arXiv subjects

Juan Liu

Publications and source records attributed to Juan Liu.

At least 37 records · Page 2Linked to original sources

arXiv2025

CrossStateECG: Multi-Scale Deep Convolutional Network with Attention for Rest-Exercise ECG Biometrics

Current research in Electrocardiogram (ECG) biometrics mainly emphasizes resting-state conditions, leaving the performance decline in rest-exercise scenarios largely unresolved. This paper introduces CrossStateECG, a robust ECG-based authentication model explicitly tailored for cross-state (rest-exercise) conditions. The proposed model creatively combines multi-scale deep convolutional feature extraction with attention mechanisms to ensure strong identification across different physiological states. Experimental results on the exercise-ECGID dataset validate the effectiveness of CrossStateECG, achieving an identification accuracy of 92.50% in the Rest-to-Exercise scenario (training on resting ECG and testing on post-exercise ECG) and 94.72% in the Exercise-to-Rest scenario (training on post-exercise ECG and testing on resting ECG). Furthermore, CrossStateECG demonstrates exceptional performance across both state combinations, reaching an accuracy of 99.94% in Rest-to-Rest scenarios and 97.85% in Mixed-to-Mixed scenarios. Additional validations on the ECG-ID and MIT-BIH datasets further confirmed the generalization abilities of CrossStateECG, underscoring its potential as a practical solution for post-exercise ECG-based authentication in dynamic real-world settings.

cs.LG↗

arXiv2025

Bridging the Gap: Enhancing Gaze-Performance Link in Children with ASD through Dual-Level Visual Guidance in MR-DMT

Autism Spectrum Disorder (ASD) is marked by action imitation deficits stemming from visuomotor integration impairments, posing challenges to imitation-based learning, such as dance movement therapy in mixed reality (MR-DMT). Previous gaze-guiding interventions in ASD have mainly focused on optimizing gaze in isolation, neglecting the crucial "gaze-performance link". This study investigates enhancing this link in MR-DMT for children with ASD. Initially, we experimentally confirmed the weak link: longer gaze durations didn't translate to better performance. Then, we proposed and validated a novel dual-level visual guidance system that operates on both perceptual and transformational levels: not only directing attention to task-relevant areas but also explicitly scaffolding the translation from gaze perception to performance execution. Our results demonstrate its effectiveness in boosting the gaze-performance link, laying key foundations for more precisely tailored and effective MR-DMT interventions for ASD.

cs.HC↗

arXiv2025

AISHELL6-whisper: A Chinese Mandarin Audio-visual Whisper Speech Dataset with Speech Recognition Baselines

Whisper speech recognition is crucial not only for ensuring privacy in sensitive communications but also for providing a critical communication bridge for patients under vocal restraint and enabling discrete interaction in noise-sensitive environments. The development of Chinese mandarin audio-visual whisper speech recognition is hindered by the lack of large-scale datasets. We present AISHELL6-Whisper, a large-scale open-source audio-visual whisper speech dataset, featuring 30 hours each of whisper speech and parallel normal speech, with synchronized frontal facial videos. Moreover, we propose an audio-visual speech recognition (AVSR) baseline based on the Whisper-Flamingo framework, which integrates a parallel training strategy to align embeddings across speech types, and employs a projection layer to adapt to whisper speech's spectral properties. The model achieves a Character Error Rate (CER) of 4.13% for whisper speech and 1.11% for normal speech in the test set of our dataset, and establishes new state-of-the-art results on the wTIMIT benchmark. The dataset and the AVSR baseline codes are open-sourced at https://zutm.github.io/AISHELL6-Whisper.

eess.AS↗

arXiv2025

SE-VLN: A Self-Evolving Vision-Language Navigation Framework Based on Multimodal Large Language Models

