{"list":"other","total":76,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1612.00593","title":"PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation","created":"2016-12-02","cited_by_count":5248},{"id":"1411.4038","title":"Fully Convolutional Networks for Semantic Segmentation","created":"2014-11-14","cited_by_count":4859},{"id":"1612.00796","title":"Overcoming catastrophic forgetting in neural networks","created":"2016-12-02","cited_by_count":4787},{"id":"2006.07733","title":"Bootstrap your own latent: A new approach to self-supervised Learning","created":"2020-06-13","cited_by_count":4750},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"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":"1502.01852","title":"Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification","created":"2015-02-06","cited_by_count":3611},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"1504.08083","title":"Fast R-CNN","created":"2015-04-30","cited_by_count":2933},{"id":"1512.03012","title":"ShapeNet: An Information-Rich 3D Model Repository","created":"2015-12-09","cited_by_count":2897},{"id":"2011.10566","title":"Exploring Simple Siamese Representation Learning","created":"2020-11-20","cited_by_count":2866},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"1912.04838","title":"Scalability in Perception for Autonomous Driving: Waymo Open Dataset","created":"2019-12-10","cited_by_count":2451},{"id":"2003.04297","title":"Improved Baselines with Momentum Contrastive Learning","created":"2020-03-09","cited_by_count":2287},{"id":"1801.07829","title":"Dynamic Graph CNN for Learning on Point Clouds","created":"2018-01-24","cited_by_count":2223},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"id":"2108.10257","title":"SwinIR: Image Restoration Using Swin Transformer","created":"2021-08-23","cited_by_count":1887},{"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":"1709.06158","title":"Matterport3D: Learning from RGB-D Data in Indoor Environments","created":"2017-09-18","cited_by_count":1376},{"id":"1805.04687","title":"BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning","created":"2018-05-12","cited_by_count":1288},{"id":"1906.03327","title":"HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips","created":"2019-06-07","cited_by_count":950},{"id":"2012.00364","title":"Pre-Trained Image Processing Transformer","created":"2020-12-01","cited_by_count":893},{"id":"1705.00754","title":"Dense-Captioning Events in Videos","created":"2017-05-02","cited_by_count":793},{"id":"1804.02505","title":"MVSNet: Depth Inference for Unstructured Multi-view Stereo","created":"2018-04-07","cited_by_count":788},{"id":"2103.15595","title":"MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereo","created":"2021-03-29","cited_by_count":740},{"id":"2012.09688","title":"PCT: Point cloud transformer","created":"2020-12-17","cited_by_count":732},{"id":"2102.13090","title":"IBRNet: Learning Multi-View Image-Based Rendering","created":"2021-02-25","cited_by_count":703},{"id":"1905.00889","title":"Local Light Field Fusion: Practical View Synthesis with Prescriptive Sampling Guidelines","created":"2019-05-02","cited_by_count":672},{"id":"2111.14819","title":"Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling","created":"2021-11-29","cited_by_count":653},{"id":"2109.00512","title":"Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstruction","created":"2021-09-01","cited_by_count":652},{"id":"2204.11918","title":"Google Scanned Objects: A High-Quality Dataset of 3D Scanned Household Items","created":"2022-04-25","cited_by_count":612},{"id":"1908.04616","title":"Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Data","created":"2019-08-13","cited_by_count":532},{"id":"2203.06604","title":"Masked Autoencoders for Point Cloud Self-supervised Learning","created":"2022-03-13","cited_by_count":459},{"id":"2005.09007","title":"U$^2$-Net: Going Deeper with Nested U-Structure for Salient Object Detection","created":"2020-05-18","cited_by_count":412},{"id":"1812.01024","title":"DeepVoxels: Learning Persistent 3D Feature Embeddings","created":"2018-12-03","cited_by_count":405},{"id":"2011.09127","title":"3D-FRONT: 3D Furnished Rooms with layOuts and semaNTics","created":"2020-11-18","cited_by_count":380},{"id":"2202.07123","title":"Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework","created":"2022-02-15","cited_by_count":379},{"id":"1811.08883","title":"Rethinking