Peer Revenue Play credits. Real papers.

Papers

Fresh from arXiv, typeset properly. Highlighted words trade on the market.

Computer Science Computer Vision

cs.CV Watch Computer Vision (sign in to use)

Wednesday 5 November

Computer Vision

MvBody: Multi-View-Based Hybrid Transformer Using Optical 3D Body Scan for Explainable Cesarean Section Prediction

Accurately assessing the risk of cesarean section (CS) delivery is critical, especially in settings with limited medical resources, where access to healthcare is often restricted. Early and reliable risk prediction allows better-informed prenatal care decisions and can improve maternal and neonatal outcomes. However, most existing predictive models are tailored for in-hospital use during labor and rely on parameters that are often unavailable in resource-limited or home-based settings. In this study, we conduct a pilot investigation to examine the feasibility of using 3D body shape for CS risk assessment for future applications with more affordable general devices. We propose a novel multi-view-based Transformer network, MvBody, which predicts CS risk using only self-reported medical data and 3D optical body scans obtained between the 31st and 38th weeks of gestation. To enhance training efficiency and model generalizability in data-scarce environments, we incorporate a metric learning loss into the network. Compared to widely used machine learning models and the latest advanced 3D analysis methods, our method demonstrates superior performance, achieving an accuracy of 84.62% and an Area Under the Receiver Operating Characteristic Curve (AUC-ROC) of 0.724 on the independent test set. To improve transparency and trust in the model's predictions, we apply the Integrated Gradients algorithm to provide theoretically grounded explanations of the model's decision-making process. Our results indicate that pre-pregnancy weight, maternal age, obstetric history, previous CS history, and body shape, particularly around the head and shoulders, are key contributors to CS risk prediction.
Read the full abstract

All authors Ruting Cheng, Boyuan Feng, Yijiang Zheng, Chuhui Qiu, Aizierjiang Aiersilan, Joaquin A. Calderon, Wentao Zhao, Qing Pan, James K. Hahn

Computer Vision

QG-CoC: Question-Guided Chain-of-Captions for Large Multimodal Models

Recently, Multimodal Large Language Models (MLLMs) encounter two key issues in multi-image contexts: (1) a lack of fine-grained perception across disparate images, and (2) a diminished capability to effectively reason over and synthesize information from multiple visual inputs. However, while various prompting methods aim to describe visual content, many existing studies focus primarily on single-image settings or specific, constrained scenarios. This leaves a critical gap in understanding and addressing how MLLMs tackle more general and complex multi-image reasoning tasks. Thus, we first extensively investigate how current prompting methods perceive fine-grained visual details and process visual information when dealing with multiple images. Our findings reveal that existing prompting methods fall short in attending to needed clues and seamlessly integrating perception and reasoning. Inspired by the findings, we propose a new zero-shot prompting method, Question-Guided Chain-of-Captions (QG-CoC), a generalized prompting approach that effectively handles problems with an arbitrary number of images. We evaluate our method on various open-source and closed-source MLLMs for multi-image and single-image benchmarks. Experimental results indicate that QG-CoC demonstrates competitive performance across tasks and exhibits robust improvements in the challenging scenarios where existing prompting methods fail.
Read the full abstract

All authors Kuei-Chun Kao, Hsu Tzu-Yin, Yunqi Hong, Ruochen Wang, Cho-Jui Hsieh

Computer Vision · Cross-listed from cs.LG

A Probabilistic U-Net Approach to Downscaling Climate Simulations

Climate models are limited by heavy computational costs, often producing outputs at coarse spatial resolutions, while many climate change impact studies require finer scales. Statistical downscaling bridges this gap, and we adapt the probabilistic U-Net for this task, combining a deterministic U-Net backbone with a variational latent space to capture aleatoric uncertainty. We evaluate four training objectives, afCRPS and WMSE-MS-SSIM with three settings for downscaling precipitation and temperature from $16\times$ coarser resolution. Our main finding is that WMSE-MS-SSIM performs well for extremes under certain settings, whereas afCRPS better captures spatial variability across scales.
Read the full abstract

All authors Maryam Alipourhajiagha, Pierre-Louis Lemaire, Youssef Diouane, Julie Carreau

Computer Vision

PETWB-REP: A Multi-Cancer Whole-Body FDG PET/CT and Radiology Report Dataset for Medical Imaging Research

Publicly available, large-scale medical imaging datasets are crucial for developing and validating artificial intelligence models and conducting retrospective clinical research. However, datasets that combine functional and anatomical imaging with detailed clinical reports across multiple cancer types remain scarce. Here, we present PETWB-REP, a curated dataset comprising whole-body 18F-Fluorodeoxyglucose (FDG) Positron Emission Tomography/Computed Tomography (PET/CT) scans and corresponding radiology reports from 490 patients diagnosed with various malignancies. The dataset primarily includes common cancers such as lung cancer, liver cancer, breast cancer, prostate cancer, and ovarian cancer. This dataset includes paired PET and CT images, de-identified textual reports, and structured clinical metadata. It is designed to support research in medical imaging, radiomics, artificial intelligence, and multi-modal learning.
Read the full abstract

All authors Le Xue, Gang Feng, Wenbo Zhang, Yichi Zhang, Lanlan Li, Shuqi Wang, Liling Peng, Sisi Peng, Xin Gao