Recent advances in vision-language navigation (VLN) were mainly attributed to emerging large language models (LLMs). These methods exhibited excellent generalization capabilities in instruction understanding and task reasoning. However, they were constrained by the fixed knowledge bases and reasoning abilities of LLMs, preventing fully incorporating experiential knowledge and thus resulting in a lack of efficient evolutionary capacity. To address this, we drew inspiration from the evolution capabilities of natural agents, and proposed a self-evolving VLN framework (SE-VLN) to endow VLN agents with the ability to continuously evolve during testing. To the best of our knowledge, it was the first time that an multimodal LLM-powered self-evolving VLN framework was proposed. Specifically, SE-VLN comprised three core modules, i.e., a hierarchical memory module to transfer successful and failure cases into reusable knowledge, a retrieval-augmented thought-based reasoning module to retrieve experience and enable multi-step decision-making, and a reflection module to realize continual evolution. Comprehensive tests illustrated that the SE-VLN achieved navigation success rates of 57% and 35.2% in unseen environments, representing absolute performance improvements of 23.9% and 15.0% over current state-of-the-art methods on R2R and REVERSE datasets, respectively. Moreover, the SE-VLN showed performance improvement with increasing experience repository, elucidating its great potential as a self-evolving agent framework for VLN.

cs.CV↗

arXiv2025

Multi-scale Scanning Network for Machine Anomalous Sound Detection

Machine sounds exhibit consistent and repetitive patterns in both the frequency and time domains, which vary significantly across scales for different machine types. For instance, rotating machines often show periodic features in short time intervals, while reciprocating machines exhibit broader patterns spanning the time domain. While prior studies have leveraged these patterns to improve Anomalous Sound Detection (ASD), the variation of patterns across scales remains insufficiently explored. To address this gap, we introduce a Multi-scale Scanning Network (MSN) designed to capture patterns at multiple scales. MSN employs kernel boxes of varying sizes to scan audio spectrograms and integrates a lightweight convolutional network with shared weights for efficient and scalable feature representation. Experimental evaluations on the DCASE 2020 and DCASE 2023 Task 2 datasets demonstrate that MSN achieves state-of-the-art performance, highlighting its effectiveness in advancing ASD systems.

cs.SD↗

arXiv2025

LLM-empowered Dynamic Prompt Routing for Vision-Language Models Tuning under Long-Tailed Distributions

Pre-trained vision-language models (VLMs), such as CLIP, have demonstrated impressive capability in visual tasks, but their fine-tuning often suffers from bias in class-imbalanced scene. Recent works have introduced large language models (LLMs) to enhance VLM fine-tuning with supplementing semantic information. However, they often overlook inherent class imbalance in VLMs' pre-training, which may lead to bias accumulation in downstream tasks. To address this problem, this paper proposes a Multi-dimensional Dynamic Prompt Routing (MDPR) framework. MDPR constructs a comprehensive knowledge base for classes, spanning five visual-semantic dimensions. During fine-tuning, the dynamic routing mechanism aligns global visual classes, retrieves optimal prompts, and balances fine-grained semantics, yielding stable predictions through logits fusion. Extensive experiments on long-tailed benchmarks, including CIFAR-LT, ImageNet-LT, and Places-LT, demonstrate that MDPR achieves comparable results with current SOTA methods. Ablation studies further confirm the effectiveness of our semantic library for tail classes, and show that our dynamic routing incurs minimal computational overhead, making MDPR a flexible and efficient enhancement for VLM fine-tuning under data imbalance.

cs.CV↗

arXiv2025

MAGNeT: Multimodal Adaptive Gaussian Networks for Intent Inference in Moving Target Selection across Complex Scenarios

Moving target selection in multimedia interactive systems faces unprecedented challenges as users increasingly interact across diverse and dynamic contexts-from live streaming in moving vehicles to VR gaming in varying environments. Existing approaches rely on probabilistic models that relate endpoint distribution to target properties such as size and speed. However, these methods require substantial training data for each new context and lack transferability across scenarios, limiting their practical deployment in diverse multimedia environments where rich multimodal contextual information is readily available. This paper introduces MAGNeT (Multimodal Adaptive Gaussian Networks), which addresses these problems by combining classical statistical modeling with a context-aware multimodal method. MAGNeT dynamically fuses pre-fitted Ternary-Gaussian models from various scenarios based on real-time contextual cues, enabling effective adaptation with minimal training data while preserving model interpretability. We conduct experiments on self-constructed 2D and 3D moving target selection datasets under in-vehicle vibration conditions. Extensive experiments demonstrate that MAGNeT achieves lower error rates with few-shot samples by applying context-aware fusion of Gaussian experts from multi-factor conditions.

