{"list":"other","total":72,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"id":"1901.05103","title":"DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation","created":"2019-01-16","cited_by_count":2689},{"id":"2307.08691","title":"FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning","created":"2023-07-17","cited_by_count":2598},{"id":"1611.05431","title":"Aggregated Residual Transformations for Deep Neural Networks","created":"2016-11-16","cited_by_count":2546},{"id":"1812.03828","title":"Occupancy Networks: Learning 3D Reconstruction in Function Space","created":"2018-12-10","cited_by_count":2041},{"id":"2212.08051","title":"Objaverse: A Universe of Annotated 3D Objects","created":"2022-12-15","cited_by_count":1540},{"id":"2303.11328","title":"Zero-1-to-3: Zero-shot One Image to 3D Object","created":"2023-03-20","cited_by_count":1489},{"id":"2011.00931","title":"Point Transformer","created":"2020-11-02","cited_by_count":1470},{"id":"1904.08755","title":"4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks","created":"2019-04-18","cited_by_count":1208},{"id":"2112.03857","title":"Grounded Language-Image Pre-training","created":"2021-12-07","cited_by_count":1156},{"id":"2106.04560","title":"Scaling Vision Transformers","created":"2021-06-08","cited_by_count":999},{"id":"2007.11571","title":"Neural Sparse Voxel Fields","created":"2020-07-22","cited_by_count":959},{"id":"2401.14159","title":"Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks","created":"2024-01-25","cited_by_count":929},{"id":"1711.00199","title":"PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenes","created":"2017-11-01","cited_by_count":775},{"id":"2003.04618","title":"Convolutional Occupancy Networks","created":"2020-03-10","cited_by_count":761},{"id":"1711.10275","title":"3D Semantic Segmentation with Submanifold Sparse Convolutional Networks","created":"2017-11-28","cited_by_count":748},{"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":"2210.04150","title":"Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP","created":"2022-10-09","cited_by_count":565},{"id":"2306.16928","title":"One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization","created":"2023-06-29","cited_by_count":560},{"id":"1611.08974","title":"Semantic Scene Completion from a Single Depth Image","created":"2016-11-28","cited_by_count":472},{"id":"2111.04276","title":"Deep Marching Tetrahedra: a Hybrid Representation for High-Resolution 3D Shape Synthesis","created":"2021-11-08","cited_by_count":460},{"id":"2102.10882","title":"Conditional Positional Encodings for Vision Transformers","created":"2021-02-22","cited_by_count":406},{"id":"2210.05666","title":"Point Transformer V2: Grouped Vector Attention and Partition-based Pooling","created":"2022-10-11","cited_by_count":388},{"id":"2302.12251","title":"VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completion","created":"2023-02-23","cited_by_count":313},{"id":"2210.04628","title":"Novel View Synthesis with Diffusion Models","created":"2022-10-06","cited_by_count":300},{"id":"2212.04493","title":"SDFusion: Multimodal 3D Shape Completion, Reconstruction, and Generation","created":"2022-12-08","cited_by_count":288},{"id":"2108.08839","title":"PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformers","created":"2021-08-19","cited_by_count":286},{"id":"2206.05836","title":"GLIPv2: Unifying Localization and Vision-Language Understanding","created":"2022-06-12","cited_by_count":275},{"id":"2304.02602","title":"Generative Novel View Synthesis with 3D-Aware Diffusion Models","created":"2023-04-05","cited_by_count":274},{"id":"2203.09516","title":"AutoSDF: Shape Priors for 3D Completion, Reconstruction and Generation","created":"2022-03-17","cited_by_count":208},{"id":"2212.06870","title":"MegaPose: 6D Pose Estimation of Novel Objects via Render & Compare","created":"2022-12-13","cited_by_count":201},{"id":"2303.08133","title":"MeshDiffusion: Score-based Generative 3D Mesh Modeling","created":"2023-03-14","cited_by_count":199},{"id":"2201.12204","title":"From data to functa: Your data point is a function and you can treat it like one","created":"2022-01-28","cited_by_count":187},{"id":"2112.05682","title":"Self-attention