{"total":70,"rows":[{"id":"2305.19466","title":"The Impact of Positional Encoding on Length Generalization in Transformers","created":"2023-05-31","cited_by_count":327,"area":null},{"id":"2202.08516","title":"SAITS: Self-Attention-based Imputation for Time Series","created":"2022-02-17","cited_by_count":169,"area":null},{"id":"2105.11115","title":"Self-Attention Networks Can Process Bounded Hierarchical Languages","created":"2021-05-24","cited_by_count":105,"area":null},{"id":"2102.11090","title":"Position Information in Transformers: An Overview","created":"2021-02-22","cited_by_count":103,"area":null},{"id":"2203.02636","title":"Boosting Crowd Counting via Multifaceted Attention","created":"2022-03-05","cited_by_count":73,"area":null},{"id":"2203.14263","title":"A General Survey on Attention Mechanisms in Deep Learning","created":"2022-03-27","cited_by_count":64,"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":"2204.07756","title":"Visual Attention Methods in Deep Learning: An In-Depth Survey","created":"2022-04-16","cited_by_count":37,"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":"2412.18287","title":"Semi-supervised Credit Card Fraud Detection via Attribute-Driven Graph Representation","created":"2024-12-24","cited_by_count":26,"area":null},{"id":"2207.07563","title":"QSAN: A Near-term Achievable Quantum Self-Attention Network","created":"2022-07-14","cited_by_count":25,"area":null},{"id":"2105.07467","title":"Focus U-Net: A novel dual attention-gated CNN for polyp segmentation during colonoscopy","created":"2021-05-16","cited_by_count":20,"area":null},{"id":"2107.04537","title":"Modality specific U-Net variants for biomedical image segmentation: A survey","created":"2021-07-09","cited_by_count":20,"area":null},{"id":"2203.14266","title":"A Survey on Aspect-Based Sentiment Classification","created":"2022-03-27","cited_by_count":18,"area":null},{"id":"2102.12671","title":"LET: Linguistic Knowledge Enhanced Graph Transformer for Chinese Short Text Matching","created":"2021-02-25","cited_by_count":15,"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":"2412.09925","title":"Simulating Hard Attention Using Soft Attention","created":"2024-12-13","cited_by_count":15,"area":null},{"id":"2212.06933","title":"Paraphrase Identification with Deep Learning: A Review of Datasets and Methods","created":"2022-12-13","cited_by_count":13,"area":null},{"id":"2101.06514","title":"Linguistically-Enriched and Context-Aware Zero-shot Slot Filling","created":"2021-01-16","cited_by_count":12,"area":null},{"id":"2103.00819","title":"Sandglasset: A Light Multi-Granularity Self-attentive Network For Time-Domain Speech Separation","created":"2021-03-01","cited_by_count":10,"area":null},{"id":"2201.05344","title":"AWSnet: An Auto-weighted Supervision Attention Network for Myocardial Scar and Edema Segmentation in Multi-sequence Cardiac Magnetic Resonance Images","created":"2022-01-14","cited_by_count":10,"area":null},{"id":"2505.16983","title":"LLM as Effective Streaming Processor: Bridging Streaming-Batch Mismatches with Group Position Encoding","created":"2025-05-22","cited_by_count":9,"area":null},{"id":"2507.02591","title":"AuroraLong: Bringing RNNs Back to Efficient Open-Ended Video Understanding","created":"2025-07-03","cited_by_count":9,"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":"2106.14742","title":"TENT: Tensorized Encoder Transformer for Temperature Forecasting","created":"2021-06-28","cited_by_count":7,"area":null},{"id":"2302.02744","title":"AMD-HookNet for Glacier Front Segmentation","created":"2023-02-06","cited_by_count":7,"area":null},{"id":"2206.02179","title":"A Simple Meta-learning Paradigm for Zero-shot Intent Classification with Mixture Attention Mechanism","created":"2022-06-05","cited_by_count":6,"area":null},{"id":"2301.05860","title":"State of the Art and Potentialities of Graph-level Learning","created":"2023-01-14","cited_by_count":6,"area":null},{"id":"2308.05051","title":"PAT: Position-Aware Transformer for Dense Multi-Label Action Detection","created":"2023-08-09","cited_by_count":6,"area":null},{"id":"2407.15355","title":"Attention Beats Linear for Fast Implicit Neural Representation Generation","created":"2024-07-22","cited_by_count":6,"area":null},{"id":"2409.02120","title":"Machine Learning Framework for High-Resolution Air Temperature Downscaling Using LiDAR-Derived Urban Morphological Features","created":"2024-08-31","cited_by_count":6,"area":null},{"id":"2501.00659","title":"Why Are Positional Encodings Nonessential for Deep Autoregressive Transformers? Revisiting a Petroglyph","created":"2024-12-31","cited_by_count":6,"area":null},{"id":"2402.18267","title":"A Survey on Neural Question Generation: Methods, Applications, and Prospects","created":"2024-02-28","cited_by_count":5,"area":null},{"id":"2103.08971","title":"TLSAN: Time-aware Long- and Short-term Attention Network for Next-item Recommendation","created":"2021-03-16","cited_by_count":4,"area":null},{"id":"2107.06785","title":"Large-Scale News Classification using BERT Language Model: Spark NLP Approach","created":"2021-07-14","cited_by_count":3,"area":null},{"id":"2112.13082","title":"Multi-Scale Feature Fusion: Learning Better Semantic Segmentation for Road Pothole Detection","created":"2021-12-24","cited_by_count":3,"area":null},{"id":"2106.06420","title":"A Framework to Enhance Generalization of Deep Metric Learning methods using General