{"total":105,"rows":[{"id":"2405.00233","title":"SemantiCodec: An Ultra Low Bitrate Semantic Audio Codec for General Sound","created":"2024-04-30","cited_by_count":45,"area":null},{"id":"2303.08536","title":"Watch or Listen: Robust Audio-Visual Speech Recognition with Visual Corruption Modeling and Reliability Scoring","created":"2023-03-15","cited_by_count":42,"area":null},{"id":"2202.12165","title":"Transformers in Medical Image Analysis: A Review","created":"2022-02-24","cited_by_count":41,"area":null},{"id":"2202.07141","title":"Machine Learning in Aerodynamic Shape Optimization","created":"2022-02-15","cited_by_count":39,"area":null},{"id":"2311.15977","title":"Text2Loc: 3D Point Cloud Localization from Natural Language","created":"2023-11-27","cited_by_count":35,"area":null},{"id":"2208.10364","title":"Scaling Up Dynamic Graph Representation Learning via Spiking Neural Networks","created":"2022-08-15","cited_by_count":24,"area":null},{"id":"2109.14320","title":"Google Neural Network Models for Edge Devices: Analyzing and Mitigating Machine Learning Inference Bottlenecks","created":"2021-09-29","cited_by_count":23,"area":null},{"id":"2210.15359","title":"Exploiting modality-invariant feature for robust multimodal emotion recognition with missing modalities","created":"2022-10-27","cited_by_count":16,"area":null},{"id":"2203.13032","title":"Multi-modal Emotion Estimation for in-the-wild Videos","created":"2022-03-24","cited_by_count":15,"area":null},{"id":"2306.04948","title":"ShuttleSet: A Human-Annotated Stroke-Level Singles Dataset for Badminton Tactical Analysis","created":"2023-06-08","cited_by_count":15,"area":null},{"id":"2407.02751","title":"Emotion and Intent Joint Understanding in Multimodal Conversation: A Benchmarking Dataset","created":"2024-07-03","cited_by_count":15,"area":null},{"id":"2407.05645","title":"OneDiff: A Generalist Model for Image Difference Captioning","created":"2024-07-08","cited_by_count":15,"area":null},{"id":"2211.02612","title":"Reservoir Computing via Quantum Recurrent Neural Networks","created":"2022-11-04","cited_by_count":14,"area":null},{"id":"2103.16910","title":"Trusted Artificial Intelligence: Towards Certification of Machine Learning Applications","created":"2021-03-31","cited_by_count":13,"area":null},{"id":"2207.00378","title":"Rapid training of quantum recurrent neural networks","created":"2022-07-01","cited_by_count":13,"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":"2104.02219","title":"Understanding Medical Conversations: Rich Transcription, Confidence Scores & Information Extraction","created":"2021-04-06","cited_by_count":10,"area":null},{"id":"2206.09457","title":"All you need is feedback: Communication with block attention feedback codes","created":"2022-06-19","cited_by_count":10,"area":null},{"id":"2207.09373","title":"Multi-Task Learning Framework for Emotion Recognition in-the-wild","created":"2022-07-19","cited_by_count":10,"area":null},{"id":"2211.12217","title":"Where Will Players Move Next? Dynamic Graphs and Hierarchical Fusion for Movement Forecasting in Badminton","created":"2022-11-22","cited_by_count":10,"area":null},{"id":"2206.03318","title":"LegoNN: Building Modular Encoder-Decoder Models","created":"2022-06-07","cited_by_count":9,"area":null},{"id":"2503.01513","title":"Evaluation and Facilitation of Online Discussions in the LLM Era: A Survey","created":"2025-03-03","cited_by_count":9,"area":null},{"id":"2211.10043","title":"Vision Transformers in Medical Imaging: A Review","created":"2022-11-18","cited_by_count":8,"area":null},{"id":"2403.13858","title":"A conditional latent autoregressive recurrent model for generation and forecasting of beam dynamics in particle accelerators","created":"2024-03-19","cited_by_count":8,"area":null},{"id":"2404.07941","title":"SiGNN: A Spike-induced Graph Neural Network for Dynamic Graph Representation Learning","created":"2024-03-11","cited_by_count":8,"area":null},{"id":"2503.20212","title":"Dolphin: A Large-Scale Automatic Speech Recognition Model for Eastern Languages","created":"2025-03-26","cited_by_count":8,"area":null},{"id":"2103.00768","title":"Mitigating