{"total":97,"rows":[{"id":"2202.07125","title":"Transformers in Time Series: A Survey","created":"2022-02-15","cited_by_count":497,"area":null},{"id":"2111.06091","title":"A Survey of Visual Transformers","created":"2021-11-11","cited_by_count":117,"area":null},{"id":"2103.14636","title":"A Practical Survey on Faster and Lighter Transformers","created":"2021-03-26","cited_by_count":73,"area":null},{"id":"2103.16775","title":"Attention, please! A survey of Neural Attention Models in Deep Learning","created":"2021-03-31","cited_by_count":51,"area":null},{"id":"2305.05813","title":"Change Detection Methods for Remote Sensing in the Last Decade: A Comprehensive Review","created":"2023-05-09","cited_by_count":41,"area":null},{"id":"2307.10236","title":"Look Before You Leap: An Exploratory Study of Uncertainty Measurement for Large Language Models","created":"2023-07-16","cited_by_count":41,"area":null},{"id":"2105.03287","title":"Order in the Court: Explainable AI Methods Prone to Disagreement","created":"2021-05-07","cited_by_count":36,"area":null},{"id":"2311.05014","title":"Interpreting Pretrained Language Models via Concept Bottlenecks","created":"2023-11-08","cited_by_count":33,"area":null},{"id":"2211.00385","title":"Behavioral Intention Prediction in Driving Scenes: A Survey","created":"2022-11-01","cited_by_count":30,"area":null},{"id":"2109.01876","title":"Attentive Neural Controlled Differential Equations for Time-series Classification and Forecasting","created":"2021-09-04","cited_by_count":29,"area":null},{"id":"2204.13154","title":"Attention Mechanism in Neural Networks: Where it Comes and Where it Goes","created":"2022-04-27","cited_by_count":29,"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":"2102.08036","title":"Exploring Transformers in Natural Language Generation: GPT, BERT, and XLNet","created":"2021-02-16","cited_by_count":27,"area":null},{"id":"2104.12874","title":"Accounting for Agreement Phenomena in Sentence Comprehension with Transformer Language Models: Effects of Similarity-based Interference on Surprisal and Attention","created":"2021-04-26","cited_by_count":27,"area":null},{"id":"2309.11932","title":"A Machine Learning-oriented Survey on Tiny Machine Learning","created":"2023-09-21","cited_by_count":27,"area":null},{"id":"2111.05711","title":"Counterfactual Explanations for Models of Code","created":"2021-11-10","cited_by_count":25,"area":null},{"id":"2211.13290","title":"SEAT: Stable and Explainable Attention","created":"2022-11-23","cited_by_count":25,"area":null},{"id":"2111.04129","title":"Global-Local Attention for Emotion Recognition","created":"2021-11-07","cited_by_count":20,"area":null},{"id":"2204.03503","title":"Survey on Automated Short Answer Grading with Deep Learning: from Word Embeddings to Transformers","created":"2022-03-11","cited_by_count":20,"area":null},{"id":"2206.03945","title":"Challenges in Applying Explainability Methods to Improve the Fairness of NLP Models","created":"2022-06-08","cited_by_count":20,"area":null},{"id":"2303.06471","title":"Multimodal Data Integration for Oncology in the Era of Deep Neural Networks: A Review","created":"2023-03-11","cited_by_count":20,"area":null},{"id":"2402.14182","title":"Do Machines and Humans Focus on Similar Code? Exploring Explainability of Large Language Models in Code Summarization","created":"2024-02-22","cited_by_count":16,"area":null},{"id":"2408.09121","title":"Selective Prompt Anchoring for Code Generation","created":"2024-08-17","cited_by_count":16,"area":null},{"id":"2105.14953","title":"ACE-NODE: Attentive Co-Evolving Neural Ordinary Differential Equations","created":"2021-05-31","cited_by_count":15,"area":null},{"id":"2208.08236","title":"DPA-1: Pretraining of Attention-based Deep Potential Model for