{"list":"other","total":52,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1503.03585","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","created":"2015-03-12","cited_by_count":7058},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"1612.00593","title":"PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation","created":"2016-12-02","cited_by_count":5248},{"id":"1310.4546","title":"Distributed Representations of Words and Phrases and their Compositionality","created":"2013-10-16","cited_by_count":3474},{"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":"2211.10440","title":"Magic3D: High-Resolution Text-to-3D Content Creation","created":"2022-11-18","cited_by_count":1290},{"id":"1904.08755","title":"4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks","created":"2019-04-18","cited_by_count":1208},{"id":"2007.08501","title":"Accelerating 3D Deep Learning with PyTorch3D","created":"2020-07-16","cited_by_count":784},{"id":"2303.13873","title":"Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creation","created":"2023-03-24","cited_by_count":687},{"id":"1505.00880","title":"Multi-view Convolutional Neural Networks for 3D Shape Recognition","created":"2015-05-05","cited_by_count":565},{"id":"1912.12033","title":"Deep Learning for 3D Point Clouds: A Survey","created":"2019-12-27","cited_by_count":558},{"id":"1707.00600","title":"Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Ugly","created":"2017-07-03","cited_by_count":538},{"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":"1812.02713","title":"PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understanding","created":"2018-12-06","cited_by_count":526},{"id":"2112.02413","title":"PointCLIP: Point Cloud Understanding by CLIP","created":"2021-12-04","cited_by_count":463},{"id":"2210.05666","title":"Point Transformer V2: Grouped Vector Attention and Partition-based Pooling","created":"2022-10-11","cited_by_count":388},{"id":"2303.16203","title":"Your Diffusion Model is Secretly a Zero-Shot Classifier","created":"2023-03-28","cited_by_count":306},{"id":"2212.05171","title":"ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understanding","created":"2022-12-10","cited_by_count":267},{"id":"1812.01784","title":"Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders","created":"2018-12-05","cited_by_count":206},{"id":"2302.02318","title":"Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining","created":"2023-02-05","cited_by_count":164},{"id":"2210.01055","title":"CLIP2Point: Transfer CLIP to Point Cloud Classification with Image-Depth Pre-training","created":"2022-10-03","cited_by_count":160},{"id":"2303.15233","title":"Text-to-Image Diffusion Models are Zero-Shot Classifiers","created":"2023-03-27","cited_by_count":143},{"id":"2303.11313","title":"CLIP goes 3D: Leveraging Prompt Tuning for Language Grounded 3D Recognition","created":"2023-03-20","cited_by_count":77},{"id":"2303.08231","title":"Rotation-Invariant Transformer for Point Cloud Matching","created":"2023-03-14","cited_by_count":69},{"id":"2108.06230","title":"Generative Zero-Shot Learning for Semantic Segmentation of 3D Point Clouds","created":"2021-08-13","cited_by_count":55},{"id":"2212.02291","title":"I2MVFormer: Large Language Model Generated Multi-View Document Supervision for Zero-Shot Image Classification","created":"2022-12-05","cited_by_count":54},{"id":"1912.07161","title":"Transductive Zero-Shot Learning for 3D Point Cloud Classification","created":"2019-12-16","cited_by_count":39},{"id":"2104.04980","title":"Zero-Shot Learning on 3D Point Cloud Objects and Beyond","created":"2021-04-11","cited_by_count":38},{"id":"1902.10272","title":"Zero-shot Learning of 3D Point Cloud Objects","created":"2019-02-27","cited_by_count":34},{"id":"2305.17940","title":"Learning Conditional Attributes for Compositional Zero-Shot Learning","created":"2023-05-29","cited_by_count":28},{"id":"2011.03298","title":"Learning to Orient Surfaces by Self-supervised Spherical CNNs","created":"2020-11-06","cited_by_count":26},{"id":"2207.11209","title":"Divide and Conquer: 3D Point Cloud Instance Segmentation With Point-Wise Binarization","created":"2022-07-22","cited_by_count":26},{"id":"1907.06371","title":"Mitigating the Hubness Problem for Zero-Shot Learning of 3D Objects","created":"2019-07-15","cited_by_count":24},{"id":"2303.15472","title":"Learning Rotation-Equivariant Features for Visual Correspondence","created":"2023-03-25","cited_by_count":23},{"id":"2305.15957","title":"DiffCLIP: Leveraging Stable Diffusion for Language Grounded 3D Classification","created":"2023-05-25","cited_by_count":23},{"id":"2011.09080","title":"Deep Positional and Relational Feature Learning for Rotation-Invariant Point Cloud Analysis","created":"2020-11-18","cited_by_count":22},{"id":"2205.15210","title":"The Devil is in the Pose: Ambiguity-free 3D Rotation-invariant Learning via Pose-aware Convolution","created":"2022-05-30","cited_by_count":18},{"id":"2308.05733","title":"FrozenRecon: Pose-free 3D Scene Reconstruction with Frozen Depth Models","created":"2023-08-10","cited_by_count":17},{"id":"2111.14673","title":"3D Compositional Zero-shot Learning with DeCompositional Consensus","created":"2021-11-29","cited_by_count":16},{"id":"2106.08605","title":"Disentangling Semantic-to-visual Confusion for Zero-shot Learning","created":"2021-06-16","cited_by_count":11},{"id":"2307.03416","title":"Learning Adversarial Semantic Embeddings for Zero-Shot Recognition in Open Worlds","created":"2023-07-07","cited_by_count":11},{"id":"2012.06236","title":"Improving Zero Shot Learning Baselines with Commonsense Knowledge","created":"2020-12-11","cited_by_count":10},{"id":"2108.07084","title":"Learning Canonical View Representation for 3D Shape Recognition with Arbitrary Views","created":"2021-08-16","cited_by_count":9},{"id":"2210.07031","title":"Rebalanced Zero-shot Learning","created":"2022-10-13","cited_by_count":8},{"id":"2308.03059","title":"Language-based Photo Color Adjustment for Graphic Designs","created":"2023-08-06","cited_by_count":6}],"next_cursor":null}