Searcharxiv⌕ Search

arXiv subjects

Hong Liu

Publications and source records attributed to Hong Liu.

At least 163 records · Page 9Linked to original sources
arXiv2025

A Dual-Stage Time-Context Network for Speech-Based Alzheimer's Disease Detection

Alzheimer's disease (AD) is a progressive neurodegenerative disorder that leads to irreversible cognitive decline in memory and communication. Early detection of AD through speech analysis is crucial for delaying disease progression. However, existing methods mainly use pre-trained acoustic models for feature extraction but have limited ability to model both local and global patterns in long-duration speech. In this letter, we introduce a Dual-Stage Time-Context Network (DSTC-Net) for speech-based AD detection, integrating local acoustic features with global conversational context in long-duration recordings.We first partition each long-duration recording into fixed-length segments to reduce computational overhead and preserve local temporal details.Next, we feed these segments into an Intra-Segment Temporal Attention (ISTA) module, where a bidirectional Long Short-Term Memory (BiLSTM) network with frame-level attention extracts enhanced local features.Subsequently, a Cross-Segment Context Attention (CSCA) module applies convolution-based context modeling and adaptive attention to unify global patterns across all segments.Extensive experiments on the ADReSSo dataset show that our DSTC-Net outperforms state-of-the-art models, reaching 83.10% accuracy and 83.15% F1.

cs.SD↗
arXiv2025

Global-Local Distillation Network-Based Audio-Visual Speaker Tracking with Incomplete Modalities

In speaker tracking research, integrating and complementing multi-modal data is a crucial strategy for improving the accuracy and robustness of tracking systems. However, tracking with incomplete modalities remains a challenging issue due to noisy observations caused by occlusion, acoustic noise, and sensor failures. Especially when there is missing data in multiple modalities, the performance of existing multi-modal fusion methods tends to decrease. To this end, we propose a Global-Local Distillation-based Tracker (GLDTracker) for robust audio-visual speaker tracking. GLDTracker is driven by a teacher-student distillation model, enabling the flexible fusion of incomplete information from each modality. The teacher network processes global signals captured by camera and microphone arrays, and the student network handles local information subject to visual occlusion and missing audio channels. By transferring knowledge from teacher to student, the student network can better adapt to complex dynamic scenes with incomplete observations. In the student network, a global feature reconstruction module based on the generative adversarial network is constructed to reconstruct global features from feature embedding with missing local information. Furthermore, a multi-modal multi-level fusion attention is introduced to integrate the incomplete feature and the reconstructed feature, leveraging the complementarity and consistency of audio-visual and global-local features. Experimental results on the AV16.3 dataset demonstrate that the proposed GLDTracker outperforms existing state-of-the-art audio-visual trackers and achieves leading performance on both standard and incomplete modalities datasets, highlighting its superiority and robustness in complex conditions. The code and models will be available.

cs.CV↗
arXiv2025

Interpolating chromatic and homomorphism thresholds

The problem of chromatic thresholds seeks for minimum degree conditions that ensure $H$-free graphs to have a bounded chromatic number, or equivalently a bounded size homomorphic image. The strengthened homomorphism thresholds problem further requires that the homomorphic image itself is $H$-free. The purpose of this paper is two-fold. First, we define a generalized notion of threshold which encapsulates and interpolates chromatic and homomorphism thresholds via the theory of VC-dimension. Our first result shows a smooth transition between these two thresholds when varying the restrictions on homomorphic images. In particular, we proved that for $t \ge s \ge 3$ and $ε>0$, if $G$ is an $n$-vertex $K_s$-free graph with VC-dimension $d$ and $δ(G) \ge (\frac{(s-3)(t-s+2)+1}{(s-2)(t-s+2)+1} + ε)n$, then $G$ is homomorphic to a $K_t$-free graph $H$ with $|H| = O(1)$. Moreover, we construct graphs showing that this minimum degree condition is optimal. This extends and unifies the results of Thomassen, Łuczak and Thomassé, and Goddard, Lyle and Nikiforov, and provides a deeper insight into the cause of existences of homomorphic images with various properties. Second, we introduce the blowup threshold $δ_B(H)$ as the infimum $α$ such that every $n$-vertex maximal $H$-free graph $G$ with $δ(G)\geαn$ is a blowup of some $F$ with $|F|=O(1)$. This notion strengthens homomorphism threshold. While the homomorphism thresholds for odd cycles remain unknown, we prove that $δ_B(C_{2k-1})=1/(2k-1)$ for any integer $k\ge 2$. This strengthens the result of Ebsen and Schacht and answers a question of Schacht and shows that, in sharp contrast to the chromatic thresholds, 0 is an accumulation point for blowup thresholds. Our proofs mix tools from VC-dimension theory and an iterative refining process, and draw connection to a problem concerning codes on graphs.