Molecular Simulation","created":"2022-08-17","cited_by_count":15,"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":"2306.01220","title":"Do Large Language Models Pay Similar Attention Like Human Programmers When Generating Code?","created":"2023-06-02","cited_by_count":14,"area":null},{"id":"2305.18450","title":"GBG++: A Fast and Stable Granular Ball Generation Method for Classification","created":"2023-05-29","cited_by_count":13,"area":null},{"id":"2107.00941","title":"Misinformation Detection on YouTube Using Video Captions","created":"2021-07-02","cited_by_count":12,"area":null},{"id":"2312.15033","title":"Sparsity-Guided Holistic Explanation for LLMs with Interpretable Inference-Time Intervention","created":"2023-12-22","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":"2203.04049","title":"Graph Attention Transformer Network for Multi-Label Image Classification","created":"2022-03-08","cited_by_count":11,"area":null},{"id":"2402.03485","title":"Attention Meets Post-hoc Interpretability: A Mathematical Perspective","created":"2024-02-05","cited_by_count":11,"area":null},{"id":"2105.04708","title":"Word-level Human Interpretable Scoring Mechanism for Novel Text Detection Using Tsetlin Machines","created":"2021-05-10","cited_by_count":10,"area":null},{"id":"2207.04132","title":"Cross-Attention Transformer for Video Interpolation","created":"2022-07-08","cited_by_count":10,"area":null},{"id":"2304.11744","title":"SketchXAI: A First Look at Explainability for Human Sketches","created":"2023-04-23","cited_by_count":10,"area":null},{"id":"2112.05909","title":"Neural Attention Models in Deep Learning: Survey and Taxonomy","created":"2021-12-11","cited_by_count":8,"area":null},{"id":"2309.15467","title":"Enabling Resource-efficient AIoT System with Cross-level Optimization: A survey","created":"2023-09-27","cited_by_count":8,"area":null},{"id":"2302.02744","title":"AMD-HookNet for Glacier Front Segmentation","created":"2023-02-06","cited_by_count":7,"area":null},{"id":"2304.02911","title":"Heavy-Tailed Regularization of Weight Matrices in Deep Neural Networks","created":"2023-04-06","cited_by_count":7,"area":null},{"id":"2102.10788","title":"Attention Models for Point Clouds in Deep Learning: A Survey","created":"2021-02-22","cited_by_count":6,"area":null},{"id":"2102.12227","title":"Multi-Task Attentive Residual Networks for Argument Mining","created":"2021-02-24","cited_by_count":6,"area":null},{"id":"2104.03046","title":"Multimodal Continuous Visual Attention Mechanisms","created":"2021-04-07","cited_by_count":6,"area":null},{"id":"2506.13060","title":"Rethinking Explainability in the Era of Multimodal AI","created":"2025-06-16","cited_by_count":6,"area":null},{"id":"2102.07259","title":"Thank you for Attention: A survey on Attention-based Artificial Neural Networks for Automatic Speech Recognition","created":"2021-02-14","cited_by_count":5,"area":null},{"id":"2205.02596","title":"Natural Language Inference with Self-Attention for Veracity Assessment of Pandemic Claims","created":"2022-05-05","cited_by_count":5,"area":null},{"id":"2211.14591","title":"A Survey of Text Representation Methods and Their Genealogy","created":"2022-11-26","cited_by_count":5,"area":null},{"id":"2405.15310","title":"Spectraformer: A Unified Random Feature Framework for Transformer","created":"2024-05-24","cited_by_count":5,"area":null},{"id":"2406.06366","title":"Symmetric Dot-Product Attention for Efficient Training of BERT Language Models","created":"2024-06-10","cited_by_count":5,"area":null},{"id":"2112.10609","title":"An ensemble deep learning technique for detecting suicidal ideation from posts in social media platforms","created":"2021-12-17","cited_by_count":4,"area":null},{"id":"2207.08412","title":"Multi-branch