Edge Machine Learning Inference Bottlenecks: An Empirical Study on Accelerating Google Edge Models","created":"2021-03-01","cited_by_count":7,"area":null},{"id":"2109.12094","title":"A spatiotemporal machine learning approach to forecasting COVID-19 incidence at the county level in the USA","created":"2021-09-24","cited_by_count":7,"area":null},{"id":"2205.00222","title":"StorSeismic: A new paradigm in deep learning for seismic processing","created":"2022-04-30","cited_by_count":7,"area":null},{"id":"2305.05738","title":"DOCTOR: A Multi-Disease Detection Continual Learning Framework Based on Wearable Medical Sensors","created":"2023-05-09","cited_by_count":7,"area":null},{"id":"2201.08017","title":"Fine-Grained Trajectory-based Travel Time Estimation for Multi-city Scenarios Based on Deep Meta-Learning","created":"2022-01-20","cited_by_count":6,"area":null},{"id":"2306.13307","title":"Towards Effective and Compact Contextual Representation for Conformer Transducer Speech Recognition Systems","created":"2023-06-23","cited_by_count":6,"area":null},{"id":"2104.02125","title":"SpeakerStew: Scaling to Many Languages with a Triaged Multilingual Text-Dependent and Text-Independent Speaker Verification System","created":"2021-04-05","cited_by_count":5,"area":null},{"id":"2201.04207","title":"Fighting Money Laundering with Statistics and Machine Learning","created":"2022-01-11","cited_by_count":5,"area":null},{"id":"2310.14982","title":"Delayed Memory Unit: Modelling Temporal Dependency Through Delay Gate","created":"2023-10-23","cited_by_count":5,"area":null},{"id":"2206.11596","title":"Two-pass Decoding and Cross-adaptation Based System Combination of End-to-end Conformer and Hybrid TDNN ASR Systems","created":"2022-06-23","cited_by_count":4,"area":null},{"id":"2211.01730","title":"Feedback is Good, Active Feedback is Better: Block Attention Active Feedback Codes","created":"2022-11-03","cited_by_count":4,"area":null},{"id":"2302.11082","title":"BB-GCN: A Bi-modal Bridged Graph Convolutional Network for Multi-label Chest X-Ray Recognition","created":"2023-02-22","cited_by_count":4,"area":null},{"id":"2505.22427","title":"RC-AutoCalib: An End-to-End Radar-Camera Automatic Calibration Network","created":"2025-05-28","cited_by_count":4,"area":null},{"id":"2510.10534","title":"MCE: Towards a General Framework for Handling Missing Modalities under Imbalanced Missing Rates","created":"2025-10-12","cited_by_count":4,"area":null},{"id":"2108.08723","title":"Feature-weighted Stacking for Nonseasonal Time Series Forecasts: A Case Study of the COVID-19 Epidemic Curves","created":"2021-08-19","cited_by_count":3,"area":null},{"id":"2301.09007","title":"MultiNet with Transformers: A Model for Cancer Diagnosis Using Images","created":"2023-01-21","cited_by_count":3,"area":null},{"id":"2303.10033","title":"Multi-modal Expression Recognition with Ensemble Method","created":"2023-03-17","cited_by_count":3,"area":null},{"id":"2306.06819","title":"Multimodal Audio-textual Architecture for Robust Spoken Language Understanding","created":"2023-06-12","cited_by_count":3,"area":null},{"id":"2406.06594","title":"Stock Movement Prediction with Multimodal Stable Fusion via Gated Cross-Attention Mechanism","created":"2024-06-06","cited_by_count":3,"area":null},{"id":"2507.23111","title":"Scalable Generative Modeling of Weighted Graphs","created":"2025-07-30","cited_by_count":3,"area":null},{"id":"2110.03326","title":"Back from the future: bidirectional CTC decoding using future information in speech recognition","created":"2021-10-07","cited_by_count":2,"area":null},{"id":"2207.12850","title":"SSIVD-Net: A Novel Salient Super Image Classification & Detection Technique for Weaponized Violence","created":"2022-07-26","cited_by_count":2,"area":null},{"id":"2211.00968","title":"Internal Language Model Estimation based Adaptive Language Model Fusion for Domain Adaptation","created":"2022-11-02","cited_by_count":2,"area":null},{"id":"2306.14108","title":"SpikeCodec: An End-to-end Learned Compression Framework for Spiking Camera","created":"2023-06-25","cited_by_count":2,"area":null},{"id":"2308.12478","title":"Attention-Based