{"total":248,"rows":[{"id":"2103.03206","title":"Perceiver: General Perception with Iterative Attention","created":"2021-03-04","cited_by_count":1104,"area":null},{"id":"2106.08903","title":"GemNet: Universal Directional Graph Neural Networks for Molecules","created":"2021-06-02","cited_by_count":343,"area":null},{"id":"2104.12229","title":"Vector Neurons: A General Framework for SO(3)-Equivariant Networks","created":"2021-04-25","cited_by_count":305,"area":null},{"id":"2101.02691","title":"Self-Supervised Pretraining of 3D Features on any Point-Cloud","created":"2021-01-07","cited_by_count":217,"area":null},{"id":"2110.03336","title":"Frame Averaging for Invariant and Equivariant Network Design","created":"2021-10-07","cited_by_count":168,"area":null},{"id":"2110.02910","title":"Equivariant Subgraph Aggregation Networks","created":"2021-10-06","cited_by_count":154,"area":null},{"id":"2101.04562","title":"Hyperbolic Deep Neural Networks: A Survey","created":"2021-01-12","cited_by_count":139,"area":null},{"id":"2211.06489","title":"Equivariance with Learned Canonicalization Functions","created":"2022-11-11","cited_by_count":109,"area":null},{"id":"2301.12780","title":"Equivariant Architectures for Learning in Deep Weight Spaces","created":"2023-01-30","cited_by_count":107,"area":null},{"id":"2102.11436","title":"Model-Based Domain Generalization","created":"2021-02-23","cited_by_count":104,"area":null},{"id":"2103.06526","title":"DualPoseNet: Category-level 6D Object Pose and Size Estimation Using Dual Pose Network with Refined Learning of Pose Consistency","created":"2021-03-11","cited_by_count":103,"area":null},{"id":"2103.16397","title":"3D AffordanceNet: A Benchmark for Visual Object Affordance Understanding","created":"2021-03-30","cited_by_count":100,"area":null},{"id":"2203.09283","title":"PanoFormer: Panorama Transformer for Indoor 360 Depth Estimation","created":"2022-03-17","cited_by_count":95,"area":null},{"id":"2102.04776","title":"Generative Models as Distributions of Functions","created":"2021-02-09","cited_by_count":89,"area":null},{"id":"2103.14147","title":"Equivariant Point Network for 3D Point Cloud Analysis","created":"2021-03-25","cited_by_count":81,"area":null},{"id":"2305.01118","title":"CSP: Self-Supervised Contrastive Spatial Pre-Training for Geospatial-Visual Representations","created":"2023-05-01","cited_by_count":69,"area":null},{"id":"2109.00182","title":"You Only Hypothesize Once: Point Cloud Registration with Rotation-equivariant Descriptors","created":"2021-09-01","cited_by_count":68,"area":null},{"id":"2105.13926","title":"Geometric Deep Learning and Equivariant Neural Networks","created":"2021-05-28","cited_by_count":65,"area":null},{"id":"2111.15669","title":"360MonoDepth: High-Resolution 360{\\deg} Monocular Depth Estimation","created":"2021-11-30","cited_by_count":60,"area":null},{"id":"2306.10619","title":"Towards Stability of Autoregressive Neural Operators","created":"2023-06-18","cited_by_count":59,"area":null},{"id":"2106.03336","title":"Wide-Baseline Relative Camera Pose Estimation with Directional Learning","created":"2021-06-07","cited_by_count":49,"area":null},{"id":"2206.14331","title":"Spherical Channels for Modeling Atomic Interactions","created":"2022-06-29","cited_by_count":47,"area":null},{"id":"2104.00568","title":"LED2-Net: Monocular 360 Layout Estimation via Differentiable Depth Rendering","created":"2021-04-01","cited_by_count":43,"area":null},{"id":"2308.09916","title":"VI-Net: Boosting Category-level 6D Object Pose Estimation via Learning Decoupled Rotations on the Spherical Representations","created":"2023-08-19","cited_by_count":41,"area":null},{"id":"2310.01647","title":"Equivariant Adaptation of Large Pretrained Models","created":"2023-10-02","cited_by_count":41,"area":null},{"id":"2205.10468","title":"Deep Learning for Omnidirectional Vision: A Survey