Computer Vision and Image Understanding最新文献

{"title":"Mobile Auslan: A multimodal dialogue-centered sign language learning system","authors":"Hongwei Sheng,&nbsp;Xin Shen,&nbsp;Heming Du,&nbsp;Xin Yu","doi":"10.1016/j.cviu.2026.104646","DOIUrl":"10.1016/j.cviu.2026.104646","url":null,"abstract":"<div><div>Learning sign language is not only a gateway to linguistic competence but also to cultural participation, self-expression, and meaningful interaction within the Deaf community. Recent advances in sign language education technologies have made notable progress in supporting vocabulary acquisition and sentence-level translation. However, dialogue, as one critical component of natural language use, remains largely absent from existing systems. We identify two underlying challenges that contribute to this gap: the lack of recognition robustness to viewpoint variation, which constrains expressive freedom during signing; and the limited semantic modeling capabilities needed to support discourse-level interpretation and interaction. To address these issues, we propose a learning-centered system that integrates pose-based multi-view augmentation and a multi-agent language modeling workflow. This system supports free-form input across diverse signing perspectives and provides structured feedback across word, sentence, and dialogue levels. Built as a modular and deployable platform, the system demonstrates strong recognition performance and learner engagement across varied input conditions. Through this integration of spatial robustness and semantic scaffolding, our work advances the design of sign language learning technologies toward more interactive, expressive, and pedagogically grounded experiences. However, the current system remains limited by its focus on successive (non-continuous) signing and by its moderate vocabulary and restricted pedagogical scope. Future work will therefore extend lexical coverage, incorporate more natural continuous signing, and investigate richer educational functions.</div></div>","PeriodicalId":50633,"journal":{"name":"Computer Vision and Image Understanding","volume":"265 ","pages":"Article 104646"},"PeriodicalIF":3.5,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146191647","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"FDE: A Frequency-Domain Enhancement method for object detection in complex traffic scenes","authors":"Wenyan Sun ,&nbsp;Feifei Xie ,&nbsp;Yuxuan Zhang ,&nbsp;Liangrui Wei ,&nbsp;Fuzheng Chu ,&nbsp;Xiaoyu Tang","doi":"10.1016/j.cviu.2026.104677","DOIUrl":"10.1016/j.cviu.2026.104677","url":null,"abstract":"<div><div>Object detectors in complex traffic scenes often struggle with small objects, cluttered boundaries, and heavy occlusions due to a low-frequency bias, where models capture smooth backgrounds but overlook high-frequency details. To address this, we propose a Frequency-Domain Enhancement (FDE) framework that integrates three modules: (i) Frequency-Adaptive Attention (FAA) to dynamically emphasize informative frequency components, (ii) Enhanced Frequency Dynamic Convolution (EFDConv) to adaptively model diverse spectral patterns, and (iii) Frequency-Aware Supervision (FAS) to guide training towards edge and fine-structure preservation. Embedded into RT-DETR, FDE achieves consistent gains of +1.7 mAP on KITTI dataset and +1.9 mAP on COCO dataset, with negligible computational overhead. These results demonstrate that FDE effectively alleviates low-frequency bias and improves detection of small and adjacent objects, making it suitable for deployment in complex traffic environments.</div></div>","PeriodicalId":50633,"journal":{"name":"Computer Vision and Image Understanding","volume":"265 ","pages":"Article 104677"},"PeriodicalIF":3.5,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146191766","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Grey wolf optimization for color quantization","authors":"María-Luisa Pérez-Delgado ,&nbsp;Jesús-Ángel Román-Gallego ,&nbsp;M. Emre Celebi","doi":"10.1016/j.cviu.2026.104659","DOIUrl":"10.1016/j.cviu.2026.104659","url":null,"abstract":"<div><div>Color quantization is an image processing operation that attempts to reduce the number of distinct colors used to represent an image without significant loss of quality. This operation is useful as an initial step to perform further processing on the image. The interest in this operation has led to several solution methods being proposed over the years. Within these methods several swarm-based methods have been used in recent years to solve the problem. This article discusses the application of one of these methods, called grey wolf optimization, to perform color quantization. This algorithm has generated good results when applied to a variety of optimization problems. Among the features that differentiate this algorithm from other swarm algorithms are its ability to converge toward better solutions, its speed, and the existence of a single control parameter. The article describes in detail how the grey wolf optimization method should be adapted to perform color quantization, so that it generates a quantized palette that allows the quantized image to be represented. In this case, each individual in the group represents a quantized palette, which is improved with the information provided by the group. The detailed description of the algorithm is complemented by an extensive testing section that compares the results of the proposed method to those of 16 others techniques. The results, based on the comparison of MSE, MAE, PSNR, SSIM, and runtime, show that grey wolf optimization can generate good quality images, better than most of the compared methods.