cs.MM↗

arXiv2025

Multi-Channel Sequence-to-Sequence Neural Diarization: Experimental Results for The MISP 2025 Challenge

This paper describes the speaker diarization system developed for the Multimodal Information-Based Speech Processing (MISP) 2025 Challenge. First, we utilize the Sequence-to-Sequence Neural Diarization (S2SND) framework to generate initial predictions using single-channel audio. Then, we extend the original S2SND framework to create a new version, Multi-Channel Sequence-to-Sequence Neural Diarization (MC-S2SND), which refines the initial results using multi-channel audio. The final system achieves a diarization error rate (DER) of 8.09% on the evaluation set of the competition database, ranking first place in the speaker diarization task of the MISP 2025 Challenge.

eess.AS↗

arXiv2025

LOHA: Direct Graph Spectral Contrastive Learning Between Low-pass and High-pass Views

Spectral Graph Neural Networks effectively handle graphs with different homophily levels, with low-pass filter mining feature smoothness and high-pass filter capturing differences. When these distinct filters could naturally form two opposite views for self-supervised learning, the commonalities between the counterparts for the same node remain unexplored, leading to suboptimal performance. In this paper, a simple yet effective self-supervised contrastive framework, LOHA, is proposed to address this gap. LOHA optimally leverages low-pass and high-pass views by embracing "harmony in diversity". Rather than solely maximizing the difference between these distinct views, which may lead to feature separation, LOHA harmonizes the diversity by treating the propagation of graph signals from both views as a composite feature. Specifically, a novel high-dimensional feature named spectral signal trend is proposed to serve as the basis for the composite feature, which remains relatively unaffected by changing filters and focuses solely on original feature differences. LOHA achieves an average performance improvement of 2.8% over runner-up models on 9 real-world datasets with varying homophily levels. Notably, LOHA even surpasses fully-supervised models on several datasets, which underscores the potential of LOHA in advancing the efficacy of spectral GNNs for diverse graph structures.

cs.LG↗

arXiv2024

Continuous and discrete-time accelerated methods for an inequality constrained convex optimization problem

This paper is devoted to the study of acceleration methods for an inequality constrained convex optimization problem by using Lyapunov functions. We first approximate such a problem as an unconstrained optimization problem by employing the logarithmic barrier function. Using the Hamiltonian principle, we propose a continuous-time dynamical system associated with a Bregman Lagrangian for solving the unconstrained optimization problem. Under certain conditions, we demonstrate that this continuous-time dynamical system exponentially converges to the optimal solution of the inequality constrained convex optimization problem. Moreover, we derive several discrete-time algorithms from this continuous-time framework and obtain their optimal convergence rates. Finally, we present numerical experiments to validate the effectiveness of the proposed algorithms.

math.OC↗

arXiv2024

Lightweight holographic near-eye display system with self-charging capability using solar energy

Near-eye display plays an important role in emerging spatial computing systems, providing a distinctive visual effect of virtual-real fusion. However, its application for all-day wear is greatly limited by the bulky structure, energy expenditure, and continuous battery heating. Here, we propose a lightweight holographic near-eye display system that takes advantage of solar energy for self-charging. To achieve the collection of solar energy and near-eye display without crosstalk, holographic optical elements (HOE) are used to diffract sunlight and signal light into a common waveguide. Then, small-area solar cells convert the collected solar energy and power the system. Compact power supply components replace heavy batteries, contributing to the lightweight design. The simple acquisition of solar energy provides the system with sustainable self-charging capability. We believe that the lightweight design and continuous energy input solution will significantly promote the popularity of near-eye display in our daily lives.

physics.optics↗

arXiv2024

A Dual-Path Framework with Frequency-and-Time Excited Network for Anomalous Sound Detection