Computer Vision

SurgAnt-ViVQA: Learning to Anticipate Surgical Events through GRU-Driven Temporal Cross-Attention

Anticipating forthcoming surgical events is vital for real-time assistance in endonasal transsphenoidal pituitary surgery, where visibility is limited and workflow changes rapidly. Most visual question answering (VQA) systems reason on isolated frames with static vision language alignment, providing little support for forecasting next steps or instrument needs. Existing surgical VQA datasets likewise center on the current scene rather than the near future. We introduce PitVQA-Anticipation, the first VQA dataset designed for forward looking surgical reasoning. It comprises 33.5 hours of operative video and 734,769 question answer pairs built from temporally grouped clips and expert annotations across four tasks: predicting the future phase, next step, upcoming instrument, and remaining duration. We further propose SurgAnt-ViVQA, a video language model that adapts a large language model using a GRU Gated Temporal Cross-Attention module. A bidirectional GRU encodes frame to frame dynamics, while an adaptive gate injects visual context into the language stream at the token level. Parameter efficient fine tuning customizes the language backbone to the surgical domain. SurgAnt-ViVQA tested upon on PitVQA-Anticipation and EndoVis datasets, surpassing strong image and video based baselines. Ablations show that temporal recurrence and gated fusion drive most of the gains. A frame budget study indicates a trade-off: 8 frames maximize fluency, whereas 32 frames slightly reduce BLEU but improve numeric time estimation. By pairing a temporally aware encoder with fine grained gated cross-attention, SurgAnt-ViVQA advances surgical VQA from retrospective description to proactive anticipation. PitVQA-Anticipation offers a comprehensive benchmark for this setting and highlights the importance of targeted temporal modeling for reliable, future aware surgical assistance.
Read the full abstract

All authors Shreyas C. Dhake, Jiayuan Huang, Runlong He, Danyal Z. Khan, Evangelos B. Mazomenos, Sophia Bano, Hani J. Marcus, Danail Stoyanov, Matthew J. Clarkson, Mobarak I. Hoque

Computer Vision

Subsampled Randomized Fourier GaLore for Adapting Foundation Models in Depth-Driven Liver Landmark Segmentation

Accurate detection and delineation of anatomical structures in medical imaging are critical for computer-assisted interventions, particularly in laparoscopic liver surgery where 2D video streams limit depth perception and complicate landmark localization. While recent works have leveraged monocular depth cues for enhanced landmark detection, challenges remain in fusing RGB and depth features and in efficiently adapting large-scale vision models to surgical domains. We propose a depth-guided liver landmark segmentation framework integrating semantic and geometric cues via vision foundation encoders. We employ Segment Anything Model V2 (SAM2) encoder to extract RGB features and Depth Anything V2 (DA2) encoder to extract depth-aware features. To efficiently adapt SAM2, we introduce SRFT-GaLore, a novel low-rank gradient projection method that replaces the computationally expensive SVD with a Subsampled Randomized Fourier Transform (SRFT). This enables efficient fine-tuning of high-dimensional attention layers without sacrificing representational power. A cross-attention fusion module further integrates RGB and depth cues. To assess cross-dataset generalization, we also construct a new Laparoscopic Liver Surgical Dataset (LLSD) as an external validation benchmark. On the public L3D dataset, our method achieves a 4.85% improvement in Dice Similarity Coefficient and a 11.78-point reduction in Average Symmetric Surface Distance compared to the D2GPLand. To further assess generalization capability, we evaluate our model on LLSD dataset. Our model maintains competitive performance and significantly outperforms SAM-based baselines, demonstrating strong cross-dataset robustness and adaptability to unseen surgical environments. These results demonstrate that our SRFT-GaLore-enhanced dual-encoder framework enables scalable and precise segmentation under real-time, depth-constrained surgical settings.
Read the full abstract

All authors Yun-Chen Lin, Jiayuan Huang, Hanyuan Zhang, Sergi Kavtaradze, Matthew J. Clarkson, Mobarak I. Hoque

Computer Vision

Finetuning-Free Personalization of Text to Image Generation via Hypernetworks

Personalizing text-to-image diffusion models has traditionally relied on subject-specific fine-tuning approaches such as DreamBooth~\cite{ruiz2023dreambooth}, which are computationally expensive and slow at inference. Recent adapter- and encoder-based methods attempt to reduce this overhead but still depend on additional fine-tuning or large backbone models for satisfactory results. In this work, we revisit an orthogonal direction: fine-tuning-free personalization via Hypernetworks that predict LoRA-adapted weights directly from subject images. Prior hypernetwork-based approaches, however, suffer from costly data generation or unstable attempts to mimic base model optimization trajectories. We address these limitations with an end-to-end training objective, stabilized by a simple output regularization, yielding reliable and effective hypernetworks. Our method removes the need for per-subject optimization at test time while preserving both subject fidelity and prompt alignment. To further enhance compositional generalization at inference time, we introduce Hybrid-Model Classifier-Free Guidance (HM-CFG), which combines the compositional strengths of the base diffusion model with the subject fidelity of personalized models during sampling. Extensive experiments on CelebA-HQ, AFHQ-v2, and DreamBench demonstrate that our approach achieves strong personalization performance and highlights the promise of hypernetworks as a scalable and effective direction for open-category personalization.
Read the full abstract