Does Not Need $O(n^2)$ Memory","created":"2021-12-10","cited_by_count":154},{"id":"2004.02122","title":"Anisotropic Convolutional Networks for 3D Semantic Scene Completion","created":"2020-04-05","cited_by_count":127},{"id":"1904.03167","title":"HomebrewedDB: RGB-D Dataset for 6D Pose Estimation of 3D Objects","created":"2019-04-05","cited_by_count":110},{"id":"2305.03045","title":"OctFormer: Octree-based Transformers for 3D Point Clouds","created":"2023-05-04","cited_by_count":109},{"id":"2107.02191","title":"TransformerFusion: Monocular RGB Scene Reconstruction using Transformers","created":"2021-07-05","cited_by_count":106},{"id":"2205.03892","title":"ConvMAE: Masked Convolution Meets Masked Autoencoders","created":"2022-05-08","cited_by_count":105},{"id":"2305.19590","title":"Neural Kernel Surface Reconstruction","created":"2023-05-31","cited_by_count":104},{"id":"1509.01329","title":"Semantic Amodal Segmentation","created":"2015-09-04","cited_by_count":103},{"id":"1712.10215","title":"ScanComplete: Large-Scale Scene Completion and Semantic Segmentation for 3D Scans","created":"2017-12-29","cited_by_count":103},{"id":"2201.01831","title":"POCO: Point Convolution for Surface Reconstruction","created":"2022-01-05","cited_by_count":92},{"id":"2006.11807","title":"Improving Image Captioning with Better Use of Captions","created":"2020-06-21","cited_by_count":84},{"id":"1609.08546","title":"Shape Completion Enabled Robotic Grasping","created":"2016-09-27","cited_by_count":79},{"id":"1912.00036","title":"SG-NN: Sparse Generative Neural Networks for Self-Supervised Scene Completion of RGB-D Scans","created":"2019-11-29","cited_by_count":77},{"id":"2207.13691","title":"ShAPO: Implicit Representations for Multi-Object Shape, Appearance, and Pose Optimization","created":"2022-07-27","cited_by_count":72},{"id":"2301.08247","title":"Multiview Compressive Coding for 3D Reconstruction","created":"2023-01-19","cited_by_count":71},{"id":"2304.05366","title":"The No Free Lunch Theorem, Kolmogorov Complexity, and the Role of Inductive Biases in Machine Learning","created":"2023-04-11","cited_by_count":63},{"id":"2003.08593","title":"Curriculum DeepSDF","created":"2020-03-19","cited_by_count":62},{"id":"2111.13674","title":"Neural Fields as Learnable Kernels for 3D Reconstruction","created":"2021-11-26","cited_by_count":58},{"id":"1903.00620","title":"RGBD Based Dimensional Decomposition Residual Network for 3D Semantic Scene Completion","created":"2019-03-02","cited_by_count":55},{"id":"1908.00382","title":"Cascaded Context Pyramid for Full-Resolution 3D Semantic Scene Completion","created":"2019-08-01","cited_by_count":43},{"id":"2209.09475","title":"Revisiting Image Pyramid Structure for High Resolution Salient Object Detection","created":"2022-09-20","cited_by_count":36},{"id":"2006.03762","title":"Deep Octree-based CNNs with Output-Guided Skip Connections for 3D Shape and Scene Completion","created":"2020-06-06","cited_by_count":33},{"id":"1703.03512","title":"Real-time Perception meets Reactive Motion Generation","created":"2017-03-10","cited_by_count":30},{"id":"1904.12012","title":"RevealNet: Seeing Behind Objects in RGB-D Scans","created":"2019-04-26","cited_by_count":30},{"id":"2312.14198","title":"ZeroShape: Regression-based Zero-shot Shape Reconstruction","created":"2023-12-21","cited_by_count":30},{"id":"2103.13539","title":"Multi-View Fusion for Multi-Level Robotic Scene Understanding","created":"2021-03-25","cited_by_count":17},{"id":"2301.00866","title":"3DSGrasp: 3D Shape-Completion for Robotic Grasp","created":"2023-01-02","cited_by_count":13},{"id":"1803.11385","title":"H-CNN: Spatial Hashing Based CNN for 3D Shape Analysis","created":"2018-03-30","cited_by_count":10},{"id":"2204.01264","title":"Probabilistic Implicit Scene Completion","created":"2022-04-04","cited_by_count":8},{"id":"2203.00315","title":"Quick Multi-Robot Motion Planning by Combining Sampling and Search","created":"2022-03-01","cited_by_count":6},{"id":"2111.12905","title":"CIRCLE: Convolutional Implicit Reconstruction and Completion for Large-scale Indoor Scene","created":"2021-11-25","cited_by_count":4}],"next_cursor":null}