Acoustic Feature Fusion Network for Depression Detection","created":"2023-08-24","cited_by_count":2,"area":null},{"id":"2309.13135","title":"Global Deep Forecasting with Patient-Specific Pharmacokinetics","created":"2023-09-22","cited_by_count":2,"area":null},{"id":"2310.12209","title":"Fast Parameter Inference on Pulsar Timing Arrays with Normalizing Flows","created":"2023-10-18","cited_by_count":2,"area":null},{"id":"2405.04865","title":"Regime Learning for Differentiable Particle Filters","created":"2024-05-08","cited_by_count":2,"area":null},{"id":"2508.03785","title":"SoilNet: A Multimodal Multitask Model for Hierarchical Classification of Soil Horizons","created":"2025-08-05","cited_by_count":2,"area":null},{"id":"2107.06057","title":"Fast-Slow Streamflow Model Using Mass-Conserving LSTM","created":"2021-07-13","cited_by_count":1,"area":null},{"id":"2205.14664","title":"Heterogeneous Data-Centric Architectures for Modern Data-Intensive Applications: Case Studies in Machine Learning and Databases","created":"2022-05-29","cited_by_count":1,"area":null},{"id":"2302.12856","title":"Machine Learning based prediction of Glucose Levels in Type 1 Diabetes Patients with the use of Continuous Glucose Monitoring Data","created":"2023-02-24","cited_by_count":1,"area":null},{"id":"2303.11020","title":"DS-TDNN: Dual-stream Time-delay Neural Network with Global-aware Filter for Speaker Verification","created":"2023-03-20","cited_by_count":1,"area":null},{"id":"2308.08799","title":"Capturing Popularity Trends: A Simplistic Non-Personalized Approach for Enhanced Item Recommendation","created":"2023-08-17","cited_by_count":1,"area":null},{"id":"2401.05373","title":"Dynamic Spiking Framework for Graph Neural Networks","created":"2023-12-15","cited_by_count":1,"area":null},{"id":"2404.02088","title":"LastResort at SemEval-2024 Task 3: Exploring Multimodal Emotion Cause Pair Extraction as Sequence Labelling Task","created":"2024-04-02","cited_by_count":1,"area":null},{"id":"2404.16206","title":"Knowledge Graph Completion using Structural and Textual Embeddings","created":"2024-04-24","cited_by_count":1,"area":null},{"id":"2406.02604","title":"Gated recurrent neural network with TPE Bayesian optimization for enhancing stock index prediction accuracy","created":"2024-06-02","cited_by_count":1,"area":null},{"id":"2406.05564","title":"Automata Extraction from Transformers","created":"2024-06-08","cited_by_count":1,"area":null},{"id":"2406.09443","title":"Comparative Analysis of Personalized Voice Activity Detection Systems: Assessing Real-World Effectiveness","created":"2024-06-12","cited_by_count":1,"area":null},{"id":"2409.13698","title":"Lightweight Transducer Based on Frame-Level Criterion","created":"2024-09-05","cited_by_count":1,"area":null},{"id":"2410.08934","title":"Understanding the Statistical Accuracy-Communication Trade-off in Personalized Federated Learning with Minimax Guarantees","created":"2024-10-11","cited_by_count":1,"area":null},{"id":"2411.11344","title":"Mitigating Knowledge Conflicts in Language Model-Driven Question Answering","created":"2024-11-18","cited_by_count":1,"area":null},{"id":"2501.09309","title":"Understanding Mental Health Content on Social Media and Its Effect Towards Suicidal Ideation","created":"2025-01-16","cited_by_count":1,"area":null},{"id":"2507.13977","title":"Open Automatic Speech Recognition Models for Classical and Modern Standard Arabic","created":"2025-07-18","cited_by_count":1,"area":null},{"id":"2509.25905","title":"User-Centric Communication Service Provision for Edge-Assisted Mobile Augmented Reality","created":"2025-09-30","cited_by_count":1,"area":null},{"id":"2510.11233","title":"CNSocialDepress: A Chinese Social Media Dataset for Depression Risk Detection and Structured Analysis","created":"2025-10-13","cited_by_count":1,"area":null},{"id":"2604.08661","title":"Geometry-Induced Long-Range Correlations in Recurrent Neural Network Quantum States","created":"2026-04-09","cited_by_count":1,"area":null},{"id":"2103.02578","title":"Scalable Learning With a Structural Recurrent Neural Network for Short-Term Traffic