</div></div>","PeriodicalId":50633,"journal":{"name":"Computer Vision and Image Understanding","volume":"265 ","pages":"Article 104659"},"PeriodicalIF":3.5,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146191771","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Enhanced local homogenization and reconstruction network for few-shot fine-grained image classification","authors":"Meiyin Hu ,&nbsp;Huan Wan ,&nbsp;Hui Wang ,&nbsp;Jianfeng Xu ,&nbsp;Xin Wei","doi":"10.1016/j.cviu.2026.104686","DOIUrl":"10.1016/j.cviu.2026.104686","url":null,"abstract":"<div><div>Few-shot fine-grained image classification is a challenging task as it requires the ability to detect minor variations across subclasses. Metric-based methods are some of the most popular methods for dealing with this issue, but they have the problems of spatial information loss and local feature misalignment. Feature reconstruction-based methods can partially mitigate these two problems and exhibit substantial potential for fine-grained image classification. However, we found and verified that feature reconstruction-based methods have two unresolved difficulties, including inadequate extraction of discriminative local information and insufficient fitting capability when reconstructing numerous support set features with limited query set features. These difficulties are key obstacles to further improving the performance of few-shot fine-grained image classification. Therefore, we propose the enhanced local homogenization and reconstruction network (ELHRN) for few-shot fine-grained image classification. The proposed method includes three main modules: the local homogenization and distinction module (HDM) to learn more subtle discriminative local features; the double-layer cross-reconstruction module (DCM) to increase the hierarchy and complexity of feature reconstruction, effectively enhancing feature diversity; and the branch weighting module (BWM) to adjust the weights of mutual reconstruction between the support set and query set, thereby mitigating the issue of insufficient fitting capability when reconstructing numerous features with a limited number of features. Extensive experiments are conducted on five benchmark fine-grained datasets, and the results demonstrate that ELHRN outperforms state-of-the-art methods. The code is available at <span><span>https://github.com/sausage0611/ELHRN</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50633,"journal":{"name":"Computer Vision and Image Understanding","volume":"265 ","pages":"Article 104686"},"PeriodicalIF":3.5,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146191776","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Slope-Track: Multiple Object Tracking on Ski Slopes","authors":"M’Saydez Campbell ,&nbsp;Christophe Ducottet ,&nbsp;Damien Muselet ,&nbsp;Rémi Emonet","doi":"10.1016/j.cviu.2026.104663","DOIUrl":"10.1016/j.cviu.2026.104663","url":null,"abstract":"<div><div>In this paper, we introduce Slope-Track. Slope-Track is a novel multiple object tracking (MOT) dataset designed to reflect the complexities of real ski slope environments. The dataset has over 96,000 frames collected from 10 different ski resorts under various weather and visibility conditions. Slope-Track addresses significant challenges in slope monitoring, including small object sizes, occlusions, fast and irregular motion, and low appearance consistency. It is densely annotated with bounding boxes and object identities, facilitating the evaluation of detection and tracking algorithms. We analyze the dataset’s characteristics comparing it to the existing MOT datasets. The results demonstrate that Slope-Track encapsulates a combination of challenges found in other datasets. Additionally, we benchmark a range of existing tracking algorithms and propose a new module that improves motion-based association by dealing with the specific shape of trajectories along ski slopes. Our results demonstrate that incorporating appearance features can have a mixed impact, depending on how they are used within each tracking algorithm. In contrast, motion-based methods and spatial association strategies show more reliable performance. Overall, we provide a challenging benchmark for evaluating and improving multi-object tracking systems in real-world outdoor environments. The dataset and code can be found at <span><span>https://slopetrack.github.io/</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50633,"journal":{"name":"Computer Vision and Image Understanding","volume":"264 ","pages":"Article 104663"},"PeriodicalIF":3.5,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146078310","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"UAVDet: A CNN–Mamba hybrid network for efficient small object detection in UAV imagery","authors":"Yiming Yang,&nbsp;Feng Guo,&nbsp;Pei Niu","doi":"10.1016/j.cviu.2026.104637","DOIUrl":"10.1016/j.cviu.2026.104637","url":null,"abstract":"<div><div>Real-time object detection is pivotal in traffic-related