{"total":77,"rows":[{"id":"2103.11251","title":"Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges","created":"2021-03-20","cited_by_count":367,"area":null},{"id":"2102.12627","title":"How to represent part-whole hierarchies in a neural network","created":"2021-02-25","cited_by_count":123,"area":null},{"id":"2103.01209","title":"Generative Adversarial Transformers","created":"2021-03-01","cited_by_count":120,"area":null},{"id":"2104.09958","title":"GENESIS-V2: Inferring Unordered Object Representations without Iterative Refinement","created":"2021-04-20","cited_by_count":109,"area":null},{"id":"2110.04361","title":"SubTab: Subsetting Features of Tabular Data for Self-Supervised Representation Learning","created":"2021-10-08","cited_by_count":104,"area":null},{"id":"2111.06349","title":"Unsupervised Part Discovery from Contrastive Reconstruction","created":"2021-11-11","cited_by_count":57,"area":null},{"id":"2302.04973","title":"Invariant Slot Attention: Object Discovery with Slot-Centric Reference Frames","created":"2023-02-09","cited_by_count":51,"area":null},{"id":"2104.14575","title":"Unsupervised Layered Image Decomposition into Object Prototypes","created":"2021-04-29","cited_by_count":50,"area":null},{"id":"2202.07559","title":"Unsupervised Learning of Group Invariant and Equivariant Representations","created":"2022-02-15","cited_by_count":39,"area":null},{"id":"2108.00580","title":"GraphFPN: Graph Feature Pyramid Network for Object Detection","created":"2021-08-02","cited_by_count":25,"area":null},{"id":"2108.08557","title":"DECA: Deep viewpoint-Equivariant human pose estimation using Capsule Autoencoders","created":"2021-08-19","cited_by_count":23,"area":null},{"id":"2310.06131","title":"Learning Layer-wise Equivariances Automatically using Gradients","created":"2023-10-09","cited_by_count":23,"area":null},{"id":"2311.02007","title":"Towards Unsupervised Object Detection From LiDAR Point Clouds","created":"2023-11-03","cited_by_count":23,"area":null},{"id":"2107.05790","title":"Visual Parser: Representing Part-whole Hierarchies with Transformers","created":"2021-07-13","cited_by_count":21,"area":null},{"id":"2109.03351","title":"Capturing the objects of vision with neural networks","created":"2021-09-07","cited_by_count":21,"area":null},{"id":"2110.00529","title":"Unsupervised Motion Representation Learning with Capsule Autoencoders","created":"2021-10-01","cited_by_count":16,"area":null},{"id":"2106.05886","title":"Group Equivariant Subsampling","created":"2021-06-10","cited_by_count":15,"area":null},{"id":"2404.15672","title":"Representing Part-Whole Hierarchies in Foundation Models by Learning Localizability, Composability, and Decomposability from Anatomy via Self-Supervision","created":"2024-04-24","cited_by_count":13,"area":null},{"id":"2103.15459","title":"Capsule Network is Not More Robust than Convolutional Network","created":"2021-03-29","cited_by_count":12,"area":null},{"id":"2304.03282","title":"Visual Dependency Transformers: Dependency Tree Emerges from Reversed Attention","created":"2023-04-06","cited_by_count":12,"area":null},{"id":"2203.03282","title":"Interpretable part-whole hierarchies and conceptual-semantic relationships in neural networks","created":"2022-03-07","cited_by_count":11,"area":null},{"id":"2103.00752","title":"Reasons, Values, Stakeholders: A Philosophical Framework for Explainable Artificial Intelligence","created":"2021-03-01","cited_by_count":10,"area":null},{"id":"2206.02664","title":"Learning with Capsules: A Survey","created":"2022-06-06","cited_by_count":10,"area":null},{"id":"2305.17023","title":"Are Deep Neural Networks Adequate Behavioural Models of Human Visual Perception?","created":"2023-05-26","cited_by_count":10,"area":null},{"id":"2203.11194","title":"Test-time Adaptation with Slot-Centric Models","created":"2022-03-21","cited_by_count":9,"area":null},{"id":"2101.11513","title":"State estimation with limited sensors -- A deep learning based