All authors Sagar Shrestha, Gopal Sharma, Luowei Zhou, Suren Kumar

Computer Vision · Cross-listed from cs.LG

Test Time Adaptation Using Adaptive Quantile Recalibration

Domain adaptation is a key strategy for enhancing the generalizability of deep learning models in real-world scenarios, where test distributions often diverge significantly from the training domain. However, conventional approaches typically rely on prior knowledge of the target domain or require model retraining, limiting their practicality in dynamic or resource-constrained environments. Recent test-time adaptation methods based on batch normalization statistic updates allow for unsupervised adaptation, but they often fail to capture complex activation distributions and are constrained to specific normalization layers. We propose Adaptive Quantile Recalibration (AQR), a test-time adaptation technique that modifies pre-activation distributions by aligning quantiles on a channel-wise basis. AQR captures the full shape of activation distributions and generalizes across architectures employing BatchNorm, GroupNorm, or LayerNorm. To address the challenge of estimating distribution tails under varying batch sizes, AQR incorporates a robust tail calibration strategy that improves stability and precision. Our method leverages source-domain statistics computed at training time, enabling unsupervised adaptation without retraining models. Experiments on CIFAR-10-C, CIFAR-100-C, and ImageNet-C across multiple architectures demonstrate that AQR achieves robust adaptation across diverse settings, outperforming existing test-time adaptation baselines. These results highlight AQR's potential for deployment in real-world scenarios with dynamic and unpredictable data distributions.
Read the full abstract

All authors Paria Mehrbod, Pedro Vianna, Geraldin Nanfack, Guy Wolf, Eugene Belilovsky

Computer Vision · Cross-listed from cs.GR

Scheduling the Off-Diagonal Weingarten Loss of Neural SDFs for CAD Models

Neural signed distance functions (SDFs) have become a powerful representation for geometric reconstruction from point clouds, yet they often require both gradient- and curvature-based regularization to suppress spurious warp and preserve structural fidelity. FlatCAD introduced the Off-Diagonal Weingarten (ODW) loss as an efficient second-order prior for CAD surfaces, approximating full-Hessian regularization at roughly half the computational cost. However, FlatCAD applies a fixed ODW weight throughout training, which is suboptimal: strong regularization stabilizes early optimization but suppresses detail recovery in later stages. We present scheduling strategies for the ODW loss that assign a high initial weight to stabilize optimization and progressively decay it to permit fine-scale refinement. We investigate constant, linear, quintic, and step interpolation schedules, as well as an increasing warm-up variant. Experiments on the ABC CAD dataset demonstrate that time-varying schedules consistently outperform fixed weights. Our method achieves up to a 35% improvement in Chamfer Distance over the FlatCAD baseline, establishing scheduling as a simple yet effective extension of curvature regularization for robust CAD reconstruction.
Read the full abstract

Computer Vision

Deploying Rapid Damage Assessments from sUAS Imagery for Disaster Response

This paper presents the first AI/ML system for automating building damage assessment in uncrewed aerial systems (sUAS) imagery to be deployed operationally during federally declared disasters (Hurricanes Debby and Helene). In response to major disasters, sUAS teams are dispatched to collect imagery of the affected areas to assess damage; however, at recent disasters, teams collectively delivered between 47GB and 369GB of imagery per day, representing more imagery than can reasonably be transmitted or interpreted by subject matter experts in the disaster scene, thus delaying response efforts. To alleviate this data avalanche encountered in practice, computer vision and machine learning techniques are necessary. While prior work has been deployed to automatically assess damage in satellite imagery, there is no current state of practice for sUAS-based damage assessment systems, as all known work has been confined to academic settings. This work establishes the state of practice via the development and deployment of models for building damage assessment with sUAS imagery. The model development involved training on the largest known dataset of post-disaster sUAS aerial imagery, containing 21,716 building damage labels, and the operational training of 91 disaster practitioners. The best performing model was deployed during the responses to Hurricanes Debby and Helene, where it assessed a combined 415 buildings in approximately 18 minutes. This work contributes documentation of the actual use of AI/ML for damage assessment during a disaster and lessons learned to the benefit of the AI/ML research and user communities.
Read the full abstract

Computer Vision

Accelerating Physical Property Reasoning for Augmented Visual Cognition

This paper introduces \sysname, a system that accelerates vision-guided physical property reasoning to enable augmented visual cognition. \sysname minimizes the run-time latency of this reasoning pipeline through a combination of both algorithmic and systematic optimizations, including rapid geometric 3D reconstruction, efficient semantic feature fusion, and parallel view encoding. Through these simple yet effective optimizations, \sysname reduces the end-to-end latency of this reasoning pipeline from 10–20 minutes to less than 6 seconds. A head-to-head comparison on the ABO dataset shows that \sysname achieves this 62.9$\times$–287.2$\times$ speedup while not only reaching on-par (and sometimes slightly better) object-level physical property estimation accuracy(e.g. mass), but also demonstrating superior performance in material segmentation and voxel-level inference than two SOTA baselines. We further combine gaze-tracking with \sysname to localize the object of interest in cluttered, real-world environments, streamlining the physical property reasoning on smart glasses. The case study with Meta Aria Glasses conducted at an IKEA furniture store demonstrates that \sysname achives consistently high performance compared to controlled captures, providing robust property estimations even with fewer views in real-world scenarios.
Read the full abstract

