{"list":"other","total":87,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"1612.00593","title":"PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation","created":"2016-12-02","cited_by_count":5248},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"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":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"1312.6114","title":"Auto-Encoding Variational Bayes","created":"2013-12-20","cited_by_count":4053},{"id":"1502.01852","title":"Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification","created":"2015-02-06","cited_by_count":3611},{"id":"2209.14988","title":"DreamFusion: Text-to-3D using 2D Diffusion","created":"2022-09-29","cited_by_count":3025},{"id":"1508.07909","title":"Neural Machine Translation of Rare Words with Subword Units","created":"2015-08-31","cited_by_count":2918},{"id":"1512.03012","title":"ShapeNet: An Information-Rich 3D Model Repository","created":"2015-12-09","cited_by_count":2897},{"id":"1611.01144","title":"Categorical Reparameterization with Gumbel-Softmax","created":"2016-11-03","cited_by_count":2739},{"id":"1901.05103","title":"DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation","created":"2019-01-16","cited_by_count":2689},{"id":"1308.3432","title":"Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation","created":"2013-08-15","cited_by_count":2079},{"id":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"id":"1812.03828","title":"Occupancy Networks: Learning 3D Reconstruction in Function Space","created":"2018-12-10","cited_by_count":2041},{"id":"1609.03499","title":"WaveNet: A Generative Model for Raw Audio","created":"2016-09-12","cited_by_count":1722},{"id":"1904.10509","title":"Generating Long Sequences with Sparse Transformers","created":"2019-04-23","cited_by_count":1546},{"id":"2212.08051","title":"Objaverse: A Universe of Annotated 3D Objects","created":"2022-12-15","cited_by_count":1540},{"id":"1906.00446","title":"Generating Diverse High-Fidelity Images with VQ-VAE-2","created":"2019-06-02","cited_by_count":1387},{"id":"2211.10440","title":"Magic3D: High-Resolution Text-to-3D Content Creation","created":"2022-11-18","cited_by_count":1290},{"id":"1510.03055","title":"A Diversity-Promoting Objective Function for Neural Conversation Models","created":"2015-10-11","cited_by_count":1077},{"id":"2103.17249","title":"StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery","created":"2021-03-31","cited_by_count":991},{"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":"1411.4555","title":"Show and Tell: A Neural Image Caption Generator","created":"2014-11-17","cited_by_count":879},{"id":"1606.05328","title":"Conditional Image Generation with PixelCNN Decoders","created":"2016-06-16","cited_by_count":862},{"id":"2205.06175","title":"A Generalist Agent","created":"2022-05-12","cited_by_count":808},{"id":"2007.08501","title":"Accelerating 3D Deep Learning with PyTorch3D","created":"2020-07-16","cited_by_count":784},{"id":"2103.01458","title":"Diffusion Probabilistic Models for 3D Point Cloud Generation","created":"2021-03-02","cited_by_count":735},{"id":"2212.08751","title":"Point-E: A System for Generating 3D Point Clouds from Complex Prompts","created":"2022-12-16","cited_by_count":699},{"id":"2007.03898","title":"NVAE: A Deep Hierarchical Variational Autoencoder","created":"2020-07-08","cited_by_count":637},{"id":"2107.14795","title":"Perceiver IO: A General Architecture for Structured Inputs & Outputs","created":"2021-07-30","cited_by_count":629},{"id":"1610.07584","title":"Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling","created":"2016-10-24","cited_by_count":558},{"id":"1701.04128","title":"Understanding the Effective Receptive Field in Deep Convolutional Neural Networks","created":"2017-01-15","cited_by_count":553},{"id":"1802.05384","title":"AtlasNet: A Papier-M\\^ach\\'e Approach to Learning 3D Surface Generation","created":"2018-02-15","cited_by_count":539},{"id":"2104.03670","title":"3D Shape Generation and Completion through Point-Voxel Diffusion","created":"2021-04-08","cited_by_count":516},{"id":"2112.01455","title":"Zero-Shot Text-Guided Object Generation with Dream Fields","created":"2021-12-02","cited_by_count":513},{"id":"1906.12320","title":"PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flows","created":"2019-06-28","cited_by_count":488},{"id":"2112.02413","title":"PointCLIP: Point Cloud Understanding by CLIP","created":"2021-12-04","cited_by_count":463},{"id":"2210.08933","title":"DiffuSeq: Sequence to Sequence Text Generation with Diffusion Models","created":"2022-10-17","cited_by_count":450},{"id":"2110.06199","title":"ABO: Dataset and Benchmarks for Real-World 3D Object Understanding","created":"2021-10-12","cited_by_count":366},{"id":"1907.03739","title":"Point-Voxel