arXiv subjects

Rong Fan

Publications and source records attributed to Rong Fan.

8 recordsLinked to original sources

arXiv2026

GroundVTS: Visual Token Sampling in Multimodal Large Language Models for Video Temporal Grounding

Video temporal grounding (VTG) is a critical task in video understanding and a key capability for extending video large language models (Vid-LLMs) to broader applications. However, existing Vid-LLMs rely on uniform frame sampling to extract video information, resulting in a sparse distribution of key frames and the loss of crucial temporal cues. To address this limitation, we propose Grounded Visual Token Sampling (GroundVTS), a Vid-LLM architecture that focuses on the most informative temporal segments. GroundVTS employs a fine-grained, query-guided mechanism to filter visual tokens before feeding them into the LLM, thereby preserving essential spatio-temporal information and maintaining temporal coherence. Futhermore, we introduce a progressive optimization strategy that enables the LLM to effectively adapt to the non-uniform distribution of visual features, enhancing its ability to model temporal dependencies and achieve precise video localization. We comprehensively evaluate GroundVTS on three standard VTG benchmarks, where it outperforms existing methods, achieving a 7.7-point improvement in mIoU for moment retrieval and 12.0-point improvement in mAP for highlight detection. Code is available at https://github.com/Florence365/GroundVTS.

cs.CV↗

arXiv2025

MoCHA: Advanced Vision-Language Reasoning with MoE Connector and Hierarchical Group Attention

Vision large language models (VLLMs) are focusing primarily on handling complex and fine-grained visual information by incorporating advanced vision encoders and scaling up visual models. However, these approaches face high training and inference costs, as well as challenges in extracting visual details, effectively bridging across modalities. In this work, we propose a novel visual framework, MoCHA, to address these issues. Our framework integrates four vision backbones (i.e., CLIP, SigLIP, DINOv2 and ConvNeXt) to extract complementary visual features and is equipped with a sparse Mixture of Experts Connectors (MoECs) module to dynamically select experts tailored to different visual dimensions. To mitigate redundant or insufficient use of the visual information encoded by the MoECs module, we further design a Hierarchical Group Attention (HGA) with intra- and inter-group operations and an adaptive gating strategy for encoded visual features. We train MoCHA on two mainstream LLMs (e.g., Phi2-2.7B and Vicuna-7B) and evaluate their performance across various benchmarks. Notably, MoCHA outperforms state-of-the-art open-weight models on various tasks. For example, compared to CuMo (Mistral-7B), our MoCHA (Phi2-2.7B) presents outstanding abilities to mitigate hallucination by showing improvements of 3.25% in POPE and to follow visual instructions by raising 153 points on MME. Finally, ablation studies further confirm the effectiveness and robustness of the proposed MoECs and HGA in improving the overall performance of MoCHA.

cs.CV↗

arXiv2024

A Deep Learning System for Rapid and Accurate Warning of Acute Aortic Syndrome on Non-contrast CT in China

The accurate and timely diagnosis of acute aortic syndromes (AAS) in patients presenting with acute chest pain remains a clinical challenge. Aortic CT angiography (CTA) is the imaging protocol of choice in patients with suspected AAS. However, due to economic and workflow constraints in China, the majority of suspected patients initially undergo non-contrast CT as the initial imaging testing, and CTA is reserved for those at higher risk. In this work, we present an artificial intelligence-based warning system, iAorta, using non-contrast CT for AAS identification in China, which demonstrates remarkably high accuracy and provides clinicians with interpretable warnings. iAorta was evaluated through a comprehensive step-wise study. In the multi-center retrospective study (n = 20,750), iAorta achieved a mean area under the receiver operating curve (AUC) of 0.958 (95% CI 0.950-0.967). In the large-scale real-world study (n = 137,525), iAorta demonstrated consistently high performance across various non-contrast CT protocols, achieving a sensitivity of 0.913-0.942 and a specificity of 0.991-0.993. In the prospective comparative study (n = 13,846), iAorta demonstrated the capability to significantly shorten the time to correct diagnostic pathway. For the prospective pilot deployment that we conducted, iAorta correctly identified 21 out of 22 patients with AAS among 15,584 consecutive patients presenting with acute chest pain and under non-contrast CT protocol in the emergency department (ED) and enabled the average diagnostic time of these 21 AAS positive patients to be 102.1 (75-133) mins. Last, the iAorta can help avoid delayed or missed diagnosis of AAS in settings where non-contrast CT remains the unavoidable the initial or only imaging test in resource-constrained regions and in patients who cannot or did not receive intravenous contrast.

eess.IV↗

arXiv2024

TDANet: A Novel Temporal Denoise Convolutional Neural Network With Attention for Fault Diagnosis

