{"total":33,"rows":[{"id":"2104.03059","title":"Differentiable Patch Selection for Image Recognition","created":"2021-04-07","cited_by_count":68,"area":null},{"id":"2108.01684","title":"Vision Transformer with Progressive Sampling","created":"2021-08-03","cited_by_count":44,"area":null},{"id":"2108.12204","title":"This looks more like that: Enhancing Self-Explaining Models by Prototypical Relevance Propagation","created":"2021-08-27","cited_by_count":43,"area":null},{"id":"2207.00938","title":"Interpretable by Design: Learning Predictors by Composing Interpretable Queries","created":"2022-07-03","cited_by_count":28,"area":null},{"id":"2102.10212","title":"Hard-Attention for Scalable Image Classification","created":"2021-02-20","cited_by_count":18,"area":null},{"id":"2210.02578","title":"AOE-Net: Entities Interactions Modeling with Adaptive Attention Mechanism for Temporal Action Proposals Generation","created":"2022-10-05","cited_by_count":14,"area":null},{"id":"2111.07534","title":"A Probabilistic Hard Attention Model For Sequentially Observed Scenes","created":"2021-11-15","cited_by_count":12,"area":null},{"id":"2110.11474","title":"AEI: Actors-Environment Interaction with Adaptive Attention for Temporal Action Proposals Generation","created":"2021-10-21","cited_by_count":11,"area":null},{"id":"2204.00656","title":"Consistency driven Sequential Transformers Attention Model for Partially Observable Scenes","created":"2022-04-01","cited_by_count":11,"area":null},{"id":"2312.01450","title":"Foveation in the Era of Deep Learning","created":"2023-12-03","cited_by_count":8,"area":null},{"id":"2202.05535","title":"A Lightweight, Efficient and Explainable-by-Design Convolutional Neural Network for Internet Traffic Classification","created":"2022-02-11","cited_by_count":6,"area":null},{"id":"2401.14089","title":"GQHAN: A Grover-inspired Quantum Hard Attention Network","created":"2024-01-25","cited_by_count":5,"area":null},{"id":"2110.00523","title":"Mask or Non-Mask? Robust Face Mask Detector via Triplet-Consistency Representation Learning","created":"2021-10-01","cited_by_count":3,"area":null},{"id":"2403.15977","title":"Towards Two-Stream Foveation-based Active Vision Learning","created":"2024-03-24","cited_by_count":3,"area":null},{"id":"2505.13191","title":"Emergence of Fixational and Saccadic Movements in a Multi-Level Recurrent Attention Model for Vision","created":"2025-05-19","cited_by_count":3,"area":null},{"id":"2110.04954","title":"Recurrent Attention Models with Object-centric Capsule Representation for Multi-object Recognition","created":"2021-10-11","cited_by_count":2,"area":null},{"id":"2602.03766","title":"FOVI: A biologically-inspired foveated interface for deep vision models","created":"2026-02-03","cited_by_count":2,"area":null},{"id":"2210.13605","title":"GliTr: Glimpse Transformers with Spatiotemporal Consistency for Online Action Prediction","created":"2022-10-24","cited_by_count":1,"area":null},{"id":"2401.17515","title":"Semantic-Syntactic Discrepancy in Images (SSDI): Learning Meaning and Order of Features from Natural Images","created":"2024-01-31","cited_by_count":1,"area":null},{"id":"2404.00185","title":"On Inherent Adversarial Robustness of Active Vision Systems","created":"2024-03-29","cited_by_count":1,"area":null},{"id":"2404.10836","title":"Semantic-Based Active Perception for Humanoid Visual Tasks with Foveal Sensors","created":"2024-04-16","cited_by_count":1,"area":null},{"id":"2406.17483","title":"TRIP: Trainable Region-of-Interest Prediction for Hardware-Efficient Neuromorphic Processing on Event-based Vision","created":"2024-06-25","cited_by_count":1,"area":null},{"id":"2603.22570","title":"CanViT: Toward Active-Vision Foundation Models","created":"2026-03-23","cited_by_count":1,"area":null},{"id":"2207.13460","title":"Adaptive sampling for scanning pixel cameras","created":"2022-07-27","cited_by_count":0,"area":null},{"id":"2310.06578","title":"Energy-Efficient Visual Search by Eye Movement and Low-Latency Spiking Neural Network","created":"2023-10-10","cited_by_count":0,"area":null},{"id":"2310.07800","title":"Language-Guided Reinforcement Learning for Hard Attention in Few-Shot Learning","created":"2023-10-11","cited_by_count":0,"area":null},{"id":"2504.02536","title":"A Sensorimotor Vision Transformer","created":"2025-04-03","cited_by_count":0,"area":null},{"id":"2510.08761","title":"SAFER-AiD: Saccade-Assisted Foveal-peripheral vision Enhanced Reconstruction for Adversarial Defense","created":"2025-10-09","cited_by_count":0,"area":null},{"id":"2603.09613","title":"A Saccade-inspired Approach to Image Classification using Vision Transformer Attention Maps","created":"2026-03-10","cited_by_count":0,"area":null},{"id":"2603.27340","title":"EVA: Bridging Performance and Human Alignment in Hard-Attention Vision Models for Image Classification","created":"2026-03-28","cited_by_count":0,"area":null},{"id":"2604.16485","title":"Saccade Attention Networks: Using Transfer Learning of Attention to Reduce Network Sizes","created":"2026-04-13","cited_by_count":0,"area":null},{"id":"2608.02140","title":"HiResNets: Native Full-HD Video Recognition with Foveal Residual Streams","created":"2026-08-03","cited_by_count":0,"area":null},{"id":"2609.09025","title":"Task-driven Processing with Coarse-to-Fine Glimpse-based Active Perception","created":"2026-09-08","cited_by_count":0,"area":null}],"next_cursor":null}