Prediction","created":"2021-03-03","cited_by_count":0,"area":null},{"id":"2104.12269","title":"A Bi-Encoder LSTM Model For Learning Unstructured Dialogs","created":"2021-04-25","cited_by_count":0,"area":null},{"id":"2112.01166","title":"Forex Trading Volatility Prediction using Neural Network Models","created":"2021-12-02","cited_by_count":0,"area":null},{"id":"2112.11444","title":"ESAN: Efficient Sentiment Analysis Network of A-Shares Research Reports for Stock Price Prediction","created":"2021-12-03","cited_by_count":0,"area":null},{"id":"2112.12078","title":"Deeper Learning with CoLU Activation","created":"2021-12-18","cited_by_count":0,"area":null},{"id":"2201.12178","title":"Compositionality-Aware Graph2Seq Learning","created":"2022-01-28","cited_by_count":0,"area":null},{"id":"2208.12025","title":"Integrating Statistical and Machine Learning Approaches to Identify Receptive Field Structure in Neural Populations","created":"2022-07-25","cited_by_count":0,"area":null},{"id":"2209.03727","title":"Developing a multi-variate prediction model for the detection of COVID-19 from Crowd-sourced Respiratory Voice Data","created":"2022-09-08","cited_by_count":0,"area":null},{"id":"2211.01091","title":"I4U System Description for NIST SRE'20 CTS Challenge","created":"2022-11-02","cited_by_count":0,"area":null},{"id":"2211.03878","title":"EEG-Fest: Few-shot based Attention Network for Driver's Vigilance Estimation with EEG Signals","created":"2022-11-07","cited_by_count":0,"area":null},{"id":"2211.12084","title":"Accelerated Solutions of Coupled Phase-Field Problems using Generative Adversarial Networks","created":"2022-11-22","cited_by_count":0,"area":null},{"id":"2211.16978","title":"Combining Neuro-Evolution of Augmenting Topologies with Convolutional Neural Networks","created":"2022-10-20","cited_by_count":0,"area":null},{"id":"2303.00311","title":"Modeling Multiple User Interests using Hierarchical Knowledge for Conversational Recommender System","created":"2023-03-01","cited_by_count":0,"area":null},{"id":"2308.08578","title":"PEvoLM: Protein Sequence Evolutionary Information Language Model","created":"2023-08-16","cited_by_count":0,"area":null},{"id":"2309.16686","title":"ecoBLE: A Low-Computation Energy Consumption Prediction Framework for Bluetooth Low Energy","created":"2023-08-02","cited_by_count":0,"area":null},{"id":"2402.15923","title":"Predicting Outcomes in Video Games with Long Short Term Memory Networks","created":"2024-02-24","cited_by_count":0,"area":null},{"id":"2406.12150","title":"CHAOSMINING: Benchmarking Post-Hoc Attribution with Sparse Informative Features in High Dimensions","created":"2024-06-17","cited_by_count":0,"area":null},{"id":"2408.12636","title":"Wave-LSTM: Multi-scale analysis of somatic whole genome copy number profiles","created":"2024-08-22","cited_by_count":0,"area":null},{"id":"2409.05330","title":"KAN-Based Fusion of Dual-Domain for Audio-Driven Facial Landmarks Generation","created":"2024-09-09","cited_by_count":0,"area":null},{"id":"2410.03385","title":"From Epilepsy Seizures Classification to Detection: A Deep Learning-based Approach for Raw EEG Signals","created":"2024-10-04","cited_by_count":0,"area":null},{"id":"2410.03511","title":"Authentication by Location Tracking in Underwater Acoustic Networks","created":"2024-10-04","cited_by_count":0,"area":null},{"id":"2410.08243","title":"Self-Attention Mechanism in Multimodal Context for Banking Transaction Flow","created":"2024-10-10","cited_by_count":0,"area":null},{"id":"2502.21279","title":"L-Lipschitz Gershgorin ResNet Network","created":"2025-02-28","cited_by_count":0,"area":null},{"id":"2505.03955","title":"Hierarchical Forecast Reconciliation on Networks: A Network Flow Optimization Formulation","created":"2025-05-06","cited_by_count":0,"area":null},{"id":"2508.03420","title":"Variety Is the Spice of Life: Detecting Misinformation with Dynamic Environmental Representations","created":"2025-08-05","cited_by_count":0,"area":null},{"id":"2509.12514","title":"A comparison of pipelines for the translation of a low resource language based on transformers","created":"2025-09-15","cited_by_count":0,"area":null}],"next_cursor":"100"}