arXiv subjects

Xiaoya Tang

Publications and source records attributed to Xiaoya Tang.

7 recordsLinked to original sources

arXiv2026

Towards Accurate and Robust Surveillance Roadside IVD via Trackletized Audio-Visual Reasoning

Idling Vehicle Detection (IVD) seeks to determine, at the final frame of a video clip, whether any vehicle is idling, meaning the vehicle is stationary with its engine running, using synchronized video from a remote surveillance camera and multichannel audio captured by spatially distributed wireless microphones along the roadside. Prior full-image, clip-level fusion approaches tend to overfit scene background and full-frame context, produce unstable temporal decisions, and lack an explicit spatial prior to align vehicles with microphones, which makes them brittle under domain shift and data inefficient. Instead, we introduce TAVR-IVD, an audio-visual framework guided by multi-object tracking. Our method detects vehicles, links detections into tracklets, and classifies each vehicle by operating on its tracklet. This design raises the effective signal-to-noise ratio, stabilizes temporal decisions through tracklets, enforces an explicit spatial prior to align vehicles with microphones, and adapts across domains with limited calibration annotations while remaining detector agnostic and efficient. To evaluate deployment robustness, we further curate two evaluation extensions, AVIVD-LT and AVIVD-M, covering inter-day and cross-site shifts.

cs.CV↗

arXiv2026

Weakly Supervised Contrastive Learning for Histopathology Patch Embeddings

Digital histopathology whole slide images (WSIs) provide gigapixel-scale high-resolution images that are highly useful for disease diagnosis. However, digital histopathology image analysis faces significant challenges due to the limited training labels, since manually annotating specific regions or small patches cropped from large WSIs requires substantial time and effort. Weakly supervised multiple instance learning (MIL) offers a practical and efficient solution by requiring only bag-level (slide-level) labels, while each bag typically contains multiple instances (patches). Most MIL methods directly use frozen image patch features generated by various image encoders as inputs and primarily focus on feature aggregation. However, feature representation learning for encoder pretraining in MIL settings has largely been neglected. In our work, we propose a novel feature representation learning framework called weakly supervised contrastive learning (WeakSupCon) that incorporates bag-level label information during training. Our method does not rely on instance-level pseudo-labeling, yet it effectively separates patches with different labels in the feature space. Experimental results demonstrate that the image features generated by our WeakSupCon method lead to improved downstream MIL performance compared to self-supervised contrastive learning approaches in three datasets. Our related code is available at github.com/BzhangURU/Paper_WeakSupCon_for_MIL

cs.CV↗

arXiv2026

How to Build Robust, Scalable Models for GSV-Based Indicators in Neighborhood Research

A substantial body of health research demonstrates a strong link between neighborhood environments and health outcomes. Recently, there has been increasing interest in leveraging advances in computer vision to enable large-scale, systematic characterization of neighborhood built environments. However, the generalizability of vision models across fundamentally different domains remains uncertain, for example, transferring knowledge from ImageNet to the distinct visual characteristics of Google Street View (GSV) imagery. In applied fields such as social health research, several critical questions arise: which models are most appropriate, whether to adopt unsupervised training strategies, what training scale is feasible under computational constraints, and how much such strategies benefit downstream performance. These decisions are often costly and require specialized expertise. In this paper, we answer these questions through empirical analysis and provide practical insights into how to select and adapt foundation models for datasets with limited size and labels, while leveraging larger, unlabeled datasets through unsupervised training. Our study includes comprehensive quantitative and visual analyses comparing model performance before and after unsupervised adaptation.

cs.CV↗

arXiv2025

DuoFormer: Leveraging Hierarchical Representations by Local and Global Attention Vision Transformer

Despite the widespread adoption of transformers in medical applications, the exploration of multi-scale learning through transformers remains limited, while hierarchical representations are considered advantageous for computer-aided medical diagnosis. We propose a novel hierarchical transformer model that adeptly integrates the feature extraction capabilities of Convolutional Neural Networks (CNNs) with the advanced representational potential of Vision Transformers (ViTs). Addressing the lack of inductive biases and dependence on extensive training datasets in ViTs, our model employs a CNN backbone to generate hierarchical visual representations. These representations are adapted for transformer input through an innovative patch tokenization process, preserving the inherited multi-scale inductive biases. We also introduce a scale-wise attention mechanism that directly captures intra-scale and inter-scale associations. This mechanism complements patch-wise attention by enhancing spatial understanding and preserving global perception, which we refer to as local and global attention, respectively. Our model significantly outperforms baseline models in terms of classification accuracy, demonstrating its efficiency in bridging the gap between Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs). The components are designed as plug-and-play for different CNN architectures and can be adapted for multiple applications. The code is available at https://github.com/xiaoyatang/DuoFormer.git.

cs.CV↗

arXiv2025

HAVT-IVD: Heterogeneity-Aware Cross-Modal Network for Audio-Visual Surveillance: Idling Vehicles Detection With Multichannel Audio and Multiscale Visual Cues

Idling vehicle detection (IVD) uses surveillance video and multichannel audio to localize and classify vehicles in the last frame as moving, idling, or engine-off in pick-up zones. IVD faces three challenges: (i) modality heterogeneity between visual cues and audio patterns; (ii) large box scale variation requiring multi-resolution detection; and (iii) training instability due to coupled detection heads. The previous end-to-end (E2E) model with simple CBAM-based bi-modal attention fails to handle these issues and often misses vehicles. We propose HAVT-IVD, a heterogeneity-aware network with a visual feature pyramid and decoupled heads. Experiments show HAVT-IVD improves mAP by 7.66 over the disjoint baseline and 9.42 over the E2E baseline.

cs.CV↗

arXiv2024

Hierarchical Transformer for Electrocardiogram Diagnosis

We propose a hierarchical Transformer for ECG analysis that combines depth-wise convolutions, multi-scale feature aggregation via a CLS token, and an attention-gated module to learn inter-lead relationships and enhance interpretability. The model is lightweight, flexible, and eliminates the need for complex attention or downsampling strategies.

cs.LG↗

arXiv2024

DuoFormer: Leveraging Hierarchical Visual Representations by Local and Global Attention

We here propose a novel hierarchical transformer model that adeptly integrates the feature extraction capabilities of Convolutional Neural Networks (CNNs) with the advanced representational potential of Vision Transformers (ViTs). Addressing the lack of inductive biases and dependence on extensive training datasets in ViTs, our model employs a CNN backbone to generate hierarchical visual representations. These representations are then adapted for transformer input through an innovative patch tokenization. We also introduce a 'scale attention' mechanism that captures cross-scale dependencies, complementing patch attention to enhance spatial understanding and preserve global perception. Our approach significantly outperforms baseline models on small and medium-sized medical datasets, demonstrating its efficiency and generalizability. The components are designed as plug-and-play for different CNN architectures and can be adapted for multiple applications. The code is available at https://github.com/xiaoyatang/DuoFormer.git.

cs.CV↗