Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Improved Pedestrian Attribute Recognition Algorithm Based on Image Style TransferiFlytek · Journal of big data and computing.Jun 1, 2025Alleviating One-to-Many Mapping in Talking Head Synthesis With Dynamic Adaptation Context and Style AdapteriFlytek · IEEE Transactions on Circuits and Systems for Video Technology1 citationMay 29, 2025ConvTimeNet: A Deep Hierarchical Fully Convolutional Model for Multivariate Time Series AnalysisiFlytek · International World Wide Web Conference (WWW)45 citationsMay 8, 2025Robust Lipreading Through a Dual-Stream Adaptive Framework with Spatiotemporal LandmarkiFlytek · International Conference on Computer Engineering and Application (ICCEA)Apr 25, 2025Cross-attention among spectrum, waveform and SSL representations with bidirectional knowledge distillation for speech enhancementiFlytek · Information Fusion3 citationsApr 24, 2025PRM-BAS: Enhancing Multimodal Reasoning through PRM-guided Beam Annealing SearchiFlytek · arXiv (Cornell University)Apr 14, 2025Unlocking the Power of Patch: Patch-Based MLP for Long-Term Time Series ForecastingiFlytek · Proceedings of the AAAI Conference on Artificial Intelligence48 citationsApr 11, 2025Cross-modulated Attention Transformer for RGBT TrackingiFlytek · Proceedings of the AAAI Conference on Artificial Intelligence33 citationsApr 11, 2025SQLFixAgent: Towards Semantic-Accurate Text-to-SQL Parsing via Consistency-Enhanced Multi-Agent CollaborationiFlytek · Proceedings of the AAAI Conference on Artificial Intelligence17 citationsApr 11, 2025DocMamba: Efficient Document Pre-training with State Space ModeliFlytek · Proceedings of the AAAI Conference on Artificial Intelligence4 citationsApr 11, 2025Automated Creation of Reusable and Diverse Toolsets for Enhancing LLM ReasoningiFlytek · Proceedings of the AAAI Conference on Artificial Intelligence3 citationsApr 11, 2025Multi-Perspective Consolidation Enhanced Cognitive Diagnosis via Conditional Diffusion ModeliFlytek · Proceedings of the AAAI Conference on Artificial Intelligence1 citationApr 11, 2025RFL: Simplifying Chemical Structure Recognition with Ring-Free LanguageiFlytek · Proceedings of the AAAI Conference on Artificial IntelligenceApr 11, 2025HPCNet: Hybrid Pixel and Contour Network for Audio-Visual Speech Enhancement With Low-Quality VideoiFlytek · IEEE Journal of Selected Topics in Signal ProcessingApr 10, 2025Text2Bundle: Towards Personalized Query-based Bundle GenerationiFlytek · ACM Transactions on Recommender Systems1 citationMar 28, 2025Bidirectional trained tree-structured decoder for Handwritten Mathematical Expression RecognitioniFlytek · Pattern Recognition5 citationsMar 26, 2025Terminology Extraction Based on Document-Level Context and Domain AdaptationiFlytek · International Conference on Advanced Algorithms and Control Engineering (ICAACE)Mar 21, 2025Phoneme-Level Contrastive Learning for User-Defined Keyword Spotting with Flexible EnrollmentiFlytek · IEEE International Conference on Acoustics Speech and Signal Processing7 citationsMar 12, 2025MVANet: Multi-Stage Video Attention Network for Sound Event Localization and Detection with Source Distance EstimationiFlytek · IEEE International Conference on Acoustics Speech and Signal Processing7 citationsMar 12, 2025Large Language Models Are Efficient Learners as Zero-Shot Speech TranslatorsiFlytek · IEEE International Conference on Acoustics Speech and Signal Processing4 citationsMar 12, 2025Enhancing Multimodal Sentiment Analysis for Missing Modality through Self-Distillation and Unified Modality Cross-AttentioniFlytek · IEEE International Conference on Acoustics Speech and Signal Processing4 citationsMar 12, 2025Col-OLHTR: A Novel Framework for Multimodal Online Handwritten Text RecognitioniFlytek · IEEE International Conference on Acoustics Speech and Signal Processing4 citationsMar 12, 2025Efficient Fine-tuning Strategies for Enhancing Face Recognition Performance in Challenging ScenariosiFlytek · IEEE International Conference on Acoustics Speech and Signal Processing4 citationsMar 12, 2025Bridging Modality Gap with Large Speech and Language Models for End-to-End Speech-to-Text TranslationiFlytek · IEEE International Conference on Acoustics Speech and Signal Processing4 citationsMar 12, 2025Incorporating Spatial Cues in Modular Speaker Diarization for Multi-channel Multi-party MeetingsiFlytek · IEEE International Conference on Acoustics Speech and Signal Processing4 citationsMar 12, 2025