Unmanned Aerial Vehicles (UAV) applications. However, UAV imagery presents significant challenges due to the predominance of small objects and complex backgrounds. Traditional backbones generally perform aggressive early-stage downsampling, causing the loss of fine-grained features. To address these issues, we propose UAVDet, a real-time detection model that combines Convolutional Neural Network (CNN) and Mamba architectures. First, we revisit the conventional backbone design by reconfiguring its depth and width, with a focus on preserving fine-grained details crucial for small object detection. Second, we propose the Cross Stage Partial Mamba (CSPMB) module, which integrates the Mamba structure into the CNN framework to enhance global feature representation and improve robustness against complex background interference. Third, we design Tiny-focused Feature Pyramid Network (TFPN) by rebalancing the feature fusion flow and replacing the large-object detection head with a tiny-object detection head, which significantly improves the perception of small objects. Comprehensive experiments on the VisDrone dataset show that our method improves AP and AP<span><math><msub><mrow></mrow><mrow><mi>S</mi></mrow></msub></math></span> by 4.5% and 5.0%, respectively, while reducing parameters by 84.9% compared to the baseline. It also reaches 53 FPS on an RTX 4090, exceeding the 30 FPS real-time threshold. Additional evaluations on UAVDT and DroneVehicle further verify the method’s robust generalization. These results indicate the effectiveness of the developed method in UAV image detection.</div></div>","PeriodicalId":50633,"journal":{"name":"Computer Vision and Image Understanding","volume":"264 ","pages":"Article 104637"},"PeriodicalIF":3.5,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145928068","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Beyond familiar landscapes: Exploring the limits of relative pose regressors in new environments","authors":"Ofer Idan,&nbsp;Yoli Shavit,&nbsp;Yosi Keller","doi":"10.1016/j.cviu.2025.104629","DOIUrl":"10.1016/j.cviu.2025.104629","url":null,"abstract":"<div><div>Relative pose regressors (RPRs) determine the pose of a query image by estimating its relative translation and rotation to a reference pose-labeled camera. Unlike other regression-based localization techniques confined to a scene’s absolute parameters, RPRs learn residuals, making them adaptable to new environments. However, RPRs have exhibited limited generalization to scenes not utilized during training (“unseen scenes”). In this work, we explore the ability of RPRs to localize in unseen scenes and propose algorithmic modifications to enhance their generalization. These modifications include attention-based aggregation of coarse feature maps, dynamic adaptation of model weights, and geometry-aware optimization. Our proposed approach improves the localization accuracy of RPRs in unseen scenes by a notable margin across multiple indoor and outdoor benchmarks and under various conditions while maintaining comparable performance in scenes used during training. We assess the contribution of each component through ablation studies and further analyze the uncertainty of our model in unseen scenes. Our Code and pre-trained models are available at <span><span>https://github.com/yolish/relformer</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50633,"journal":{"name":"Computer Vision and Image Understanding","volume":"264 ","pages":"Article 104629"},"PeriodicalIF":3.5,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145928066","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"RGB-D and IMU-based staircase quantification for assistive navigation using step estimation for exoskeleton support","authors":"Edgar R. Guzman ,&nbsp;Letizia Gionfrida ,&nbsp;Robert D. Howe","doi":"10.1016/j.cviu.2025.104621","DOIUrl":"10.1016/j.cviu.2025.104621","url":null,"abstract":"<div><div>This paper introduces a vision-based environment quantification pipeline designed to tailor the assistance provided by lower limb assistive devices during the transition from level walking to stair navigation. The framework consists of three components: staircase detection, transitional step prediction, and staircase dimension estimation. These components utilize an RGB-D camera worn on the chest and an Inertial Measurement Unit (IMU) worn at the hip. To detect ascending stairs, we employed a YOLOv3 model applied to continuous recordings, achieving an average accuracy of 98.1%. For descending stair detection, an edge detection algorithm was used, resulting in a pixel-wise edge localization accuracy of 89.1%. To estimate user locomotion speed and footfall, the IMU was positioned on the participant’s left waist, and the RGB-D camera was mounted at chest level. This setup accurately captured step lengths with an average accuracy of 94.4% across all participants and trials, enabling precise determination of the number of steps leading up to the transitional step on the staircase. As a result, the system accurately predicted the number of steps and localized the final footfall with an average error of <span><math><mrow><mn>5</mn><mo>.