and New Perspectives","created":"2022-05-21","cited_by_count":38,"area":null},{"id":"2106.02733","title":"DISCO: accurate Discrete Scale Convolutions","created":"2021-06-04","cited_by_count":36,"area":null},{"id":"2209.02952","title":"BiFuse++: Self-supervised and Efficient Bi-projection Fusion for 360 Depth Estimation","created":"2022-09-07","cited_by_count":35,"area":null},{"id":"2205.03972","title":"Robust (Controlled) Table-to-Text Generation with Structure-Aware Equivariance Learning","created":"2022-05-08","cited_by_count":32,"area":null},{"id":"2105.14291","title":"Deep Learning on Monocular Object Pose Detection and Tracking: A Comprehensive Overview","created":"2021-05-29","cited_by_count":31,"area":null},{"id":"2108.09169","title":"Geometry-Aware Self-Training for Unsupervised Domain Adaptationon Object Point Clouds","created":"2021-08-20","cited_by_count":31,"area":null},{"id":"2201.07788","title":"ConDor: Self-Supervised Canonicalization of 3D Pose for Partial Shapes","created":"2022-01-19","cited_by_count":31,"area":null},{"id":"2101.01000","title":"Conditional Local Convolution for Spatio-temporal Meteorological Forecasting","created":"2021-01-04","cited_by_count":30,"area":null},{"id":"2208.02879","title":"PointConvFormer: Revenge of the Point-based Convolution","created":"2022-08-04","cited_by_count":30,"area":null},{"id":"2202.13094","title":"RIConv++: Effective Rotation Invariant Convolutions for 3D Point Clouds Deep Learning","created":"2022-02-26","cited_by_count":29,"area":null},{"id":"2204.02394","title":"SE(3)-Equivariant Attention Networks for Shape Reconstruction in Function Space","created":"2022-04-05","cited_by_count":27,"area":null},{"id":"2306.06722","title":"$E(2)$-Equivariant Vision Transformer","created":"2023-06-11","cited_by_count":27,"area":null},{"id":"2107.10296","title":"Correspondence-Free Point Cloud Registration with SO(3)-Equivariant Implicit Shape Representations","created":"2021-07-21","cited_by_count":24,"area":null},{"id":"2209.13603","title":"Scalable and Equivariant Spherical CNNs by Discrete-Continuous (DISCO) Convolutions","created":"2022-09-27","cited_by_count":24,"area":null},{"id":"2311.02608","title":"Deep Learning-based 3D Point Cloud Classification: A Systematic Survey and Outlook","created":"2023-11-05","cited_by_count":24,"area":null},{"id":"2408.13242","title":"Improving Equivariant Model Training via Constraint Relaxation","created":"2024-08-23","cited_by_count":23,"area":null},{"id":"2110.13059","title":"Exploiting Redundancy: Separable Group Convolutional Networks on Lie Groups","created":"2021-10-25","cited_by_count":22,"area":null},{"id":"2209.15458","title":"Towards General-Purpose Representation Learning of Polygonal Geometries","created":"2022-09-29","cited_by_count":22,"area":null},{"id":"2105.05400","title":"Homogeneous vector bundles and $G$-equivariant convolutional neural networks","created":"2021-05-12","cited_by_count":21,"area":null},{"id":"2204.13630","title":"Rotationally Equivariant 3D Object Detection","created":"2022-04-28","cited_by_count":21,"area":null},{"id":"2306.05420","title":"Scaling Spherical CNNs","created":"2023-06-08","cited_by_count":21,"area":null},{"id":"2102.06942","title":"Rotation-Equivariant Deep Learning for Diffusion MRI","created":"2021-02-13","cited_by_count":20,"area":null},{"id":"2206.08362","title":"Unified Fourier-based Kernel and Nonlinearity Design for Equivariant Networks on Homogeneous Spaces","created":"2022-06-16","cited_by_count":20,"area":null},{"id":"2307.07313","title":"HEAL-SWIN: A Vision Transformer On The Sphere","created":"2023-07-14","cited_by_count":20,"area":null},{"id":"2310.02299","title":"Discovering Symmetry Breaking in Physical Systems with Relaxed Group Convolution","created":"2023-10-03","cited_by_count":20,"area":null},{"id":"2104.03584","title":"PDO-eS2CNNs: Partial Differential