math.CO↗
arXiv2025

Separating hypergraph Turán densities

Determining the Turán densities of hypergraphs is a notoriously difficult problem at the core of combinatorics. Although Turán posed this problem in 1941, $π(K_{\ell}^{(k)})$ remains unknown for all $\ell>k\geq 3$. Prior to this work, it was not even known whether $π(K_{\ell}^{(k)})<π(K_{\ell+1}^{(k)})$ holds for general $\ell$ and $k$, and the best-known bounds on $π(K_{\ell}^{(k)})$ are far from implying anything close to this. We prove that $π(K_{\ell}^{(k)})<π(K_{\ell+1}^{(k)})$, for all $\ell>k\geq 3$, and provide a general criterion to distinguish the Turán densities of two hypergraphs. As a corollary, we obtain that $π(K_{k+1}^{(k)})<π(K_{k+2}^{(k)-})$, for all $k\geq 3$. For $k=3$, this was previously proved by Markström, answering a question by Erdős.

math.CO↗
arXiv2025

Quantum correction to the orbital Hall effect

Evaluations of the orbital Hall effect (OHE) have only retained inter-band matrix elements of the position operator. Here we evaluate the OHE including all matrix elements of the position operator, including the technically challenging intra-band elements. We recover previous results and find quantum corrections due to the non-commutativity of the position and velocity operators and inter-band matrix elements of the orbital angular momentum. The quantum corrections dominate the OHE responses of the topological antiferromagnet CuMnAs and of massive Dirac fermions.

cond-mat.mes-hall↗
arXiv2025

Extremal density for subdivisions with length or sparsity constraints

Given a graph $H$, a balanced subdivision of $H$ is obtained by replacing all edges of $H$ with internally disjoint paths of the same length. In this paper, we prove that for any graph $H$, a linear-in-$e(H)$ bound on average degree guarantees a balanced $H$-subdivision. This strengthens an old result of Bollobás and Thomason, and resolves a question of Gil-Fernández, Hyde, Liu, Pikhurko and Wu. We observe that this linear bound on average degree is best possible whenever $H$ is logarithmically dense. We further show that this logarithmic density is the critical threshold: for many graphs $H$ below this density, its subdivisions are forcible by a sublinear-in-$e(H)$ bound on average degree. We provide such examples by proving that the subdivisions of any almost bipartite graph $H$ with sublogarithmic density are forcible by a sublinear-in-$e(H)$ bound on average degree, provided that $H$ satisfies some additional separability condition.

math.CO↗
arXiv2025

TCPFormer: Learning Temporal Correlation with Implicit Pose Proxy for 3D Human Pose Estimation

Recent multi-frame lifting methods have dominated the 3D human pose estimation. However, previous methods ignore the intricate dependence within the 2D pose sequence and learn single temporal correlation. To alleviate this limitation, we propose TCPFormer, which leverages an implicit pose proxy as an intermediate representation. Each proxy within the implicit pose proxy can build one temporal correlation therefore helping us learn more comprehensive temporal correlation of human motion. Specifically, our method consists of three key components: Proxy Update Module (PUM), Proxy Invocation Module (PIM), and Proxy Attention Module (PAM). PUM first uses pose features to update the implicit pose proxy, enabling it to store representative information from the pose sequence. PIM then invocates and integrates the pose proxy with the pose sequence to enhance the motion semantics of each pose. Finally, PAM leverages the above mapping between the pose sequence and pose proxy to enhance the temporal correlation of the whole pose sequence. Experiments on the Human3.6M and MPI-INF-3DHP datasets demonstrate that our proposed TCPFormer outperforms the previous state-of-the-art methods.

cs.CV↗
arXiv2024

B-AVIBench: Towards Evaluating the Robustness of Large Vision-Language Model on Black-box Adversarial Visual-Instructions