ImageNet Pre-training","created":"2018-11-21","cited_by_count":377},{"id":"2110.06199","title":"ABO: Dataset and Benchmarks for Real-World 3D Object Understanding","created":"2021-10-12","cited_by_count":366},{"id":"1812.06216","title":"ABC: A Big CAD Model Dataset For Geometric Deep Learning","created":"2018-12-15","cited_by_count":341},{"id":"1902.10556","title":"Recurrent MVSNet for High-resolution Multi-view Stereo Depth Inference","created":"2019-02-27","cited_by_count":254},{"id":"1906.07316","title":"DeepView: View Synthesis with Learned Gradient Descent","created":"2019-06-18","cited_by_count":253},{"id":"2103.14635","title":"PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds","created":"2021-03-26","cited_by_count":211},{"id":"2010.01089","title":"Unsupervised Point Cloud Pre-Training via Occlusion Completion","created":"2020-10-02","cited_by_count":186},{"id":"2010.04595","title":"GRF: Learning a General Radiance Field for 3D Representation and Rendering","created":"2020-10-09","cited_by_count":183},{"id":"2105.01288","title":"Walk in the Cloud: Learning Curves for Point Clouds Shape Analysis","created":"2021-05-04","cited_by_count":172},{"id":"1704.03847","title":"Semantic3D.net: A new Large-scale Point Cloud Classification Benchmark","created":"2017-04-12","cited_by_count":158},{"id":"2012.09988","title":"Objectron: A Large Scale Dataset of Object-Centric Videos in the Wild with Pose Annotations","created":"2020-12-18","cited_by_count":155},{"id":"2203.11183","title":"Masked Discrimination for Self-Supervised Learning on Point Clouds","created":"2022-03-21","cited_by_count":155},{"id":"1811.11187","title":"Scan2CAD: Learning CAD Model Alignment in RGB-D Scans","created":"2018-11-27","cited_by_count":142},{"id":"2011.13244","title":"MVTN: Multi-View Transformation Network for 3D Shape Recognition","created":"2020-11-26","cited_by_count":140},{"id":"2006.12250","title":"Pix2Vox++: Multi-scale Context-aware 3D Object Reconstruction from Single and Multiple Images","created":"2020-06-22","cited_by_count":79},{"id":"2206.01204","title":"Siamese Image Modeling for Self-Supervised Vision Representation Learning","created":"2022-06-02","cited_by_count":78},{"id":"2204.02389","title":"ObjectFolder 2.0: A Multisensory Object Dataset for Sim2Real Transfer","created":"2022-04-05","cited_by_count":75},{"id":"2012.10921","title":"Learning Geometry-Disentangled Representation for Complementary Understanding of 3D Object Point Cloud","created":"2020-12-20","cited_by_count":71},{"id":"2103.16552","title":"Unsupervised Learning of 3D Object Categories from Videos in the Wild","created":"2021-03-30","cited_by_count":67},{"id":"1602.02481","title":"A Large Dataset of Object Scans","created":"2016-02-08","cited_by_count":64},{"id":"2210.03895","title":"ViewFool: Evaluating the Robustness of Visual Recognition to Adversarial Viewpoints","created":"2022-10-08","cited_by_count":48},{"id":"2205.07058","title":"RTMV: A Ray-Traced Multi-View Synthetic Dataset for Novel View Synthesis","created":"2022-05-14","cited_by_count":33},{"id":"2104.05374","title":"Self-supervised Multi-view Stereo via Effective Co-Segmentation and Data-Augmentation","created":"2021-04-12","cited_by_count":31},{"id":"2203.03949","title":"RC-MVSNet: Unsupervised Multi-View Stereo with Neural Rendering","created":"2022-03-08","cited_by_count":30},{"id":"2104.02972","title":"Self-supervised Learning of Depth Inference for Multi-view Stereo","created":"2021-04-07","cited_by_count":28},{"id":"1809.09761","title":"PhotoShape: Photorealistic Materials for Large-Scale Shape Collections","created":"2018-09-26","cited_by_count":21},{"id":"2207.10425","title":"KD-MVS: Knowledge Distillation Based Self-supervised Learning for Multi-view Stereo","created":"2022-07-21","cited_by_count":18},{"id":"2203.09440","title":"TO-Scene: A Large-scale Dataset for Understanding 3D Tabletop Scenes","created":"2022-03-17","cited_by_count":10},{"id":"1904.04621","title":"Towards Analyzing Semantic Robustness of Deep Neural Networks","created":"2019-04-09","cited_by_count":9},{"id":"2206.12356","title":"HM3D-ABO: A Photo-realistic Dataset for Object-centric Multi-view 3D Reconstruction","created":"2022-06-24","cited_by_count":4}],"next_cursor":null}