Xiaofen Xing

MNV-17: A High-Quality Performative Mandarin Dataset for Nonverbal Vocalization Recognition in Speech

Jialong Mai, Jinxin Ji, Xiaofen Xing, Yang Chen et autres

Mainstream Automatic Speech Recognition (ASR) systems excel at transcribing lexical content, but largely fail to recognize nonverbal vocalizations (NVs) embedded in speech, such as sighs, laughs, and coughs. This capability is important for a comprehensive understanding of human communication, as NVs convey …

cn, hk (code pays fourni par la source)

HD-PPT: Hierarchical Decoding of Content- and Prompt-Preference Tokens for Instruction-Based TTS

Sihang Nie, Xiaofen Xing, Jing Xing, Baiji Liu et autres

Large Language Model (LLM)-based Text-to-Speech (TTS) models have already reached a high degree of naturalness. However, the precision control of TTS inference is still challenging. Although instruction-based Text-to-Speech (Instruct-TTS) models are proposed, these models still lack fine-grained control due to the modality …

cn (code pays fourni par la source)

Random graph construction-based hierarchical attention multi-task graph convolution network for sEEG SOZ identification

Huachao Yan, Kailing Guo, Shiwei Song, Xiaofen Xing et autres

cn (code pays fourni par la source)

Profile-aided distillation framework for personalized sleep analysis with compact models using LLM-guided synthetic data

Huimin Zheng, Xiaoqi Ai, Xueyan Liu, Xiaofen Xing et autres

Introduction: Enabling personalized sleep analysis and interaction directly on edge devices is crucial for providing real-time health insights and tailored guidance. However, this goal remains challenging due to the scarcity of high-quality physiological data and the computational constraints of edge hardware. Methods: …

cn (code pays fourni par la source)

Momoka-RAG: MCTS-Organized Mapping of Knowledge Associations for Long-Document Retrieval Augmented Generation

Wenyu Tao, Xiaofen Xing, Zeliang Li, Xiangmin Xu

A Non-Contact Capacitive ECG Smart Mattress System Using Sensor Arrays and Adaptive Switching Strategy for Unconstrained In-Bed Sleep

Baoliang Feng, Lin Shu, Xiaofen Xing, Jun Guo et autres

cn (code pays fourni par la source)

PulseDiff: Controllable rPPG Modulation in Facial Videos via Physiology-Guided Diffusion

Ziyi Zhao, Kailing Guo, Lin Wang, Fang Liu et autres

cn (code pays fourni par la source)

Enhanced PPG-based stress recognition: a transfer learning approach to internal vs. external stress

Guodong Liang, Han Chen, Xiaofen Xing, Lan Zhang et autres

Abstract Objective. To develop a comprehensive physiological dataset for assessing internal and external stress and to propose robust automated stress recognition methods based on photoplethysmographic (PPG) signals. Approach. We established the Internal and External Stress Dataset (IESD), comprising PPG signals from 107 …

cn (code pays fourni par la source)

SemGesture: Synthesizing Semantically Enhanced and Coherent Gestures

P. L. Liu, Zhaojie Chu, Xiaofen Xing, Xiangmin Xu

Co-speech gestures are generally categorized into rhythmic and semantic gestures: rhythmic gestures align with speech rhythm and intonation, while semantic gestures convey specific meanings or emotions, enriching verbal communication. Most previous studies have focused on synthesizing rhythmic gestures, while recent methods have …

cn (code pays fourni par la source)

From Flat to Round: Redefining Brain Decoding with Surface-Based fMRI and Cortex Structure

Sijin Yu, Zijiao Chen, Wenliang Wu, Shengxian Chen et autres

Reconstructing visual stimuli from human brain activity (e.g., fMRI) bridges neuroscience and computer vision by decoding neural representations. However, existing methods often overlook critical brain structure-function relationships, flattening spatial information and neglecting individual anatomical variations. To address these issues, we propose (1) …

cn, us (code pays fourni par la source)

VolumeSwap: Volumetric Decomposed 3D‐Aware Face Swapping

Yuyuan Chen, Cheng Xu, Xuemiao Xu, Xiaofen Xing et autres

Abstract 3D face swapping has been widely applied in entertainment, gaming and privacy protection. Traditional methods often interpolate directly in the latent space to generate a global swapped code, followed by per‐image latent code optimisation. While these approaches achieve 3D consistency, they …

hk, cn, sg (code pays fourni par la source)

Patch-as-Decodable-Token: Towards Unified Multi-Modal Vision Tasks in MLLMs

Yongyi Su, Haojie Zhang, Shijie Li, Nanqing Liu et autres

Multimodal large language models (MLLMs) have advanced rapidly in recent years. However, existing approaches for vision tasks often rely on indirect representations, such as generating coordinates as text for detection, which limits performance and prevents dense prediction tasks like segmentation. To overcome …