approach","created":"2021-01-27","cited_by_count":7,"area":null},{"id":"2203.10699","title":"HP-Capsule: Unsupervised Face Part Discovery by Hierarchical Parsing Capsule Network","created":"2022-03-21","cited_by_count":7,"area":null},{"id":"2108.07543","title":"Graph Capsule Aggregation for Unaligned Multimodal Sequences","created":"2021-08-17","cited_by_count":6,"area":null},{"id":"2110.03473","title":"Unsupervised Image Decomposition with Phase-Correlation Networks","created":"2021-10-07","cited_by_count":6,"area":null},{"id":"2201.08813","title":"Active Predictive Coding Networks: A Neural Solution to the Problem of Learning Reference Frames and Part-Whole Hierarchies","created":"2022-01-14","cited_by_count":6,"area":null},{"id":"2301.01583","title":"Why Capsule Neural Networks Do Not Scale: Challenging the Dynamic Parse-Tree Assumption","created":"2023-01-04","cited_by_count":6,"area":null},{"id":"2111.10854","title":"XnODR and XnIDR: Two Accurate and Fast Fully Connected Layers For Convolutional Neural Networks","created":"2021-11-21","cited_by_count":5,"area":null},{"id":"2112.00775","title":"Routing with Self-Attention for Multimodal Capsule Networks","created":"2021-12-01","cited_by_count":5,"area":null},{"id":"2206.01829","title":"Drawing out of Distribution with Neuro-Symbolic Generative Models","created":"2022-06-03","cited_by_count":5,"area":null},{"id":"2304.09704","title":"Learnable Earth Parser: Discovering 3D Prototypes in Aerial Scans","created":"2023-04-19","cited_by_count":5,"area":null},{"id":"2312.12223","title":"Self-Supervised Detection of Perfect and Partial Input-Dependent Symmetries","created":"2023-12-19","cited_by_count":4,"area":null},{"id":"2411.00868","title":"Unsupervised Object Discovery: A Comprehensive Survey and Unified Taxonomy","created":"2024-10-30","cited_by_count":4,"area":null},{"id":"2104.05031","title":"Deformable Capsules for Object Detection","created":"2021-04-11","cited_by_count":3,"area":null},{"id":"2107.11153","title":"Constellation: Learning relational abstractions over objects for compositional imagination","created":"2021-07-23","cited_by_count":3,"area":null},{"id":"2209.15567","title":"Holographic-(V)AE: an end-to-end SO(3)-Equivariant (Variational) Autoencoder in Fourier Space","created":"2022-09-30","cited_by_count":3,"area":null},{"id":"2302.03531","title":"Structured Generative Models for Scene Understanding","created":"2023-02-07","cited_by_count":3,"area":null},{"id":"2303.10896","title":"Graphics Capsule: Learning Hierarchical 3D Face Representations from 2D Images","created":"2023-03-20","cited_by_count":3,"area":null},{"id":"2101.06848","title":"Faster Convergence in Deep-Predictive-Coding Networks to Learn Deeper Representations","created":"2021-01-18","cited_by_count":2,"area":null},{"id":"2103.06676","title":"Inference for Generative Capsule Models","created":"2021-03-11","cited_by_count":2,"area":null},{"id":"2104.14735","title":"DPR-CAE: Capsule Autoencoder with Dynamic Part Representation for Image Parsing","created":"2021-04-30","cited_by_count":2,"area":null},{"id":"2107.02453","title":"Neural Mixture Models with Expectation-Maximization for End-to-end Deep Clustering","created":"2021-07-06","cited_by_count":2,"area":null},{"id":"2110.02911","title":"Shifting Capsule Networks from the Cloud to the Deep Edge","created":"2021-10-06","cited_by_count":2,"area":null},{"id":"2204.01298","title":"Capsule Networks Do Not Need to Model Everything","created":"2022-04-04","cited_by_count":2,"area":null},{"id":"2209.03115","title":"Inference and Learning for Generative Capsule Models","created":"2022-09-07","cited_by_count":2,"area":null},{"id":"2307.16005","title":"Enhancing Object Detection in Ancient Documents with Synthetic Data Generation and Transformer-Based Models","created":"2023-07-29","cited_by_count":2,"area":null},{"id":"2405.14386","title":"Capsule Network Projectors are Equivariant and Invariant Learners","created":"2024-05-23","cited_by_count":2,"area":null},{"id":"2111.12873","title":"Quantised