Large Vision-Language Models (LVLMs) have shown significant progress in responding well to visual-instructions from users. However, these instructions, encompassing images and text, are susceptible to both intentional and inadvertent attacks. Despite the critical importance of LVLMs' robustness against such threats, current research in this area remains limited. To bridge this gap, we introduce B-AVIBench, a framework designed to analyze the robustness of LVLMs when facing various Black-box Adversarial Visual-Instructions (B-AVIs), including four types of image-based B-AVIs, ten types of text-based B-AVIs, and nine types of content bias B-AVIs (such as gender, violence, cultural, and racial biases, among others). We generate 316K B-AVIs encompassing five categories of multimodal capabilities (ten tasks) and content bias. We then conduct a comprehensive evaluation involving 14 open-source LVLMs to assess their performance. B-AVIBench also serves as a convenient tool for practitioners to evaluate the robustness of LVLMs against B-AVIs. Our findings and extensive experimental results shed light on the vulnerabilities of LVLMs, and highlight that inherent biases exist even in advanced closed-source LVLMs like GeminiProVision and GPT-4V. This underscores the importance of enhancing the robustness, security, and fairness of LVLMs. The source code and benchmark are available at https://github.com/zhanghao5201/B-AVIBench.

cs.CV↗
arXiv2024

Learning Mutual Excitation for Hand-to-Hand and Human-to-Human Interaction Recognition

Recognizing interactive actions, including hand-to-hand interaction and human-to-human interaction, has attracted increasing attention for various applications in the field of video analysis and human-robot interaction. Considering the success of graph convolution in modeling topology-aware features from skeleton data, recent methods commonly operate graph convolution on separate entities and use late fusion for interactive action recognition, which can barely model the mutual semantic relationships between pairwise entities. To this end, we propose a mutual excitation graph convolutional network (me-GCN) by stacking mutual excitation graph convolution (me-GC) layers. Specifically, me-GC uses a mutual topology excitation module to firstly extract adjacency matrices from individual entities and then adaptively model the mutual constraints between them. Moreover, me-GC extends the above idea and further uses a mutual feature excitation module to extract and merge deep features from pairwise entities. Compared with graph convolution, our proposed me-GC gradually learns mutual information in each layer and each stage of graph convolution operations. Extensive experiments on a challenging hand-to-hand interaction dataset, i.e., the Assembely101 dataset, and two large-scale human-to-human interaction datasets, i.e., NTU60-Interaction and NTU120-Interaction consistently verify the superiority of our proposed method, which outperforms the state-of-the-art GCN-based and Transformer-based methods.

cs.CV↗
arXiv2024

Unlocking the Potential of Weakly Labeled Data: A Co-Evolutionary Learning Framework for Abnormality Detection and Report Generation

Anatomical abnormality detection and report generation of chest X-ray (CXR) are two essential tasks in clinical practice. The former aims at localizing and characterizing cardiopulmonary radiological findings in CXRs, while the latter summarizes the findings in a detailed report for further diagnosis and treatment. Existing methods often focused on either task separately, ignoring their correlation. This work proposes a co-evolutionary abnormality detection and report generation (CoE-DG) framework. The framework utilizes both fully labeled (with bounding box annotations and clinical reports) and weakly labeled (with reports only) data to achieve mutual promotion between the abnormality detection and report generation tasks. Specifically, we introduce a bi-directional information interaction strategy with generator-guided information propagation (GIP) and detector-guided information propagation (DIP). For semi-supervised abnormality detection, GIP takes the informative feature extracted by the generator as an auxiliary input to the detector and uses the generator's prediction to refine the detector's pseudo labels. We further propose an intra-image-modal self-adaptive non-maximum suppression module (SA-NMS). This module dynamically rectifies pseudo detection labels generated by the teacher detection model with high-confidence predictions by the student.Inversely, for report generation, DIP takes the abnormalities' categories and locations predicted by the detector as input and guidance for the generator to improve the generated reports.

cs.CV↗
arXiv2024

Neural-Network-Driven Reward Prediction as a Heuristic: Advancing Q-Learning for Mobile Robot Path Planning

