{"list":"other","total":124,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"1512.04150","title":"Learning Deep Features for Discriminative Localization","created":"2015-12-14","cited_by_count":2436},{"id":"2103.13413","title":"Vision Transformers for Dense Prediction","created":"2021-03-24","cited_by_count":1803},{"id":"1506.04214","title":"Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting","created":"2015-06-13","cited_by_count":1436},{"id":"1709.06158","title":"Matterport3D: Learning from RGB-D Data in Indoor Environments","created":"2017-09-18","cited_by_count":1376},{"id":"1502.00956","title":"ORB-SLAM: a Versatile and Accurate Monocular SLAM System","created":"2015-02-03","cited_by_count":988},{"id":"1906.05797","title":"The Replica Dataset: A Digital Replica of Indoor Spaces","created":"2019-06-13","cited_by_count":904},{"id":"1610.06475","title":"ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Cameras","created":"2016-10-20","cited_by_count":806},{"id":"2108.10869","title":"DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras","created":"2021-08-24","cited_by_count":687},{"id":"1611.08974","title":"Semantic Scene Completion from a Single Depth Image","created":"2016-11-28","cited_by_count":472},{"id":"1703.01780","title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","created":"2017-03-06","cited_by_count":472},{"id":"1801.10130","title":"Spherical CNNs","created":"2018-01-30","cited_by_count":456},{"id":"1702.01105","title":"Joint 2D-3D-Semantic Data for Indoor Scene Understanding","created":"2017-02-03","cited_by_count":406},{"id":"1606.00373","title":"Deeper Depth Prediction with Fully Convolutional Residual Networks","created":"2016-06-01","cited_by_count":403},{"id":"1908.00222","title":"Structured3D: A Large Photo-realistic Dataset for Structured 3D Modeling","created":"2019-08-01","cited_by_count":286},{"id":"1902.04615","title":"Gauge Equivariant Convolutional Networks and the Icosahedral CNN","created":"2019-02-11","cited_by_count":267},{"id":"1711.06721","title":"Learning SO(3) Equivariant Representations with Spherical CNNs","created":"2017-11-17","cited_by_count":248},{"id":"2011.12172","title":"VIGOR: Cross-View Image Geo-localization beyond One-to-one Retrieval","created":"2020-11-24","cited_by_count":189},{"id":"1604.03605","title":"What do different evaluation metrics tell us about saliency models?","created":"2016-04-12","cited_by_count":185},{"id":"1910.10088","title":"Gaze360: Physically Unconstrained Gaze Estimation in the Wild","created":"2019-10-22","cited_by_count":174},{"id":"2204.00097","title":"TransGeo: Transformer Is All You Need for Cross-view Image Geo-localization","created":"2022-03-31","cited_by_count":168},{"id":"1704.00090","title":"Learning to Predict Indoor Illumination from a Single Image","created":"2017-04-01","cited_by_count":161},{"id":"2005.03860","title":"Where am I looking at? Joint Location and Orientation Estimation by Cross-View Matching","created":"2020-05-08","cited_by_count":126},{"id":"2105.08756","title":"Pathdreamer: A World Model for Indoor Navigation","created":"2021-05-18","cited_by_count":118},{"id":"2001.05049","title":"DeepFactors: Real-Time Probabilistic Dense Monocular SLAM","created":"2020-01-14","cited_by_count":117},{"id":"2103.06818","title":"Coming Down to Earth: Satellite-to-Street View Synthesis for Geo-Localization","created":"2021-03-11","cited_by_count":113},{"id":"1901.03861","title":"HorizonNet: Learning Room Layout with 1D Representation and Pano Stretch Data Augmentation","created":"2019-01-12","cited_by_count":108},{"id":"2011.11498","title":"HoHoNet: 360 Indoor Holistic Understanding with Latent Horizontal Features","created":"2020-11-23","cited_by_count":105},{"id":"1712.10215","title":"ScanComplete: Large-Scale Scene Completion and Semantic Segmentation for 3D Scans","created":"2017-12-29","cited_by_count":103},{"id":"1807.09620","title":"OmniDepth: Dense Depth Estimation for Indoors Spherical Panoramas","created":"2018-07-25","cited_by_count":99},{"id":"1803.08999","title":"LayoutNet: Reconstructing the 3D Room Layout from a Single RGB Image","created":"2018-03-23","cited_by_count":95},{"id":"1904.11045","title":"Bridging the Domain Gap for Ground-to-Aerial Image Matching","created":"2019-04-24","cited_by_count":95},{"id":"2011.01819","title":"Learning Representations from Audio-Visual Spatial Alignment","created":"2020-11-03","cited_by_count":95},{"id":"1809.02587","title":"Self-Supervised Generation of Spatial Audio for 360 Video","created":"2018-09-07","cited_by_count":93},{"id":"2102.03550","title":"UniFuse: Unidirectional Fusion for 360$^{\\circ}$ Panorama Depth