Cascaded Swin Transformers with Attention to k-space Sampling Pattern for Accelerated MRI Reconstruction","created":"2022-07-18","cited_by_count":4,"area":null},{"id":"2310.07882","title":"The Thousand Faces of Explainable AI Along the Machine Learning Life Cycle: Industrial Reality and Current State of Research","created":"2023-10-11","cited_by_count":4,"area":null},{"id":"2412.00359","title":"Does Self-Attention Need Separate Weights in Transformers?","created":"2024-11-30","cited_by_count":4,"area":null},{"id":"2505.19956","title":"DCG-SQL: Enhancing In-Context Learning for Text-to-SQL with Deep Contextual Schema Link Graph","created":"2025-05-26","cited_by_count":4,"area":null},{"id":"2107.12079","title":"An Argumentative Dialogue System for COVID-19 Vaccine Information","created":"2021-07-26","cited_by_count":3,"area":null},{"id":"2111.00316","title":"Real-time Speaker counting in a cocktail party scenario using Attention-guided Convolutional Neural Network","created":"2021-10-30","cited_by_count":3,"area":null},{"id":"2201.01869","title":"Earthquake Nowcasting with Deep Learning","created":"2021-12-18","cited_by_count":3,"area":null},{"id":"2201.06390","title":"SwinUNet3D -- A Hierarchical Architecture for Deep Traffic Prediction using Shifted Window Transformers","created":"2022-01-17","cited_by_count":3,"area":null},{"id":"2204.04518","title":"Attention U-Net as a surrogate model for groundwater prediction","created":"2022-04-09","cited_by_count":3,"area":null},{"id":"2204.07390","title":"Email Spam Detection Using Hierarchical Attention Hybrid Deep Learning Method","created":"2022-04-15","cited_by_count":3,"area":null},{"id":"2301.13014","title":"Attribute-Guided Multi-Level Attention Network for Fine-Grained Fashion Retrieval","created":"2022-12-27","cited_by_count":3,"area":null},{"id":"2501.14985","title":"DepressionX: Knowledge Infused Residual Attention for Explainable Depression Severity Assessment","created":"2025-01-24","cited_by_count":3,"area":null},{"id":"2510.20084","title":"ShapeX: Shapelet-Driven Post Hoc Explanations for Time Series Classification Models","created":"2025-10-23","cited_by_count":3,"area":null},{"id":"2110.00124","title":"Tree-Constrained Graph Neural Networks For Argument Mining","created":"2021-09-02","cited_by_count":2,"area":null},{"id":"2112.04008","title":"Multinational Address Parsing: A Zero-Shot Evaluation","created":"2021-12-07","cited_by_count":2,"area":null},{"id":"2410.18541","title":"On Explaining with Attention Matrices","created":"2024-10-24","cited_by_count":2,"area":null},{"id":"2504.20980","title":"Jekyll-and-Hyde Tipping Point in an AI's Behavior","created":"2025-04-29","cited_by_count":2,"area":null},{"id":"2110.00125","title":"Combining Transformers with Natural Language Explanations","created":"2021-09-02","cited_by_count":1,"area":null},{"id":"2205.01639","title":"Dynamic and Context-Dependent Stock Price Prediction Using Attention Modules and News Sentiment","created":"2022-03-13","cited_by_count":1,"area":null},{"id":"2205.06801","title":"Twitter-Based Gender Recognition Using Transformers","created":"2022-04-24","cited_by_count":1,"area":null},{"id":"2212.14150","title":"A Dynamics Theory of Implicit Regularization in Deep Low-Rank Matrix Factorization","created":"2022-12-29","cited_by_count":1,"area":null},{"id":"2309.02206","title":"Language Models for Novelty Detection in System Call Traces","created":"2023-09-05","cited_by_count":1,"area":null},{"id":"2410.03805","title":"Local Attention Mechanism: Boosting the Transformer Architecture for Long-Sequence Time Series Forecasting","created":"2024-10-04","cited_by_count":1,"area":null},{"id":"2410.13247","title":"Collaborative AI in Sentiment Analysis: System Architecture, Data Prediction and Deployment