Q-learning is a widely used reinforcement learning technique for solving path planning problems. It primarily involves the interaction between an agent and its environment, enabling the agent to learn an optimal strategy that maximizes cumulative rewards. Although many studies have reported the effectiveness of Q-learning, it still faces slow convergence issues in practical applications. To address this issue, we propose the NDR-QL method, which utilizes neural network outputs as heuristic information to accelerate the convergence process of Q-learning. Specifically, we improved the dual-output neural network model by introducing a start-end channel separation mechanism and enhancing the feature fusion process. After training, the proposed NDR model can output a narrowly focused optimal probability distribution, referred to as the guideline, and a broadly distributed suboptimal distribution, referred to as the region. Subsequently, based on the guideline prediction, we calculate the continuous reward function for the Q-learning method, and based on the region prediction, we initialize the Q-table with a bias. We conducted training, validation, and path planning simulation experiments on public datasets. The results indicate that the NDR model outperforms previous methods by up to 5\% in prediction accuracy. Furthermore, the proposed NDR-QL method improves the convergence speed of the baseline Q-learning method by 90\% and also surpasses the previously improved Q-learning methods in path quality metrics.

cs.RO↗
arXiv2024

Boosting LLM-based Relevance Modeling with Distribution-Aware Robust Learning

With the rapid advancement of pre-trained large language models (LLMs), recent endeavors have leveraged the capabilities of LLMs in relevance modeling, resulting in enhanced performance. This is usually done through the process of fine-tuning LLMs on specifically annotated datasets to determine the relevance between queries and items. However, there are two limitations when LLMs are naively employed for relevance modeling through fine-tuning and inference. First, it is not inherently efficient for performing nuanced tasks beyond simple yes or no answers, such as assessing search relevance. It may therefore tend to be overconfident and struggle to distinguish fine-grained degrees of relevance (e.g., strong relevance, weak relevance, irrelevance) used in search engines. Second, it exhibits significant performance degradation when confronted with data distribution shift in real-world scenarios. In this paper, we propose a novel Distribution-Aware Robust Learning framework (DaRL) for relevance modeling in Alipay Search. Specifically, we design an effective loss function to enhance the discriminability of LLM-based relevance modeling across various fine-grained degrees of query-item relevance. To improve the generalizability of LLM-based relevance modeling, we first propose the Distribution-Aware Sample Augmentation (DASA) module. This module utilizes out-of-distribution (OOD) detection techniques to actively select appropriate samples that are not well covered by the original training set for model fine-tuning. Furthermore, we adopt a multi-stage fine-tuning strategy to simultaneously improve in-distribution (ID) and OOD performance, bridging the performance gap between them. DaRL has been deployed online to serve the Alipay's insurance product search...

cs.IR↗
arXiv2024

Strong-field magnetohydrodynamics for neutron stars

We present a formulation of magnetohydrodynamics which can be used to describe the evolution of strong magnetic fields in neutron star interiors. Our approach is based on viewing magnetohydrodynamics as a theory with a one-form global symmetry and developing an effective field theory for the hydrodynamic modes associated with this symmetry. In the regime where the local velocity and temperature variations can be neglected, we derive the most general constitutive relation consistent with symmetry constraints for the electric field in the presence of a strong magnetic field. This constitutive relation not only reproduces the phenomena of Ohmic decay, ambipolar diffusion, and Hall drift derived in a phenomenological model by Goldreich and Reisenegger, but also reveals new terms in the evolution of the magnetic field which cannot easily be seen from such microscopic models. This formulation gives predictions for novel diffusion behaviors of small perturbations around a constant background magnetic field, and for the two-point correlation functions among various components of the electric and magnetic fields.

astro-ph.HE↗
arXiv2024

Transverse magnetic focusing in two-dimensional hole gases

Two-dimensional hole gases (2DHGs) have strong intrinsic spin-orbit coupling and could be used to build spin filters by utilising transverse magnetic focusing (TMF). However, with an increase in the spin degree of freedom, holes demonstrate significantly different behaviour to electrons in TMF experiments, making it difficult to interpret the results of these experiments. In this paper, we numerically model TMF in a 2DHG within a GaAs/Al$_{\mathrm{x}}$Ga$_{\mathrm{1-x}}$As heterostructure. Our band structure calculations show that the heavy $(\langle J_{z} \rangle = \pm\frac{3}{2})$ and light $(\langle J_{z} \rangle = \pm\frac{1}{2})$ hole states in the valence band mix at finite $k$, and the heavy hole subbands which are spin-split due to the Rashba effect are not spin-polarised. This lack of spin polarisation casts doubt on the viability of spin filtering using TMF in 2DHGs within conventional GaAs/Al$_{\mathrm{x}}$Ga$_{\mathrm{1-x}}$As heterostructures. We then calculate transport properties of the 2DHG with spin projection and offer a new perspective on interpreting and designing TMF experiments in 2DHGs.