Operator Based Equivariant Spherical CNNs","created":"2021-04-08","cited_by_count":19,"area":null},{"id":"2110.06084","title":"Implicit Bias of Linear Equivariant Networks","created":"2021-10-12","cited_by_count":19,"area":null},{"id":"2112.01741","title":"Frame Averaging for Equivariant Shape Space Learning","created":"2021-12-03","cited_by_count":19,"area":null},{"id":"2212.08892","title":"Flattening-Net: Deep Regular 2D Representation for 3D Point Cloud Analysis","created":"2022-12-17","cited_by_count":19,"area":null},{"id":"2303.15651","title":"4D Panoptic Segmentation as Invariant and Equivariant Field Prediction","created":"2023-03-28","cited_by_count":19,"area":null},{"id":"2102.02828","title":"Scattering Networks on the Sphere for Scalable and Rotationally Equivariant Spherical CNNs","created":"2021-02-04","cited_by_count":18,"area":null},{"id":"2103.16516","title":"Recognizing Actions in Videos from Unseen Viewpoints","created":"2021-03-30","cited_by_count":18,"area":null},{"id":"2205.13599","title":"VectorAdam for Rotation Equivariant Geometry Optimization","created":"2022-05-26","cited_by_count":18,"area":null},{"id":"2406.10322","title":"LieRE: Lie Rotational Positional Encodings","created":"2024-06-14","cited_by_count":18,"area":null},{"id":"2504.08896","title":"Position: Beyond Euclidean -- Foundation Models Should Embrace Non-Euclidean Geometries","created":"2025-04-11","cited_by_count":18,"area":null},{"id":"2111.07383","title":"Sparse Steerable Convolutions: An Efficient Learning of SE(3)-Equivariant Features for Estimation and Tracking of Object Poses in 3D Space","created":"2021-11-14","cited_by_count":17,"area":null},{"id":"2106.06662","title":"Equivariant Networks for Pixelized Spheres","created":"2021-06-12","cited_by_count":16,"area":null},{"id":"2204.01159","title":"Shape-Pose Disentanglement using SE(3)-equivariant Vector Neurons","created":"2022-04-03","cited_by_count":16,"area":null},{"id":"2303.01043","title":"I2P-Rec: Recognizing Images on Large-scale Point Cloud Maps through Bird's Eye View Projections","created":"2023-03-02","cited_by_count":16,"area":null},{"id":"2505.01458","title":"A Survey of Robotic Navigation and Manipulation with Physics Simulators in the Era of Embodied AI","created":"2025-05-01","cited_by_count":16,"area":null},{"id":"2102.12093","title":"PRIN/SPRIN: On Extracting Point-wise Rotation Invariant Features","created":"2021-02-24","cited_by_count":15,"area":null},{"id":"2103.09360","title":"Towards physically consistent data-driven weather forecasting: Integrating data assimilation with equivariance-preserving deep spatial transformers","created":"2021-03-16","cited_by_count":15,"area":null},{"id":"2104.06703","title":"Deep Permutation Equivariant Structure from Motion","created":"2021-04-14","cited_by_count":15,"area":null},{"id":"2106.05886","title":"Group Equivariant Subsampling","created":"2021-06-10","cited_by_count":15,"area":null},{"id":"2209.08956","title":"Panoramic Vision Transformer for Saliency Detection in 360{\\deg} Videos","created":"2022-09-19","cited_by_count":15,"area":null},{"id":"2212.07347","title":"Lorentz group equivariant autoencoders","created":"2022-12-14","cited_by_count":15,"area":null},{"id":"2409.00353","title":"RI-MAE: Rotation-Invariant Masked AutoEncoders for Self-Supervised Point Cloud Representation Learning","created":"2024-08-31","cited_by_count":15,"area":null},{"id":"2304.10528","title":"Generalizing Neural Human Fitting to Unseen Poses With Articulated SE(3) Equivariance","created":"2023-04-20","cited_by_count":14,"area":null},{"id":"2111.08190","title":"Learning Augmentation Distributions using Transformed Risk Minimization","created":"2021-11-16","cited_by_count":13,"area":null},{"id":"2201.12212","title":"M\\\"obius Convolutions for Spherical CNNs","created":"2022-01-28","cited_by_count":13,"area":null},{"id":"2208.14543","title":"BioSLAM: A Bio-inspired Lifelong Memory System for General Place Recognition","created":"2022-08-30","cited_by_count":13,"area":null},{"id":"2101.00483","title":"Learning Rotation-Invariant Representations of Point Clouds Using Aligned Edge Convolutional Neural Networks","created":"2021-01-02","cited_by_count":12,"area":null},{"id":"2203.03888","title":"ART-Point: Improving Rotation Robustness of Point Cloud Classifiers via Adversarial Rotation","created":"2022-03-08","cited_by_count":12,"area":null},{"id":"2307.08252","title":"Large-Scale Person Detection and Localization using Overhead Fisheye Cameras","created":"2023-07-17","cited_by_count":12,"area":null},{"id":"2106.15301","title":"VolterraNet: A higher order convolutional network with group equivariance for homogeneous manifolds","created":"2021-06-05","cited_by_count":11,"area":null},{"id":"2202.04942","title":"Spherical Transformer","created":"2022-02-10","cited_by_count":11,"area":null},{"id":"2209.04497","title":"General Place Recognition Survey: Towards the Real-world Autonomy Age","created":"2022-09-09","cited_by_count":11,"area":null},{"id":"2401.09252","title":"3D Scene Geometry Estimation from 360$^\\circ$ Imagery: A Survey","created":"2024-01-17","cited_by_count":11,"area":null},{"id":"2402.00019","title":"Diffusion MRI with Machine Learning","created":"2024-01-01","cited_by_count":11,"area":null},{"id":"2111.08799","title":"DeltaConv: Anisotropic Operators for Geometric Deep Learning on Point Clouds","created":"2021-11-16","cited_by_count":10,"area":null},{"id":"2207.06965","title":"AutoMerge: A Framework for Map Assembling and Smoothing in City-scale Environments","created":"2022-07-14","cited_by_count":10,"area":null},{"id":"2209.05924","title":"SVNet: Where SO(3) Equivariance Meets Binarization on Point Cloud Representation","created":"2022-09-13","cited_by_count":10,"area":null},{"id":"2301.07895","title":"Spatially Covariant Lesion Segmentation","created":"2023-01-19","cited_by_count":10,"area":null},{"id":"2308.03312","title":"Exploiting Code Symmetries for Learning Program Semantics","created":"2023-08-07","cited_by_count":10,"area":null},{"id":"2505.11157","title":"Attention on the Sphere","created":"2025-05-16","cited_by_count":10,"area":null},{"id":"2210.02045","title":"Coarse-to-Fine Point Cloud Registration with SE(3)-Equivariant Representations","created":"2022-10-05","cited_by_count":9,"area":null},{"id":"2210.03773","title":"In What Ways Are Deep Neural Networks Invariant and How Should We Measure This?","created":"2022-10-07","cited_by_count":9,"area":null},{"id":"2212.06096","title":"Implicit Convolutional Kernels for Steerable CNNs","created":"2022-12-12","cited_by_count":9,"area":null},{"id":"2210.00935","title":"Analysis of (sub-)Riemannian PDE-G-CNNs","created":"2022-10-03","cited_by_count":8,"area":null},{"id":"2311.11106","title":"ShapeMatcher: Self-Supervised Joint Shape Canonicalization, Segmentation, Retrieval and Deformation","created":"2023-11-18","cited_by_count":8,"area":null},{"id":"2401.13786","title":"FoVA-Depth: Field-of-View Agnostic Depth Estimation for Cross-Dataset Generalization","created":"2024-01-24","cited_by_count":8,"area":null},{"id":"2408.06321","title":"EqNIO: Subequivariant Neural Inertial Odometry","created":"2024-08-12","cited_by_count":8,"area":null},{"id":"2503.04123","title":"GAGrasp: Geometric Algebra Diffusion for Dexterous Grasping","created":"2025-03-06","cited_by_count":8,"area":null},{"id":"2102.03939","title":"Single-Shot Cuboids: Geodesics-based End-to-end Manhattan Aligned Layout Estimation from Spherical Panoramas","created":"2021-02-07","cited_by_count":7,"area":null},{"id":"2107.09179","title":"OSLO: On-the-Sphere Learning for Omnidirectional images and its application to 360-degree image compression","created":"2021-07-19","cited_by_count":7,"area":null}],"next_cursor":"100"}