All authors Hongbo Lan, Zhenlin An, Haoyu Li, Vaibhav Singh, Longfei Shangguan

Computer Vision

Image-Intrinsic Priors for Integrated Circuit Defect Detection and Novel Class Discovery via Self-Supervised Learning

Integrated circuit manufacturing is highly complex, comprising hundreds of process steps. Defects can arise at any stage, causing yield loss and ultimately degrading product reliability. Supervised methods require extensive human annotation and struggle with emergent categories and rare, data scarce defects. Clustering-based unsupervised methods often exhibit unstable performance due to missing priors. We propose IC DefectNCD, a support set free framework that leverages Image Intrinsic Priors in IC SEM images for defect detection and novel class discovery. We first develop Self Normal Information Guided IC Defect Detection, aggregating representative normal features via a learnable normal information extractor and using reconstruction residuals to coarsely localize defect regions. To handle saliency variations across defects, we introduce an adaptive binarization strategy that produces stable subimages focused on core defective areas. Finally, we design Self Defect Information Guided IC Defect Classification, which incorporates a soft mask guided attention mechanism to inject spatial defect priors into the teacher student model. This enhances sensitivity to defective regions, suppresses background interference, and enables recognition and classification of unseen defects. We validate the approach on a real world dataset spanning three key fabrication stages and covering 15 defect types. Experiments demonstrate robust performance on both defect detection and unseen defect classification.
Read the full abstract

All authors Botong.Zhao, Xubin.Wang, Shujing.Lyu, Yue.Lu

Computer Vision

DentalSplat: Dental Occlusion Novel View Synthesis from Sparse Intra-Oral Photographs

In orthodontic treatment, particularly within telemedicine contexts, observing patients' dental occlusion from multiple viewpoints facilitates timely clinical decision-making. Recent advances in 3D Gaussian Splatting (3DGS) have shown strong potential in 3D reconstruction and novel view synthesis. However, conventional 3DGS pipelines typically rely on densely captured multi-view inputs and precisely initialized camera poses, limiting their practicality. Orthodontic cases, in contrast, often comprise only three sparse images, specifically, the anterior view and bilateral buccal views, rendering the reconstruction task especially challenging. The extreme sparsity of input views severely degrades reconstruction quality, while the absence of camera pose information further complicates the process. To overcome these limitations, we propose DentalSplat, an effective framework for 3D reconstruction from sparse orthodontic imagery. Our method leverages a prior-guided dense stereo reconstruction model to initialize the point cloud, followed by a scale-adaptive pruning strategy to improve the training efficiency and reconstruction quality of 3DGS. In scenarios with extremely sparse viewpoints, we further incorporate optical flow as a geometric constraint, coupled with gradient regularization, to enhance rendering fidelity. We validate our approach on a large-scale dataset comprising 950 clinical cases and an additional video-based test set of 195 cases designed to simulate real-world remote orthodontic imaging conditions. Experimental results demonstrate that our method effectively handles sparse input scenarios and achieves superior novel view synthesis quality for dental occlusion visualization, outperforming state-of-the-art techniques.
Read the full abstract

All authors Yiyi Miao, Taoyu Wu, Tong Chen, Sihao Li, Ji Jiang, Youpeng Yang, Angelos Stefanidis, Limin Yu, Jionglong Su

Computer Vision

ISC-Perception: A Hybrid Computer Vision Dataset for Object Detection in Novel Steel Assembly

The Intermeshed Steel Connection (ISC) system, when paired with robotic manipulators, can accelerate steel-frame assembly and improve worker safety by eliminating manual assembly. Dependable perception is one of the initial stages for ISC-aware robots. However, this is hampered by the absence of a dedicated image corpus, as collecting photographs on active construction sites is logistically difficult and raises safety and privacy concerns. In response, we introduce ISC-Perception, the first hybrid dataset expressly designed for ISC component detection. It blends procedurally rendered CAD images, game-engine photorealistic scenes, and a limited, curated set of real photographs, enabling fully automatic labelling of the synthetic portion. We explicitly account for all human effort to produce the dataset, including simulation engine and scene setup, asset preparation, post-processing scripts and quality checks; our total human time to generate a 10,000-image dataset was 30.5,h versus 166.7,h for manual labelling at 60,s per image (-81.7%). A manual pilot on a representative image with five instances of ISC members took 60,s (maximum 80,s), anchoring the manual baseline. Detectors trained on ISC-Perception achieved a mean Average Precision at IoU 0.50 of 0.756, substantially surpassing models trained on synthetic-only or photorealistic-only data. On a 1,200-frame bench test, we report mAP@0.50/mAP@[0.50:0.95] of 0.943/0.823. By bridging the data gap for construction-robotics perception, ISC-Perception facilitates rapid development of custom object detectors and is freely available for research and industrial use upon request.
Read the full abstract