cond-mat.mes-hall↗
arXiv2024

Dual-Branch Graph Transformer Network for 3D Human Mesh Reconstruction from Video

Human Mesh Reconstruction (HMR) from monocular video plays an important role in human-robot interaction and collaboration. However, existing video-based human mesh reconstruction methods face a trade-off between accurate reconstruction and smooth motion. These methods design networks based on either RNNs or attention mechanisms to extract local temporal correlations or global temporal dependencies, but the lack of complementary long-term information and local details limits their performance. To address this problem, we propose a \textbf{D}ual-branch \textbf{G}raph \textbf{T}ransformer network for 3D human mesh \textbf{R}econstruction from video, named DGTR. DGTR employs a dual-branch network including a Global Motion Attention (GMA) branch and a Local Details Refine (LDR) branch to parallelly extract long-term dependencies and local crucial information, helping model global human motion and local human details (e.g., local motion, tiny movement). Specifically, GMA utilizes a global transformer to model long-term human motion. LDR combines modulated graph convolutional networks and the transformer framework to aggregate local information in adjacent frames and extract crucial information of human details. Experiments demonstrate that our DGTR outperforms state-of-the-art video-based methods in reconstruction accuracy and maintains competitive motion smoothness. Moreover, DGTR utilizes fewer parameters and FLOPs, which validate the effectiveness and efficiency of the proposed DGTR. Code is publicly available at \href{https://github.com/TangTao-PKU/DGTR}{\textcolor{myBlue}{https://github.com/TangTao-PKU/DGTR}}.

cs.CV↗
arXiv2024

DoubleCCA: Improving Foundation Model Group Robustness with Random Sentence Embeddings

This paper presents a novel method to improve the robustness of foundation models to group-based biases. We propose a simple yet effective method, called DoubleCCA, that leverages random sentences and Canonical Correlation Analysis (CCA) to enrich the text embeddings of the foundation model. First, we generate various random sentences that augment the original prompts, which extends the original prompts with random words or character sequences. Second, we use an additional sentence embedding model to generate different text embeddings with respect to these random sentences. We then use CCA double twice to align the representations and reconstruct them back to the original representation space. We demonstrate the effectiveness of our method on a variety of tasks and datasets, showing that it outperforms existing methods in terms of both performance and robustness. Our method is simple to implement and can be easily integrated into existing models, making it a practical solution for improving the robustness of foundation models to group-based biases.

cs.CL↗
arXiv2024

Induced even cycles in locally sparse graphs

A graph $G$ is $(c,t)$-sparse if for every pair of vertex subsets $A,B\subset V(G)$ with $|A|,|B|\geq t$, $e(A,B)\leq (1-c)|A||B|$. In this paper we prove that for every $c>0$ and integer $\ell$, there exists $C>1$ such that if an $n$-vertex graph $G$ is $(c,t)$-sparse for some $t$, and has at least $C t^{1-1/\ell}n^{1+1/\ell}$ edges, then $G$ contains an induced copy of $C_{2\ell}$. This resolves a conjecture of Fox, Nenadov and Pham.

math.CO↗
arXiv2024

Subregion-subalgebra duality: emergence of space and time in holography

In holographic duality, a higher dimensional quantum gravity system emerges from a lower dimensional conformal field theory (CFT) with a large number of degrees of freedom. We propose a formulation of duality for a general causally complete bulk spacetime region, called subregion-subalgebra duality, which provides a framework to describe how geometric notions in the gravity system, such as spacetime subregions, different notions of times, and causal structure, emerge from the dual CFT. Subregion-subalgebra duality generalizes and brings new insights into subregion-subregion duality (or equivalently entanglement wedge reconstruction). It provides a mathematically precise definition of subregion-subregion duality and gives an independent definition of entanglement wedges without using entropy. Geometric properties of entanglement wedges, including those that play a crucial role in interpreting the bulk as a quantum error correcting code, can be understood from the duality as the geometrization of the superadditivity of certain algebras. Using general boundary subalgebras rather than those associated with geometric subregions makes it possible to find duals for general bulk spacetime regions, including those not touching the boundary. Applying subregion-subalgebra duality to a boundary state describing a single-sided black hole also provides a precise way to define mirror operators.

hep-th↗