Discriminative Feature Learning and Class Adversarial Neural Networks","created":"2021-06-11","cited_by_count":2,"area":null},{"id":"2202.03430","title":"A Topology-Attention ConvLSTM Network and Its Application to EM Images","created":"2022-02-07","cited_by_count":2,"area":null},{"id":"2205.01620","title":"Unifying the Convergences in Multilingual Neural Machine Translation","created":"2022-05-03","cited_by_count":2,"area":null},{"id":"2303.13801","title":"Toward Open-domain Slot Filling via Self-supervised Co-training","created":"2023-03-24","cited_by_count":2,"area":null},{"id":"2304.03228","title":"FedBot: Enhancing Privacy in Chatbots with Federated Learning","created":"2023-04-04","cited_by_count":2,"area":null},{"id":"2408.09075","title":"Improving Rare Word Translation With Dictionaries and Attention Masking","created":"2024-08-17","cited_by_count":2,"area":null},{"id":"2511.06818","title":"Learning to Focus: Focal Attention for Selective and Scalable Transformers","created":"2025-11-10","cited_by_count":2,"area":null},{"id":"2102.04610","title":"Joint Intent Detection and Slot Filling with Wheel-Graph Attention Networks","created":"2021-02-09","cited_by_count":1,"area":null},{"id":"2105.08213","title":"Distantly Supervised Relation Extraction via Recursive Hierarchy-Interactive Attention and Entity-Order Perception","created":"2021-05-18","cited_by_count":1,"area":null},{"id":"2110.08811","title":"Attention W-Net: Improved Skip Connections for better Representations","created":"2021-10-17","cited_by_count":1,"area":null},{"id":"2301.06057","title":"Hawk: An Industrial-strength Multi-label Document Classifier","created":"2023-01-15","cited_by_count":1,"area":null},{"id":"2307.05799","title":"3D Medical Image Segmentation based on multi-scale MPU-Net","created":"2023-07-11","cited_by_count":1,"area":null},{"id":"2309.03877","title":"Introducing \"Forecast Utterance\" for Conversational Data Science","created":"2023-09-07","cited_by_count":1,"area":null},{"id":"2412.06088","title":"A4-Unet: Deformable Multi-Scale Attention Network for Brain Tumor Segmentation","created":"2024-12-08","cited_by_count":1,"area":null},{"id":"2501.13735","title":"A Study of the Plausibility of Attention between RNN Encoders in Natural Language Inference","created":"2025-01-23","cited_by_count":1,"area":null},{"id":"2104.01290","title":"Measuring Linguistic Diversity During COVID-19","created":"2021-04-03","cited_by_count":0,"area":null},{"id":"2106.04905","title":"DGA-Net Dynamic Gaussian Attention Network for Sentence Semantic Matching","created":"2021-06-09","cited_by_count":0,"area":null},{"id":"2107.01528","title":"Incorporating Reachability Knowledge into a Multi-Spatial Graph Convolution Based Seq2Seq Model for Traffic Forecasting","created":"2021-07-04","cited_by_count":0,"area":null},{"id":"2109.03009","title":"Sequential Attention Module for Natural Language Processing","created":"2021-09-07","cited_by_count":0,"area":null},{"id":"2109.13021","title":"Attention Gate in Traffic Forecasting","created":"2021-09-27","cited_by_count":0,"area":null},{"id":"2210.04246","title":"Better Pre-Training by Reducing Representation Confusion","created":"2022-10-09","cited_by_count":0,"area":null},{"id":"2301.08209","title":"GIPA: A General Information Propagation Algorithm for Graph Learning","created":"2023-01-19","cited_by_count":0,"area":null},{"id":"2302.04625","title":"Weakly Supervised Human Skin Segmentation using Guidance Attention Mechanisms","created":"2023-02-09","cited_by_count":0,"area":null},{"id":"2305.05162","title":"Effective Medical Code Prediction via Label Internal Alignment","created":"2023-05-09","cited_by_count":0,"area":null},{"id":"2307.03212","title":"Attentive Graph Enhanced Region Representation Learning","created":"2023-07-06","cited_by_count":0,"area":null},{"id":"2310.19405","title":"Radar-Lidar Fusion for Object Detection by Designing Effective Convolution Networks","created":"2023-10-30","cited_by_count":0,"area":null},{"id":"2312.11898","title":"Short-Term Multi-Horizon Line Loss Rate Forecasting of a Distribution Network Using Attention-GCN-LSTM","created":"2023-12-19","cited_by_count":0,"area":null},{"id":"2406.06187","title":"An Effective-Efficient Approach for Dense Multi-Label Action Detection","created":"2024-06-10","cited_by_count":0,"area":null},{"id":"2407.03340","title":"A Multi-Modal Explainability Approach for Human-Aware Robots in Multi-Party Conversation","created":"2024-05-20","cited_by_count":0,"area":null},{"id":"2410.07725","title":"Towards Trustworthy Web Attack Detection: An Uncertainty-Aware Ensemble Deep Kernel Learning Model","created":"2024-10-10","cited_by_count":0,"area":null},{"id":"2501.06446","title":"Cross-Technology Interference: Detection, Avoidance, and Coexistence Mechanisms in the ISM Bands","created":"2025-01-11","cited_by_count":0,"area":null},{"id":"2505.14747","title":"LOD1 3D City Model from LiDAR: The Impact of Segmentation Accuracy on Quality of Urban 3D Modeling and Morphology Extraction","created":"2025-05-20","cited_by_count":0,"area":null},{"id":"2511.21473","title":"Hierarchical Ranking Neural Network for Long Document Readability Assessment","created":"2025-11-26","cited_by_count":0,"area":null},{"id":"2610.00257","title":"Attention Manifolds: Steering or Blocking Language Models by Editing Learned B-Spline Surfaces","created":"2026-09-24","cited_by_count":0,"area":null}],"next_cursor":null}