All authors Miftahur Rahman, Samuel Adebayo, Dorian A. Acevedo-Mejia, David Hester, Daniel McPolin, Karen Rafferty, Debra F. Laefer

Computer Vision

A Plug-and-Play Framework for Volumetric Light-Sheet Image Reconstruction

Cardiac contraction is a rapid, coordinated process that unfolds across three-dimensional tissue on millisecond timescales. Traditional optical imaging is often inadequate for capturing dynamic cellular structure in the beating heart because of a fundamental trade-off between spatial and temporal resolution. To overcome these limitations, we propose a high-performance computational imaging framework that integrates Compressive Sensing (CS) with Light-Sheet Microscopy (LSM) for efficient, low-phototoxic cardiac imaging. The system performs compressed acquisition of fluorescence signals via random binary mask coding using a Digital Micromirror Device (DMD). We propose a Plug-and-Play (PnP) framework, solved using the alternating direction method of multipliers (ADMM), which flexibly incorporates advanced denoisers, including Tikhonov, Total Variation (TV), and BM3D. To preserve structural continuity in dynamic imaging, we further introduce temporal regularization enforcing smoothness between adjacent z-slices. Experimental results on zebrafish heart imaging under high compression ratios demonstrate that the proposed method successfully reconstructs cellular structures with excellent denoising performance and image clarity, validating the effectiveness and robustness of our algorithm in real-world high-speed, low-light biological imaging scenarios.
Read the full abstract

All authors Yi Gong, Xinyuan Zhang, Jichen Chai, Yichen Ding, Yifei Lou

Tuesday 4 November

Computer Vision

V-Agent: An Interactive Video Search System Using Vision-Language Models

We introduce V-Agent, a novel multi-agent platform designed for advanced video search and interactive user-system conversations. By fine-tuning a vision-language model (VLM) with a small video preference dataset and enhancing it with a retrieval vector from an image-text retrieval model, we overcome the limitations of traditional text-based retrieval systems in multimodal scenarios. The VLM-based retrieval model independently embeds video frames and audio transcriptions from an automatic speech recognition (ASR) module into a shared multimodal representation space, enabling V-Agent to interpret both visual and spoken content for context-aware video search. This system consists of three agents-a routing agent, a search agent, and a chat agent-that work collaboratively to address user intents by refining search outputs and communicating with users. The search agent utilizes the VLM-based retrieval model together with an additional re-ranking module to further enhance video retrieval quality. Our proposed framework demonstrates state-of-the-art zero-shot performance on the MultiVENT 2.0 benchmark, highlighting its potential for both academic research and real-world applications. The retrieval model and demo videos are available at https://huggingface.co/NCSOFT/multimodal-embedding.
Read the full abstract

All authors SunYoung Park, Jong-Hyeon Lee, Youngjune Kim, Daegyu Sung, Younghyun Yu, Young-rok Cha, Jeongho Ju

Computer Vision

DiffSwap++: 3D Latent-Controlled Diffusion for Identity-Preserving Face Swapping

Diffusion-based approaches have recently achieved strong results in face swapping, offering improved visual quality over traditional GAN-based methods. However, even state-of-the-art models often suffer from fine-grained artifacts and poor identity preservation, particularly under challenging poses and expressions. A key limitation of existing approaches is their failure to meaningfully leverage 3D facial structure, which is crucial for disentangling identity from pose and expression. In this work, we propose DiffSwap++, a novel diffusion-based face-swapping pipeline that incorporates 3D facial latent features during training. By guiding the generation process with 3D-aware representations, our method enhances geometric consistency and improves the disentanglement of facial identity from appearance attributes. We further design a diffusion architecture that conditions the denoising process on both identity embeddings and facial landmarks, enabling high-fidelity and identity-preserving face swaps. Extensive experiments on CelebA, FFHQ, and CelebV-Text demonstrate that DiffSwap++ outperforms prior methods in preserving source identity while maintaining target pose and expression. Additionally, we introduce a biometric-style evaluation and conduct a user study to further validate the realism and effectiveness of our approach. Code will be made publicly available at https://github.com/WestonBond/DiffSwapPP
Read the full abstract

All authors Weston Bondurant, Arkaprava Sinha, Hieu Le, Srijan Das, Stephanie Schuckers

Computer Vision

Elements of Active Continuous Learning and Uncertainty Self-Awareness: a Narrow Implementation for Face and Facial Expression Recognition

Reflection on one's thought process and making corrections to it if there exists dissatisfaction in its performance is, perhaps, one of the essential traits of intelligence. However, such high-level abstract concepts mandatory for Artificial General Intelligence can be modelled even at the low level of narrow Machine Learning algorithms. Here, we present the self-awareness mechanism emulation in the form of a supervising artificial neural network (ANN) observing patterns in activations of another underlying ANN in a search for indications of the high uncertainty of the underlying ANN and, therefore, the trustworthiness of its predictions. The underlying ANN is a convolutional neural network (CNN) ensemble employed for face recognition and facial expression tasks. The self-awareness ANN has a memory region where its past performance information is stored, and its learnable parameters are adjusted during the training to optimize the performance. The trustworthiness verdict triggers the active learning mode, giving elements of agency to the machine learning algorithm that asks for human help in high uncertainty and confusion conditions.
Read the full abstract