In contrast to human speech, machine-generated sounds of the same type often exhibit consistent frequency characteristics and discernible temporal periodicity. However, leveraging these dual attributes in anomaly detection remains relatively under-explored. In this paper, we propose an automated dual-path framework that learns prominent frequency and temporal patterns for diverse machine types. One pathway uses a novel Frequency-and-Time Excited Network (FTE-Net) to learn the salient features across frequency and time axes of the spectrogram. It incorporates a Frequency-and-Time Chunkwise Encoder (FTC-Encoder) and an excitation network. The other pathway uses a 1D convolutional network for utterance-level spectrum. Experimental results on the DCASE 2023 task 2 dataset show the state-of-the-art performance of our proposed method. Moreover, visualizations of the intermediate feature maps in the excitation network are provided to illustrate the effectiveness of our method.

eess.AS↗

arXiv2024

UAV-Enabled Wireless Networks for Integrated Sensing and Learning-Oriented Communication

Future wireless networks are envisioned to support both sensing and artificial intelligence (AI) services. However, conventional integrated sensing and communication (ISAC) networks may not be suitable due to the ignorance of diverse task-specific data utilities in different AI applications. In this letter, a full-duplex unmanned aerial vehicle (UAV)-enabled wireless network providing sensing and edge learning services is investigated. To maximize the learning performance while ensuring sensing quality, a convergence-guaranteed iterative algorithm is developed to jointly determine the uplink time allocation, as well as UAV trajectory and transmit power. Simulation results show that the proposed algorithm significantly outperforms the baselines and demonstrate the critical tradeoff between sensing and learning performance.

cs.NI↗

arXiv2024

FR-SLAM: A SLAM Improvement Method Based on Floor Plan Registration

Simultaneous Localization and Mapping (SLAM) technology enables the construction of environmental maps and localization, serving as a key technique for indoor autonomous navigation of mobile robots. Traditional SLAM methods typically require exhaustive traversal of all rooms during indoor navigation to obtain a complete map, resulting in lengthy path planning times and prolonged time to reach target points. Moreover, cumulative errors during motion lead to inaccurate robot localization, impacting navigation efficiency.This paper proposes an improved SLAM method, FR-SLAM, based on floor plan registration, utilizing a morphology-based floor plan registration algorithm to align and transform original floor plans. This approach facilitates the rapid acquisition of comprehensive motion maps and efficient path planning, enabling swift navigation to target positions within a shorter timeframe. To enhance registration and robot motion localization accuracy, a real-time update strategy is employed, comparing the current position's building structure with the map and dynamically updating floor plan registration results for precise localization. Comparative tests conducted on real and simulated datasets demonstrate that, compared to other benchmark algorithms, this method achieves higher floor plan registration accuracy and shorter time consumption to reach target positions.

cs.RO↗

arXiv2024

A new condition on dominated pair degree sum for a digraph to be supereulerian

A digraph $D$ is supereulerian if $D$ contains a spanning eulerian subdigraph. For any two vertices $u,v$ in a digraph $D$, if $(u,w),(v,w)\in A(D)$ for some $w\in V(D)$, then we call the pair $\{u, v\}$ dominating; if $(w,u),(w,v)\in A(D)$ for some $w\in V(D)$, then we call the pair $\{u, v\}$ dominated. In 2015, Bang-Jensen and Maddaloni [Journal of graph theory, 79(1) (2015) 8-20] proved that if a strong digraph $D$ with $n$ vertices satisfies $d(u) + d(v)\geq 2n -3$ for any pair of nonadjacent vertices $\{u,v\}$ of $D$, then $D$ is supereulerian. In this paper, we study the above degree sum condition for any pair of dominated or dominating nonadjacent vertices of supereulerian digraphs.