Fault diagnosis plays a crucial role in maintaining the operational integrity of mechanical systems, preventing significant losses due to unexpected failures. As intelligent manufacturing and data-driven approaches evolve, Deep Learning (DL) has emerged as a pivotal technique in fault diagnosis research, recognized for its ability to autonomously extract complex features. However, the practical application of current fault diagnosis methods is challenged by the complexity of industrial environments. This paper proposed the Temporal Denoise Convolutional Neural Network With Attention (TDANet), designed to improve fault diagnosis performance in noise environments. This model transforms one-dimensional signals into two-dimensional tensors based on their periodic properties, employing multi-scale 2D convolution kernels to extract signal information both within and across periods. This method enables effective identification of signal characteristics that vary over multiple time scales. The TDANet incorporates a Temporal Variable Denoise (TVD) module with residual connections and a Multi-head Attention Fusion (MAF) module, enhancing the saliency of information within noisy data and maintaining effective fault diagnosis performance. Evaluation on two datasets, CWRU (single sensor) and Real aircraft sensor fault (multiple sensors), demonstrates that the TDANet model significantly outperforms existing deep learning approaches in terms of diagnostic accuracy under noisy environments.

cs.LG↗

arXiv2020

Commuting Service Platform: Concept and Analysis

We propose and investigate the concept of commuting service platforms (CSP) that leverage emerging mobility services to provide commuting services and connect directly commuters (employees) and their worksites (employers). By applying the two-sided market analysis framework, we show under what conditions a CSP may present the two-sidedness. Both the monopoly and duopoly CSPs are then analyzed. We showhowthe price allocation, i.e., the prices charged to commuters and worksites, can impact the participation and profit of the CSPs. We also add demand constraints to the duopoly model so that the participation rates ofworksites and employees are (almost) the same. With demand constraints, the competition between the two CSPs becomes less intense in general. Discussions are presented on how the results and findings in this paper may help build CSP in practice and how to develop new, CSP-based travel demand management strategies.

econ.GN↗

arXiv2012

Complex Orthogonal Matching Pursuit and Its Exact Recovery Conditions

In this paper, we present new results on using orthogonal matching pursuit (OMP), to solve the sparse approximation problem over redundant dictionaries for complex cases (i.e., complex measurement vector, complex dictionary and complex additive white Gaussian noise (CAWGN)). A sufficient condition that OMP can recover the optimal representation of an exactly sparse signal in the complex cases is proposed both in noiseless and bound Gaussian noise settings. Similar to exact recovery condition (ERC) results in real cases, we extend them to complex case and derivate the corresponding ERC in the paper. It leverages this theory to show that OMP succeed for k-sparse signal from a class of complex dictionary. Besides, an application with geometrical theory of diffraction (GTD) model is presented for complex cases. Finally, simulation experiments illustrate the validity of the theoretical analysis.

cs.IT↗

arXiv2012

A Fast HRRP Synthesis Algorithm with Sensing Dictionary in GTD Model

To achieve high range resolution profile (HRRP), the geometric theory of diffraction (GTD) parametric model is widely used in stepped-frequency radar system. In the paper, a fast synthetic range profile algorithm, called orthogonal matching pursuit with sensing dictionary (OMP-SD), is proposed. It formulates the traditional HRRP synthetic to be a sparse approximation problem over redundant dictionary. As it employs a priori information that targets are sparsely distributed in the range space, the synthetic range profile (SRP) can be accomplished even in presence of data lost. Besides, the computational complexity is reduced by introducing sensing dictionary (SD) and it mitigates the model mismatch at the same time. The computation complexity decreases from O(MNDK) flops for OMP to O(M(N +D)K) flops for OMP-SD. Simulation experiments illustrate its advantages both in additive white Gaussian noise (AWGN) and noiseless situation, respectively.

cs.IT↗

arXiv2003

Two band gap field-dependent thermal conductivity of $MgB_2$

The thermal conductivity $\kappa (H,T)$ of the new superconductor $MgB_2$ was studied as a function of the temperature and a magnetic field. No anomaly in the thermal conductivity $\kappa (H,T)$ is observed around the superconducting transition in absence or presence of magnetic fields up to 14 Tesla; upon that field the superconductivity of $MgB_2$ persisted. The thermal conductivity in zero-field shows a $T$-linear increase up to 50K. The thermal conductivity is found to increase with increasing field at high fields. We interpret the findings as if there are two subsystems of quasiparticles with different field-dependent characters in a two ($L$ and $S$)-band superconductor reacting differently with the vortex structure. The unusual enhancement of $\kappa (H ,T)$ at low temperature but higher than a ($H_{c2S}\simeq 3T$) critical field is interpreted as a result of the overlap of the low energy states outside the vortex cores in the $S$-band.

cond-mat.supr-con↗