Computer Vision

Video Text Preservation with Synthetic Text-Rich Videos

While Text-To-Video (T2V) models have advanced rapidly, they continue to struggle with generating legible and coherent text within videos. In particular, existing models often fail to render correctly even short phrases or words and previous attempts to address this problem are computationally expensive and not suitable for video generation. In this work, we investigate a lightweight approach to improve T2V diffusion models using synthetic supervision. We first generate text-rich images using a text-to-image (T2I) diffusion model, then animate them into short videos using a text-agnostic image-to-video (I2v) model. These synthetic video-prompt pairs are used to fine-tune Wan2.1, a pre-trained T2V model, without any architectural changes. Our results show improvement in short-text legibility and temporal consistency with emerging structural priors for longer text. These findings suggest that curated synthetic data and weak supervision offer a practical path toward improving textual fidelity in T2V generation.
Read the full abstract

Computer Vision

C3-Diff: Super-resolving Spatial Transcriptomics via Cross-modal Cross-content Contrastive Diffusion Modelling

The rapid advancement of spatial transcriptomics (ST), i.e., spatial gene expressions, has made it possible to measure gene expression within original tissue, enabling us to discover molecular mechanisms. However, current ST platforms frequently suffer from low resolution, limiting the in-depth understanding of spatial gene expression. Super-resolution approaches promise to enhance ST maps by integrating histology images with gene expressions of profiled tissue spots. However, it remains a challenge to model the interactions between histology images and gene expressions for effective ST enhancement. This study presents a cross-modal cross-content contrastive diffusion framework, called C3-Diff, for ST enhancement with histology images as guidance. In C3-Diff, we firstly analyze the deficiency of traditional contrastive learning paradigm, which is then refined to extract both modal-invariant and content-invariant features of ST maps and histology images. Further, to overcome the problem of low sequencing sensitivity in ST maps, we perform nosing-based information augmentation on the surface of feature unit hypersphere. Finally, we propose a dynamic cross-modal imputation-based training strategy to mitigate ST data scarcity. We tested C3-Diff by benchmarking its performance on four public datasets, where it achieves significant improvements over competing methods. Moreover, we evaluate C3-Diff on downstream tasks of cell type localization, gene expression correlation and single-cell-level gene expression prediction, promoting AI-enhanced biotechnology for biomedical research and clinical applications. Codes are available at https://github.com/XiaofeiWang2018/C3-Diff.
Read the full abstract

Computer Vision

Do Street View Imagery and Public Participation GIS align: Comparative Analysis of Urban Attractiveness

As digital tools increasingly shape spatial planning practices, understanding how different data sources reflect human experiences of urban environments is essential. Street View Imagery (SVI) and Public Participation GIS (PPGIS) represent two prominent approaches for capturing place-based perceptions that can support urban planning decisions, yet their comparability remains underexplored. This study investigates the alignment between SVI-based perceived attractiveness and residents' reported experiences gathered via a city-wide PPGIS survey in Helsinki, Finland. Using participant-rated SVI data and semantic image segmentation, we trained a machine learning model to predict perceived attractiveness based on visual features. We compared these predictions to PPGIS-identified locations marked as attractive or unattractive, calculating agreement using two sets of strict and moderate criteria. Our findings reveal only partial alignment between the two datasets. While agreement (with a moderate threshold) reached 67% for attractive and 77% for unattractive places, agreement (with a strict threshold) dropped to 27% and 29%, respectively. By analysing a range of contextual variables, including noise, traffic, population presence, and land use, we found that non-visual cues significantly contributed to mismatches. The model failed to account for experiential dimensions such as activity levels and environmental stressors that shape perceptions but are not visible in images. These results suggest that while SVI offers a scalable and visual proxy for urban perception, it cannot fully substitute the experiential richness captured through PPGIS. We argue that both methods are valuable but serve different purposes; therefore, a more integrated approach is needed to holistically capture how people perceive urban environments.
Read the full abstract

All authors Milad Malekzadeh, Elias Willberg, Jussi Torkko, Silviya Korpilo, Kamyar Hasanzadeh, Olle Järv, Tuuli Toivonen

Computer Vision · Cross-listed from cs.LG

Adaptive Sample-Level Framework Motivated by Distributionally Robust Optimization with Variance-Based Radius Assignment for Enhanced Neural Network Generalization Under Distribution Shift

Distribution shifts and minority subpopulations frequently undermine the reliability of deep neural networks trained using Empirical Risk Minimization (ERM). Distributionally Robust Optimization (DRO) addresses this by optimizing for the worst-case risk within a neighborhood of the training distribution. However, conventional methods depend on a single, global robustness budget, which can lead to overly conservative models or a misallocation of robustness. We propose a variance-driven, adaptive, sample-level DRO (Var-DRO) framework that automatically identifies high-risk training samples and assigns a personalized robustness budget to each based on its online loss variance. Our formulation employs two-sided, KL-divergence-style bounds to constrain the ratio between adversarial and empirical weights for every sample. This results in a linear inner maximization problem over a convex polytope, which admits an efficient water-filling solution. To stabilize training, we introduce a warmup phase and a linear ramp schedule for the global cap on per-sample budgets, complemented by label smoothing for numerical robustness. Evaluated on CIFAR-10-C (corruptions), our method achieves the highest overall mean accuracy compared to ERM and KL-DRO. On Waterbirds, Var-DRO improves overall performance while matching or surpassing KL-DRO. On the original CIFAR-10 dataset, Var-DRO remains competitive, exhibiting the modest trade-off anticipated when prioritizing robustness. The proposed framework is unsupervised (requiring no group labels), straightforward to implement, theoretically sound, and computationally efficient.
Read the full abstract