CNN for Efficient 3D Deep Learning","created":"2019-07-08","cited_by_count":343},{"id":"1703.00395","title":"Lossy Image Compression with Compressive Autoencoders","created":"2017-03-01","cited_by_count":294},{"id":"2110.02624","title":"CLIP-Forge: Towards Zero-Shot Text-to-Shape Generation","created":"2021-10-06","cited_by_count":254},{"id":"2008.06520","title":"Learning Gradient Fields for Shape Generation","created":"2020-08-14","cited_by_count":245},{"id":"2012.02206","title":"Scan2Cap: Context-aware Dense Captioning in RGB-D Scans","created":"2020-12-03","cited_by_count":218},{"id":"2203.09516","title":"AutoSDF: Shape Priors for 3D Completion, Reconstruction and Generation","created":"2022-03-17","cited_by_count":208},{"id":"1803.08495","title":"Text2Shape: Generating Shapes from Natural Language by Learning Joint Embeddings","created":"2018-03-22","cited_by_count":169},{"id":"1912.00280","title":"Morphing and Sampling Network for Dense Point Cloud Completion","created":"2019-11-30","cited_by_count":132},{"id":"1708.01749","title":"SurfaceNet: An End-to-end 3D Neural Network for Multiview Stereopsis","created":"2017-08-05","cited_by_count":128},{"id":"1904.02342","title":"Text Generation from Knowledge Graphs with Graph Transformers","created":"2019-04-04","cited_by_count":122},{"id":"1712.08290","title":"CSGNet: Neural Shape Parser for Constructive Solid Geometry","created":"2017-12-22","cited_by_count":106},{"id":"2201.10326","title":"ShapeFormer: Transformer-based Shape Completion via Sparse Representation","created":"2022-01-25","cited_by_count":106},{"id":"1805.11085","title":"More Than a Feeling: Learning to Grasp and Regrasp using Vision and Touch","created":"2018-05-28","cited_by_count":102},{"id":"1908.04725","title":"Learning elementary structures for 3D shape generation and matching","created":"2019-08-13","cited_by_count":98},{"id":"2204.02389","title":"ObjectFolder 2.0: A Multisensory Object Dataset for Sim2Real Transfer","created":"2022-04-05","cited_by_count":75},{"id":"1901.02875","title":"Learning to Infer and Execute 3D Shape Programs","created":"2019-01-09","cited_by_count":68},{"id":"2203.14622","title":"Towards Implicit Text-Guided 3D Shape Generation","created":"2022-03-28","cited_by_count":68},{"id":"2207.09446","title":"ShapeCrafter: A Recursive Text-Conditioned 3D Shape Generation Model","created":"2022-07-19","cited_by_count":62},{"id":"2003.07717","title":"Multimodal Shape Completion via Conditional Generative Adversarial Networks","created":"2020-03-17","cited_by_count":61},{"id":"1812.11166","title":"Learning to Reconstruct Shapes from Unseen Classes","created":"2018-12-28","cited_by_count":60},{"id":"2106.02285","title":"Subdivision-Based Mesh Convolution Networks","created":"2021-06-04","cited_by_count":60},{"id":"1908.00575","title":"StructureNet: Hierarchical Graph Networks for 3D Shape Generation","created":"2019-08-01","cited_by_count":59},{"id":"1905.02925","title":"ShapeGlot: Learning Language for Shape Differentiation","created":"2019-05-08","cited_by_count":54},{"id":"2005.01819","title":"Neural Subdivision","created":"2020-05-04","cited_by_count":49},{"id":"2204.01955","title":"Autoregressive 3D Shape Generation via Canonical Mapping","created":"2022-04-05","cited_by_count":37},{"id":"2203.16531","title":"Understanding 3D Object Articulation in Internet Videos","created":"2022-03-30","cited_by_count":36},{"id":"2006.05353","title":"MeshWalker: Deep Mesh Understanding by Random Walks","created":"2020-06-09","cited_by_count":32},{"id":"1604.01879","title":"GIFT: A Real-time and Scalable 3D Shape Search Engine","created":"2016-04-07","cited_by_count":31},{"id":"2002.06478","title":"Learning to Group: A Bottom-Up Framework for 3D Part Discovery in Unseen Categories","created":"2020-02-16","cited_by_count":30},{"id":"1705.02090","title":"GRASS: Generative Recursive Autoencoders for Shape Structures","created":"2017-05-05","cited_by_count":24},{"id":"2009.08026","title":"ShapeAssembly: Learning to Generate Programs for 3D Shape Structure Synthesis","created":"2020-09-17","cited_by_count":19},{"id":"2206.07028","title":"Learning 3D Object Shape and Layout without 3D Supervision","created":"2022-06-14","cited_by_count":19},{"id":"2110.01182","title":"Differentiable 3D CAD Programs for Bidirectional Editing","created":"2021-10-04","cited_by_count":14},{"id":"2204.02289","title":"Neural Convolutional Surfaces","created":"2022-04-05","cited_by_count":9},{"id":"1911.08432","title":"Defective Convolutional Networks","created":"2019-11-19","cited_by_count":5},{"id":"2104.06392","title":"ShapeMOD: Macro Operation Discovery for 3D Shape Programs","created":"2021-04-13","cited_by_count":4}],"next_cursor":null}