math.CO↗

arXiv2024

Antidirected hamiltonian paths in $k$-hypertournaments

A $k$-hypertournament $H$ on $n$ vertices is a pair $(V(H),A(H))$, where $V(H)$ is a set of vertices and $A(H)$ is a set of $k$-tuples of vertices, called arcs, such that for any $k$-subset $S$ of $V(H)$, $A(H)$ contains exactly one of the $k!$ $k$-tuples whose entries belong to $S$. Clearly, a 2-hypertournament is a tournament. An antidirected path in $H$ is a sequence $x_1 a_1 x_2 a_2 x_3 \ldots x_{t-1} a_{t-1} x_t$ of distinct vertices $x_1, x_2, \ldots, x_t$ and distinct arcs $a_1, a_{2},\ldots, a_{t-1}$ such that for any $i\in \{2,3,\ldots, t-1\}$, either $x_{i-1}$ precedes $x_{i}$ in $a_{i-1}$ and $x_{i+1}$ precedes $x_{i}$ in $a_{i}$, or $x_{i}$ precedes $x_{i-1}$ in $a_{i-1}$ and $x_{i}$ precedes $x_{i+1}$ in $a_{i}$. An antidirected path that includes all vertices of $H$ is known as an antidirected hamiltonian path. In this paper, we prove that except for four hypertournaments, $T_3^{c}, T_5^{c}, T_7^{c}$ and $H_{4}$, every $k$-hypertournament with $n$ vetices, where $2\leq k\leq n-1$, has an antidirected hamiltonian path, which extends Grünbaum's theorem on tournaments (except for three tournaments, $T_3^{c}, T_5^{c}$ and $T_7^{c}$, every tournament has an antidirected hamiltonian path).

math.CO↗

arXiv2024

Sufficient conditions for closed-trailable in digraphs

A digraph $D$ with a subset $S$ of $V(D)$ is called $\boldsymbol{S}${\bf -strong} if for every pair of distinct vertices $u$ and $v$ of $S$, there is a $(u, v)$-dipath and a $(v, u)$-dipath in $D$. We define a digraph $D$ with a subset $S$ of $V(D)$ to be $\boldsymbol{S}${\bf -strictly strong} if there exist two nonadjacent vertices $u,v\in S$ such that $D$ contains a closed ditrail through the vertices $u$ and $v$; and define a subset $S\subseteq V(D)$ to be {\bf closed-trailable} if $D$ contains a closed ditrail through all the vertices of $S$. In this paper, we prove that for a digraph $D$ with $n$ vertices and a subset $S$ of $V(D)$, if $D$ is $S$-strong and if $d(u) + d(v)\geq 2n -3$ for any two nonadjacent vertices $u,v$ of $S$, then $S$ is closed-trailable. This result generalizes the theorem of Bang-Jensen et al. \cite{BaMa14} on supereulerianity. Moveover, we show that for a digraph $D$ and a subset $S$ of $V(D)$, if $D$ is $S$-strictly strong and if $δ^0(D\langle S\rangle)\geqα'(D\langle S\rangle)>0$, where $δ^0(D\langle S\rangle)$ is the minimum semi-degree of $D\langle S\rangle$ and $α'(D\langle S\rangle)$ is the matching number of $D\langle S\rangle$, then $S$ is closed-trailable. This result generalizes the theorem of Algefari et al. \cite{AlLa15} on supereulerianity.

math.CO↗

arXiv2024

Perceiver-Prompt: Flexible Speaker Adaptation in Whisper for Chinese Disordered Speech Recognition

Disordered speech recognition profound implications for improving the quality of life for individuals afflicted with, for example, dysarthria. Dysarthric speech recognition encounters challenges including limited data, substantial dissimilarities between dysarthric and non-dysarthric speakers, and significant speaker variations stemming from the disorder. This paper introduces Perceiver-Prompt, a method for speaker adaptation that utilizes P-Tuning on the Whisper large-scale model. We first fine-tune Whisper using LoRA and then integrate a trainable Perceiver to generate fixed-length speaker prompts from variable-length inputs, to improve model recognition of Chinese dysarthric speech. Experimental results from our Chinese dysarthric speech dataset demonstrate consistent improvements in recognition performance with Perceiver-Prompt. Relative reduction up to 13.04% in CER is obtained over the fine-tuned Whisper.

eess.AS↗