Computer Vision

Automatic Extraction of Road Networks by using Teacher-Student Adaptive Structural Deep Belief Network and Its Application to Landslide Disaster

An adaptive structural learning method of Restricted Boltzmann Machine (RBM) and Deep Belief Network (DBN) has been developed as one of prominent deep learning models. The neuron generation-annihilation algorithm in RBM and layer generation algorithm in DBN make an optimal network structure for given input during the learning. In this paper, our model is applied to an automatic recognition method of road network system, called RoadTracer. RoadTracer can generate a road map on the ground surface from aerial photograph data. A novel method of RoadTracer using the Teacher-Student based ensemble learning model of Adaptive DBN is proposed, since the road maps contain many complicated features so that a model with high representation power to detect should be required. The experimental results showed the detection accuracy of the proposed model was improved from 40.0% to 89.0% on average in the seven major cities among the test dataset. In addition, we challenged to apply our method to the detection of available roads when landslide by natural disaster is occurred, in order to rapidly obtain a way of transportation. For fast inference, a small size of the trained model was implemented on a small embedded edge device as lightweight deep learning. We reported the detection results for the satellite image before and after the rainfall disaster in Japan. This version of the article was improved the search algorithm at the border around image.
Read the full abstract

Computer Vision

Efficient Online Continual Learning in Sensor-Based Human Activity Recognition

Machine learning models for sensor-based human activity recognition (HAR) are expected to adapt post-deployment to recognize new activities and different ways of performing existing ones. To address this need, Online Continual Learning (OCL) mechanisms have been proposed, allowing models to update their knowledge incrementally as new data become available while preserving previously acquired information. However, existing OCL approaches for sensor-based HAR are computationally intensive and require extensive labeled samples to represent new changes. Recently, pre-trained model-based (PTM-based) OCL approaches have shown significant improvements in performance and efficiency for computer vision applications. These methods achieve strong generalization capabilities by pre-training complex models on large datasets, followed by fine-tuning on downstream tasks for continual learning. However, applying PTM-based OCL approaches to sensor-based HAR poses significant challenges due to the inherent heterogeneity of HAR datasets and the scarcity of labeled data in post-deployment scenarios. This paper introduces PTRN-HAR, the first successful application of PTM-based OCL to sensor-based HAR. Unlike prior PTM-based OCL approaches, PTRN-HAR pre-trains the feature extractor using contrastive loss with a limited amount of data. This extractor is then frozen during the streaming stage. Furthermore, it replaces the conventional dense classification layer with a relation module network. Our design not only significantly reduces the resource consumption required for model training while maintaining high performance, but also improves data efficiency by reducing the amount of labeled data needed for effective continual learning, as demonstrated through experiments on three public datasets, outperforming the state-of-the-art. The code can be found here: https://anonymous.4open.science/r/PTRN-HAR-AF60/
Read the full abstract

Computer Vision

In-Context Adaptation of VLMs for Few-Shot Cell Detection in Optical Microscopy

Foundation vision-language models (VLMs) excel on natural images, but their utility for biomedical microscopy remains underexplored. In this paper, we investigate how in-context learning enables state-of-the-art VLMs to perform few-shot object detection when large annotated datasets are unavailable, as is often the case with microscopic images. We introduce the Micro-OD benchmark, a curated collection of 252 images specifically curated for in-context learning, with bounding-box annotations spanning 11 cell types across four sources, including two in-lab expert-annotated sets. We systematically evaluate eight VLMs under few-shot conditions and compare variants with and without implicit test-time reasoning tokens. We further implement a hybrid Few-Shot Object Detection (FSOD) pipeline that combines a detection head with a VLM-based few-shot classifier, which enhances the few-shot performance of recent VLMs on our benchmark. Across datasets, we observe that zero-shot performance is weak due to the domain gap; however, few-shot support consistently improves detection, with marginal gains achieved after six shots. We observe that models with reasoning tokens are more effective for end-to-end localization, whereas simpler variants are more suitable for classifying pre-localized crops. Our results highlight in-context adaptation as a practical path for microscopy, and our benchmark provides a reproducible testbed for advancing open-vocabulary detection in biomedical imaging.
Read the full abstract

All authors Shreyan Ganguly, Angona Biswas, Jaydeep Rade, Md Hasibul Hasan Hasib, Nabila Masud, Nitish Singla, Abhipsa Dash, Ushashi Bhattacharjee, Aditya Balu, Anwesha Sarkar, Adarsh Krishnamurthy, Soumik Sarkar

Computer Vision

M2S2L: Mamba-based Multi-Scale Spatial-temporal Learning for Video Anomaly Detection