</mo><mn>77</mn><mspace></mspace><mtext>cm</mtext></mrow></math></span>, measured as the distance between the predicted and actual placement of the final foot relative to the target destination. Finally, to capture the dimensions of the staircase’s tread depth and riser height, an algorithm analyzing point cloud data was applied when the user was in close proximity to the stairs. This yielded mean absolute errors of <span><math><mrow><mn>1</mn><mo>.</mo><mn>20</mn><mo>±</mo><mn>0</mn><mo>.</mo><mn>49</mn><mspace></mspace><mtext>cm</mtext></mrow></math></span> in height and <span><math><mrow><mn>1</mn><mo>.</mo><mn>35</mn><mo>±</mo><mn>0</mn><mo>.</mo><mn>45</mn><mspace></mspace><mtext>cm</mtext></mrow></math></span> in depth for ascending stairs, and <span><math><mrow><mn>1</mn><mo>.</mo><mn>28</mn><mo>±</mo><mn>0</mn><mo>.</mo><mn>55</mn><mspace></mspace><mtext>cm</mtext></mrow></math></span> in height and <span><math><mrow><mn>1</mn><mo>.</mo><mn>47</mn><mo>±</mo><mn>0</mn><mo>.</mo><mn>65</mn><mspace></mspace><mtext>cm</mtext></mrow></math></span> in depth for descending stairs. Our proposed approach lays the groundwork for optimizing control strategies in exoskeleton technologies by integrating environmental sensing with human locomotion analysis. These results demonstrate the feasibility and effectiveness of our system, promising enhanced user experiences and improved functionality in real-world scenarios.</div></div>","PeriodicalId":50633,"journal":{"name":"Computer Vision and Image Understanding","volume":"264 ","pages":"Article 104621"},"PeriodicalIF":3.5,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145847576","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Body shape diversity in the training data and consequences on motion generation","authors":"Hugo Rodet,&nbsp;Lama Séoud","doi":"10.1016/j.cviu.2025.104632","DOIUrl":"10.1016/j.cviu.2025.104632","url":null,"abstract":"<div><div>Describing human movement is key to many applications, ranging from medicine to 3D animation. Morphology is an important factor influencing how people move, but as of yet it is seldom accounted for in human-centric tasks like motion generation. In this study, we first assess the diversity of body shapes in real human motion datasets, then demonstrate the benefits of morphology-aware motion generation. We reveal biases in the data regarding body shape, in particular for body fat and gender representation. Considering the incompleteness of even the largest motion-capture datasets, proving quantitatively that morphology influences motion is difficult using existing tools: we thus propose a new metric relying on 3D body mesh self-collision, and use it to demonstrate that individuals with varied body mass indices also differ in their movements. One consequence is that generic, morphology-agnostic generated poses tend to be unsuitable for the body models they are used with, and we show that it tends to increase self-collision artifacts. Building upon these results, we show that morphology-aware motion generation reduces mesh self-collision artifacts despite not being trained for it explicitly, even when using a common backbone and a naive conditioning strategy. Morphology-aware generation can also be seamlessly integrated to most pose and motion generation architectures with little-to-no extra computational cost and without compromising generation diversity of realism.</div></div>","PeriodicalId":50633,"journal":{"name":"Computer Vision and Image Understanding","volume":"264 ","pages":"Article 104632"},"PeriodicalIF":3.5,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145978914","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"SpinVision: An end-to-end volleyball spin estimation with Siamese-based deep classification","authors":"Shreya Bansal ,&nbsp;Anterpreet Kaur Bedi ,&nbsp;Pratibha Kumari ,&nbsp;Rishi Kumar Soni ,&nbsp;Narayanan C. Krishnan ,&nbsp;Mukesh Saini","doi":"10.1016/j.cviu.2025.104628","DOIUrl":"10.1016/j.cviu.2025.104628","url":null,"abstract":"<div><div>Accurate spin estimation is a very crucial process in detailing ball dynamics, conducting trainings and analyzing performance in different sports such as volleyball. Traditional methods usually rely on geometric assumptions, handcrafted features, or marker based estimation, which leads to their limited adaptability to real-world problems. In this paper, we propose a novel spin estimation framework, namely SpinVision, considering it as a soft-classification problem. The deep learning model employs Gaussian soft labels and Kullback–Leibler Divergence (KLD) loss. Further, it employs fusion methods alongside squeeze-and-excitation blocks and residual connections, which helps in achieving distinctive representations without the support of external markers or registration procedures. Also, inclusion of transfer learning helps generalizing the model effectively to real-world problems, such as estimating the spin of a volleyball. When compared with the hard-classification or regression-based methods, the proposed model results in more reliable and smooth predictions, thus highlighting it as more accurate, robust, and practical solution for spin prediction in sports analytics and related applications.</div></div>","PeriodicalId":50633,"journal":{"name":"Computer Vision and Image Understanding","volume":"264 ","pages":"Article 104628"},"PeriodicalIF":3.5,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145886185","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}