Strategies","created":"2024-10-17","cited_by_count":1,"area":null},{"id":"2509.18010","title":"Cross-Attention is Half Explanation in Speech-to-Text Models","created":"2025-09-22","cited_by_count":1,"area":null},{"id":"2602.20461","title":"Nonparametric Teaching of Attention Learners","created":"2026-02-24","cited_by_count":1,"area":null},{"id":"2108.08077","title":"Towards Interpreting Zoonotic Potential of Betacoronavirus Sequences With Attention","created":"2021-08-18","cited_by_count":0,"area":null},{"id":"2201.02816","title":"Clustering Text Using Attention","created":"2022-01-08","cited_by_count":0,"area":null},{"id":"2202.08960","title":"Toward a traceable, explainable, and fairJD/Resume recommendation system","created":"2022-02-02","cited_by_count":0,"area":null},{"id":"2205.04322","title":"ISA-bEL: Intelligent Search Algorithm based on Entity Linking","created":"2022-05-09","cited_by_count":0,"area":null},{"id":"2209.01332","title":"Class-Specific Channel Attention for Few-Shot Learning","created":"2022-09-03","cited_by_count":0,"area":null},{"id":"2210.11711","title":"Modelling Multi-relations for Convolutional-based Knowledge Graph Embedding","created":"2022-10-21","cited_by_count":0,"area":null},{"id":"2301.08949","title":"Estimation of Sea State Parameters from Ship Motion Responses Using Attention-based Neural Networks","created":"2023-01-21","cited_by_count":0,"area":null},{"id":"2308.10822","title":"A Novel Ehanced Move Recognition Algorithm Based on Pre-trained Models with Positional Embeddings","created":"2023-08-14","cited_by_count":0,"area":null},{"id":"2401.16808","title":"Encoding Temporal Statistical-space Priors via Augmented Representation","created":"2024-01-30","cited_by_count":0,"area":null},{"id":"2404.08935","title":"Developing An Attention-Based Ensemble Learning Framework for Financial Portfolio Optimisation","created":"2024-04-13","cited_by_count":0,"area":null},{"id":"2405.01216","title":"DMON: A Simple yet Effective Approach for Argument Structure Learning","created":"2024-05-02","cited_by_count":0,"area":null},{"id":"2407.00501","title":"Aeroengine performance prediction using a physical-embedded data-driven method","created":"2024-06-29","cited_by_count":0,"area":null},{"id":"2411.05876","title":"Trends, Challenges, and Future Directions in Deep Learning for Glaucoma: A Systematic Review","created":"2024-11-07","cited_by_count":0,"area":null},{"id":"2504.13974","title":"Enhancing Stroke Diagnosis in the Brain Using a Weighted Deep Learning Approach","created":"2025-04-17","cited_by_count":0,"area":null},{"id":"2504.18988","title":"LINC: Supporting Language Independent Communication and Comprehension to Enhance Contribution in Multilingual Collaborative Meetings","created":"2025-04-26","cited_by_count":0,"area":null},{"id":"2508.01932","title":"Proactive Disentangled Modeling of Trigger-Object Pairings for Backdoor Defense","created":"2025-08-03","cited_by_count":0,"area":null},{"id":"2510.00706","title":"AttentionDep: Domain-Aware Attention for Explainable Depression Severity Assessment","created":"2025-10-01","cited_by_count":0,"area":null},{"id":"2604.23615","title":"Applications of the Transformer Architecture in AI-Assisted English Reading Comprehension","created":"2026-04-26","cited_by_count":0,"area":null},{"id":"2604.25740","title":"QAROO: AI-Driven Online Task Offloading for Energy-Efficient and Sustainable MEC Networks","created":"2026-04-28","cited_by_count":0,"area":null},{"id":"2607.11353","title":"Characterising AI Models for Cataloguing","created":"2026-07-13","cited_by_count":0,"area":null},{"id":"2610.13261","title":"Data-Adaptive Mahalanobis Metric Learning for Cross-Head Attention in Transformers","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}