hidden Positives for Unsupervised Semantic Segmentation","created":"2023-03-27","cited_by_count":40},{"id":"2001.10709","title":"Depth Based Semantic Scene Completion with Position Importance Aware Loss","created":"2020-01-29","cited_by_count":37},{"id":"2210.03043","title":"Feature-Realistic Neural Fusion for Real-Time, Open Set Scene Understanding","created":"2022-10-06","cited_by_count":37},{"id":"2312.17243","title":"Unsupervised Universal Image Segmentation","created":"2023-12-28","cited_by_count":35},{"id":"1804.10975","title":"Matryoshka Networks: Predicting 3D Geometry via Nested Shape Layers","created":"2018-04-29","cited_by_count":33},{"id":"2310.07522","title":"S4C: Self-Supervised Semantic Scene Completion with Neural Fields","created":"2023-10-11","cited_by_count":28},{"id":"2403.01482","title":"EAGLE: Eigen Aggregation Learning for Object-Centric Unsupervised Semantic Segmentation","created":"2024-03-03","cited_by_count":27},{"id":"2305.12427","title":"VL-Fields: Towards Language-Grounded Neural Implicit Spatial Representations","created":"2023-05-21","cited_by_count":23},{"id":"2310.18887","title":"Dynamo-Depth: Fixing Unsupervised Depth Estimation for Dynamical Scenes","created":"2023-10-29","cited_by_count":20},{"id":"2309.12378","title":"Unsupervised Semantic Segmentation Through Depth-Guided Feature Correlation and Sampling","created":"2023-09-21","cited_by_count":19},{"id":"2502.08769","title":"Cluster and Predict Latent Patches for Improved Masked Image Modeling","created":"2025-02-12","cited_by_count":17},{"id":"2311.12174","title":"LABELMAKER: Automatic Semantic Label Generation from RGB-D Trajectories","created":"2023-11-20","cited_by_count":14},{"id":"2306.05411","title":"R-MAE: Regions Meet Masked Autoencoders","created":"2023-06-08","cited_by_count":13},{"id":"2111.14798","title":"Semi-supervised Implicit Scene Completion from Sparse LiDAR","created":"2021-11-29","cited_by_count":10},{"id":"2504.01955","title":"Scene-Centric Unsupervised Panoptic Segmentation","created":"2025-04-02","cited_by_count":10},{"id":"2404.16818","title":"Boosting Unsupervised Semantic Segmentation with Principal Mask Proposals","created":"2024-04-25","cited_by_count":9},{"id":"2304.07314","title":"Uncovering the Inner Workings of STEGO for Safe Unsupervised Semantic Segmentation","created":"2023-04-14","cited_by_count":7},{"id":"2404.07933","title":"Boosting Self-Supervision for Single-View Scene Completion via Knowledge Distillation","created":"2024-04-11","cited_by_count":6}],"next_cursor":"100"}