Video anomaly detection (VAD) is an essential task in the image processing community with prospects in video surveillance, which faces fundamental challenges in balancing detection accuracy with computational efficiency. As video content becomes increasingly complex with diverse behavioral patterns and contextual scenarios, traditional VAD approaches struggle to provide robust assessment for modern surveillance systems. Existing methods either lack comprehensive spatial-temporal modeling or require excessive computational resources for real-time applications. In this regard, we present a Mamba-based multi-scale spatial-temporal learning (M2S2L) framework in this paper. The proposed method employs hierarchical spatial encoders operating at multiple granularities and multi-temporal encoders capturing motion dynamics across different time scales. We also introduce a feature decomposition mechanism to enable task-specific optimization for appearance and motion reconstruction, facilitating more nuanced behavioral modeling and quality-aware anomaly assessment. Experiments on three benchmark datasets demonstrate that M2S2L framework achieves 98.5%, 92.1%, and 77.9% frame-level AUCs on UCSD Ped2, CUHK Avenue, and ShanghaiTech respectively, while maintaining efficiency with 20.1G FLOPs and 45 FPS inference speed, making it suitable for practical surveillance deployment.
Read the full abstract

All authors Yang Liu, Boan Chen, Xiaoguang Zhu, Jing Liu, Peng Sun, Wei Zhou

Computer Vision

FilletRec: A Lightweight Graph Neural Network with Intrinsic Features for Automated Fillet Recognition

Automated recognition and simplification of fillet features in CAD models is critical for CAE analysis, yet it remains an open challenge. Traditional rule-based methods lack robustness, while existing deep learning models suffer from poor generalization and low accuracy on complex fillets due to their generic design and inadequate training data. To address these issues, this paper proposes an end-to-end, data-driven framework specifically for fillet features. We first construct and release a large-scale, diverse benchmark dataset for fillet recognition to address the inadequacy of existing data. Based on it, we propose FilletRec, a lightweight graph neural network. The core innovation of this network is its use of pose-invariant intrinsic geometric features, such as curvature, enabling it to learn more fundamental geometric patterns and thereby achieve high-precision recognition of complex geometric topologies. Experiments show that FilletRec surpasses state-of-the-art methods in both accuracy and generalization, while using only 0.2%-5.4% of the parameters of baseline models, demonstrating high model efficiency. Finally, the framework completes the automated workflow from recognition to simplification by integrating an effective geometric simplification algorithm.
Read the full abstract

All authors Jiali Gao, Taoran Liu, Hongfei Ye, Jianjun Chen

Computer Vision

From Propagation to Prediction: Point-level Uncertainty Evaluation of MLS Point Clouds under Limited Ground Truth

Evaluating uncertainty is critical for reliable use of Mobile Laser Scanning (MLS) point clouds in many high-precision applications such as Scan-to-BIM, deformation analysis, and 3D modeling. However, obtaining the ground truth (GT) for evaluation is often costly and infeasible in many real-world applications. To reduce this long-standing reliance on GT in uncertainty evaluation research, this study presents a learning-based framework for MLS point clouds that integrates optimal neighborhood estimation with geometric feature extraction. Experiments on a real-world dataset show that the proposed framework is feasible and the XGBoost model delivers fully comparable accuracy to Random Forest while achieving substantially higher efficiency (about 3 times faster), providing initial evidence that geometric features can be used to predict point-level uncertainty quantified by the C2C distance. In summary, this study shows that MLS point clouds' uncertainty is learnable, offering a novel learning-based viewpoint towards uncertainty evaluation research.
Read the full abstract

Computer Vision · Cross-listed from cs.LG

Data-Efficient Realized Volatility Forecasting with Vision Transformers

Recent work in financial machine learning has shown the virtue of complexity: the phenomenon by which deep learning methods capable of learning highly nonlinear relationships outperform simpler approaches in financial forecasting. While transformer architectures like Informer have shown promise for financial time series forecasting, the application of transformer models for options data remains largely unexplored. We conduct preliminary studies towards the development of a transformer model for options data by training the Vision Transformer (ViT) architecture, typically used in modern image recognition and classification systems, to predict the realized volatility of an asset over the next 30 days from its implied volatility surface (augmented with date information) for a single day. We show that the ViT can learn seasonal patterns and nonlinear features from the IV surface, suggesting a promising direction for model development.
Read the full abstract

Computer Vision

SLIP: Structural-aware Language-Image Pretraining for Vision-Language Alignment

Vision-Language Pretraining (VLP) has achieved remarkable success across various downstream tasks, but such gains are largely driven by scaling up on training data. Yet, literature methods treat image-text pairs as isolated training examples; this neglects the rich relational structure naturally present in many domains, such as e-commerce product co-purchase graphs and social recommendation networks. Inspired by neuroscientific evidence that human encodes knowledge as relationship cognitive maps, we introduce Structure-aware Language-Image Pretraining (SLIP). SLIP integrates a structural contrastive loss to align modalities while also modeling relationships between neighboring entities in a structured graph. To support this paradigm, we construct a large-scale Amazon Product Co-purchase Multimodal Graph Dataset, enabling structured cross-modality supervision at scale. Experiment results show that SLIP consistently outperforms CLIP on cross-modal retrieval and classification tasks in both zero-shot and few-shot settings, showing the value of relational supervision for cross-modal alignment.
Read the full abstract