Transforming Auto-Encoders: Achieving Equivariance to Arbitrary Transformations in Deep Networks","created":"2021-11-25","cited_by_count":1,"area":null},{"id":"2112.07954","title":"Object Pursuit: Building a Space of Objects via Discriminative Weight Generation","created":"2021-12-15","cited_by_count":1,"area":null},{"id":"2209.00232","title":"Hybrid Gromov-Wasserstein Embedding for Capsule Learning","created":"2022-09-01","cited_by_count":1,"area":null},{"id":"2209.05239","title":"$\\beta$-CapsNet: Learning Disentangled Representation for CapsNet by Information Bottleneck","created":"2022-09-12","cited_by_count":1,"area":null},{"id":"2302.08682","title":"Random Padding Data Augmentation","created":"2023-02-17","cited_by_count":1,"area":null},{"id":"2308.09897","title":"Spatial-Temporal Alignment Network for Action Recognition","created":"2023-08-19","cited_by_count":1,"area":null},{"id":"2311.17975","title":"GeoDeformer: Geometric Deformable Transformer for Action Recognition","created":"2023-11-29","cited_by_count":1,"area":null},{"id":"2403.04724","title":"Masked Capsule Autoencoders","created":"2024-03-07","cited_by_count":1,"area":null},{"id":"2406.19726","title":"EPOCH: Jointly Estimating the 3D Pose of Cameras and Humans","created":"2024-06-28","cited_by_count":1,"area":null},{"id":"2505.13289","title":"RECON: Robust symmetry discovery via Explicit Canonical Orientation Normalization","created":"2025-05-19","cited_by_count":1,"area":null},{"id":"2603.14022","title":"A Hyperbolic Perspective on Hierarchical Structure in Object-Centric Scene Representations","created":"2026-03-14","cited_by_count":1,"area":null},{"id":"2103.12404","title":"Diversity Regularized Interests Modeling for Recommender Systems","created":"2021-03-23","cited_by_count":0,"area":null},{"id":"2104.00698","title":"Back to Square One: Superhuman Performance in Chutes and Ladders Through Deep Neural Networks and Tree Search","created":"2021-04-01","cited_by_count":0,"area":null},{"id":"2109.02231","title":"Image recognition via Vietoris-Rips complex","created":"2021-09-06","cited_by_count":0,"area":null},{"id":"2202.13755","title":"Towards Robust Stacked Capsule Autoencoder with Hybrid Adversarial Training","created":"2022-02-28","cited_by_count":0,"area":null},{"id":"2203.08948","title":"CapsNet for Medical Image Segmentation","created":"2022-03-16","cited_by_count":0,"area":null},{"id":"2205.14195","title":"Unsupervised learning of features and object boundaries from local prediction","created":"2022-05-27","cited_by_count":0,"area":null},{"id":"2211.07082","title":"Learning Latent Part-Whole Hierarchies for Point Clouds","created":"2022-11-14","cited_by_count":0,"area":null},{"id":"2302.06194","title":"Capsules as viewpoint learners for human pose estimation","created":"2023-02-13","cited_by_count":0,"area":null},{"id":"2304.13538","title":"ElegansNet: a brief scientific report and initial experiments","created":"2023-04-06","cited_by_count":0,"area":null},{"id":"2305.05349","title":"Towards the Characterization of Representations Learned via Capsule-based Network Architectures","created":"2023-05-09","cited_by_count":0,"area":null},{"id":"2307.10212","title":"Capsule network with shortcut routing","created":"2023-07-14","cited_by_count":0,"area":null},{"id":"2401.00824","title":"Graph-Convolutional Autoencoder Ensembles for the Humanities, Illustrated with a Study of the American Slave Trade","created":"2024-01-01","cited_by_count":0,"area":null},{"id":"2604.19480","title":"Deep Sprite-based Image Models: An Analysis","created":"2026-04-21","cited_by_count":0,"area":null},{"id":"2607.08249","title":"HSA: Hierarchical Slot Attention for Multi-granularity Scene-Decomposition","created":"2026-07-09","cited_by_count":0,"area":null},{"id":"2609.07939","title":"Bottom-up Modeling of Repeated Elements via Single Image Analysis-by-Synthesis","created":"2026-09-07","cited_by_count":0,"area":null}],"next_cursor":null}