Estimation","created":"2021-02-06","cited_by_count":92},{"id":"1612.02709","title":"Predicting Ground-Level Scene Layout from Aerial Imagery","created":"2016-12-08","cited_by_count":90},{"id":"2110.05122","title":"Pano-AVQA: Grounded Audio-Visual Question Answering on 360$^\\circ$ Videos","created":"2021-10-11","cited_by_count":86},{"id":"1910.08812","title":"Deep Parametric Indoor Lighting Estimation","created":"2019-10-19","cited_by_count":83},{"id":"1912.09390","title":"Tangent Images for Mitigating Spherical Distortion","created":"2019-12-19","cited_by_count":79},{"id":"2103.07466","title":"3D Semantic Scene Completion: a Survey","created":"2021-03-12","cited_by_count":74},{"id":"2203.01452","title":"Bending Reality: Distortion-aware Transformers for Adapting to Panoramic Semantic Segmentation","created":"2022-03-02","cited_by_count":72},{"id":"1811.11977","title":"DuLa-Net: A Dual-Projection Network for Estimating Room Layouts from a Single RGB Panorama","created":"2018-11-29","cited_by_count":68},{"id":"1806.01320","title":"Cube Padding for Weakly-Supervised Saliency Prediction in 360{\\deg} Videos","created":"2018-06-04","cited_by_count":66},{"id":"2012.15000","title":"DeepSphere: a graph-based spherical CNN","created":"2020-12-30","cited_by_count":66},{"id":"1701.01081","title":"SalGAN: Visual Saliency Prediction with Generative Adversarial Networks","created":"2017-01-04","cited_by_count":65},{"id":"2203.00838","title":"OmniFusion: 360 Monocular Depth Estimation via Geometry-Aware Fusion","created":"2022-03-02","cited_by_count":61},{"id":"2111.15669","title":"360MonoDepth: High-Resolution 360{\\deg} Monocular Depth Estimation","created":"2021-11-30","cited_by_count":60},{"id":"2102.07448","title":"OmniDet: Surround View Cameras based Multi-task Visual Perception Network for Autonomous Driving","created":"2021-02-15","cited_by_count":57},{"id":"1812.03115","title":"Kernel Transformer Networks for Compact Spherical Convolution","created":"2018-12-07","cited_by_count":56},{"id":"1903.08094","title":"Corners for Layout: End-to-End Layout Recovery from 360 Images","created":"2019-03-19","cited_by_count":55},{"id":"1611.06403","title":"Deep Outdoor Illumination Estimation","created":"2016-11-19","cited_by_count":53},{"id":"1907.12849","title":"Orientation-aware Semantic Segmentation on Icosahedron Spheres","created":"2019-07-30","cited_by_count":53},{"id":"1909.08112","title":"Spherical View Synthesis for Self-Supervised 360 Depth Estimation","created":"2019-09-17","cited_by_count":51},{"id":"2103.05687","title":"Capturing Omni-Range Context for Omnidirectional Segmentation","created":"2021-03-09","cited_by_count":50},{"id":"2012.11116","title":"EMLight: Lighting Estimation via Spherical Distribution Approximation","created":"2020-12-21","cited_by_count":48},{"id":"2203.14668","title":"Diverse Plausible 360-Degree Image Outpainting for Efficient 3DCG Background Creation","created":"2022-03-28","cited_by_count":47},{"id":"2104.00568","title":"LED2-Net: Monocular 360 Layout Estimation via Differentiable Depth Rendering","created":"2021-04-01","cited_by_count":43},{"id":"1801.00708","title":"Restricted Deformable Convolution based Road Scene Semantic Segmentation Using Surround View Cameras","created":"2018-01-02","cited_by_count":42},{"id":"1811.08196","title":"SpherePHD: Applying CNNs on a Spherical PolyHeDron Representation of 360 degree Images","created":"2018-11-20","cited_by_count":41},{"id":"1811.05304","title":"Self-Supervised Learning of Depth and Camera Motion from 360{\\deg} Videos","created":"2018-11-13","cited_by_count":40},{"id":"1911.04460","title":"360SD-Net: 360{\\deg} Stereo Depth Estimation with Learnable Cost Volume","created":"2019-11-11","cited_by_count":40},{"id":"2112.14440","title":"ACDNet: Adaptively Combined Dilated Convolution for Monocular Panorama Depth Estimation","created":"2021-12-29","cited_by_count":39},{"id":"2108.06383","title":"DensePASS: Dense Panoramic Semantic Segmentation via Unsupervised Domain Adaptation with Attention-Augmented Context Exchange","created":"2021-08-13","cited_by_count":36},{"id":"1710.10755","title":"Predicting Head Movement in Panoramic Video: A Deep Reinforcement Learning Approach","created":"2017-10-30","cited_by_count":34},{"id":"2110.11062","title":"Transfer beyond the Field of View: Dense Panoramic Semantic Segmentation via Unsupervised Domain Adaptation","created":"2021-10-21","cited_by_count":34},{"id":"2108.10743","title":"DeepPanoContext: Panoramic 3D Scene Understanding with Holistic Scene Context Graph and Relation-based Optimization","created":"2021-08-24","cited_by_count":33},{"id":"2002.09140","title":"Blind Omnidirectional Image Quality Assessment with Viewport Oriented Graph Convolutional Networks","created":"2020-02-21","cited_by_count":31},{"id":"1909.07721","title":"DS-PASS: Detail-Sensitive Panoramic Annular Semantic Segmentation through SwaftNet for Surrounding Sensing","created":"2019-09-17","cited_by_count":30},{"id":"1707.03123","title":"SaltiNet: Scan-path Prediction on 360 Degree Images using Saliency Volumes","created":"2017-07-11","cited_by_count":29},{"id":"1805.02838","title":"A Memory Network Approach for Story-based Temporal Summarization of 360{\\deg} Videos","created":"2018-05-08","cited_by_count":29},{"id":"1910.01712","title":"360-Indoor: Towards Learning Real-World Objects in 360{\\deg} Indoor Equirectangular Images","created":"2019-10-03","cited_by_count":26},{"id":"2003.04210","title":"Semantic Object Prediction and Spatial Sound Super-Resolution with Binaural Sounds","created":"2020-03-09","cited_by_count":26},{"id":"2112.06179","title":"BIPS: Bi-modal Indoor Panorama Synthesis via Residual Depth-aided Adversarial Learning","created":"2021-12-12","cited_by_count":26},{"id":"1907.00939","title":"Pano Popups: Indoor 3D Reconstruction with a Plane-Aware Network","created":"2019-07-01","cited_by_count":25},{"id":"2012.06628","title":"Sat2Vid: Street-view Panoramic Video Synthesis from a Single Satellite Image","created":"2020-12-11","cited_by_count":25},{"id":"1902.10904","title":"SweepNet: Wide-baseline Omnidirectional Depth Estimation","created":"2019-02-28","cited_by_count":24},{"id":"2103.00868","title":"Panoramic Panoptic Segmentation: Towards Complete Surrounding Understanding via Unsupervised Contrastive Learning","created":"2021-03-01","cited_by_count":23},{"id":"2203.09855","title":"Multi-Modal Masked Pre-Training for Monocular Panoramic Depth Completion","created":"2022-03-18","cited_by_count":23},{"id":"1612.02335","title":"Pano2Vid: Automatic Cinematography for Watching 360$^{\\circ}$ Videos","created":"2016-12-07","cited_by_count":22},{"id":"1705.01759","title":"Deep 360 Pilot: Learning a Deep Agent for Piloting through 360{\\deg} Sports Video","created":"2017-05-04","cited_by_count":22},{"id":"1708.00919","title":"Learning Spherical Convolution for Fast Features from 360{\\deg} Imagery","created":"2017-08-02","cited_by_count":22},{"id":"1709.06505","title":"SalNet360: Saliency Maps for omni-directional images with CNN","created":"2017-09-19","cited_by_count":21},{"id":"1908.06257","title":"OmniMVS: End-to-End Learning for Omnidirectional Stereo Matching","created":"2019-08-17","cited_by_count":21},{"id":"1805.08009","title":"Object Detection in Equirectangular Panorama","created":"2018-05-21","cited_by_count":20},{"id":"2102.11393","title":"No-Reference Quality Assessment for 360-degree Images by Analysis of Multi-frequency Information and Local-global Naturalness","created":"2021-02-22","cited_by_count":20},{"id":"1807.10990","title":"Bridge the Gap Between VQA and Human Behavior on Omnidirectional Video: A Large-Scale Dataset and a Deep Learning Model","created":"2018-07-29","cited_by_count":19},{"id":"2106.10859","title":"Moving in a 360 World: Synthesizing Panoramic Parallaxes from a Single Panorama","created":"2021-06-21","cited_by_count":19},{"id":"2109.10563","title":"Improving 360 Monocular Depth Estimation via Non-local Dense Prediction Transformer and Joint Supervised and Self-supervised Learning","created":"2021-09-22","cited_by_count":19},{"id":"1908.04297","title":"Super-resolution of Omnidirectional Images Using Adversarial Learning","created":"2019-08-12","cited_by_count":18},{"id":"1707.08301","title":"Graph-Based Classification of Omnidirectional Images","created":"2017-07-26","cited_by_count":16},{"id":"1801.10312","title":"A Deep Ranking Model for Spatio-Temporal Highlight Detection from a 360 Video","created":"2018-01-31","cited_by_count":16},{"id":"1910.06138","title":"What's in my Room? Object Recognition on Indoor Panoramic Images","created":"2019-10-14","cited_by_count":16},{"id":"2106.06662","title":"Equivariant Networks for Pixelized Spheres","created":"2021-06-12","cited_by_count":16},{"id":"2202.02796","title":"GLPanoDepth: Global-to-Local Panoramic Depth Estimation","created":"2022-02-06","cited_by_count":16},{"id":"2001.03339","title":"Visual Question Answering on 360{\\deg} Images","created":"2020-01-10","cited_by_count":15},{"id":"2202.08010","title":"360 Depth Estimation in the Wild -- The Depth360 Dataset and the SegFuse Network","created":"2022-02-16","cited_by_count":15},{"id":"1703.00495","title":"Making 360$^{\\circ}$ Video Watchable in 2D: Learning Videography for Click Free Viewing","created":"2017-03-01","cited_by_count":13}],"next_cursor":"100"}