检索结果-内蒙古大学图书馆

Enabling visual object detection With object Sounds via visual Modality Recalling Memory

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2025年第1期36卷 341-353页

作者： Kim, Jung Uk Ro, Yong Man Korea Adv Inst Sci & Technol KAIST Sch Elect Engn Image & Video Syst Lab Daejeon 34141 South Korea Kyung Hee Univ Dept Comp Sci & Engn Visual Artificial Intelligence Lab Yongin 17104 South Korea

When humans hear the sound of an object, they recall associated visual information and integrate the sound with recalled visual modality to detect the object. In this article, we present a novel sound-based object detector that mimics this process. We design a visual modality recalling (VMR) memory to recall information of a visual modality based on an audio modal input (i.e., sound). To achieve this goal, we propose a VMR loss and an audio-visual association loss to guide the VMR memory to memorize visual modal information by establishing associations between audio and visual modalities. With the visual modal information recalled through the VMR memory along with the original audio input, we perform audio-visual integration. In this step, we introduce an integrated feature contrastive loss that allows the integrated feature to be embedded as if it were encoded using both audio and visual modal inputs. This guidance enables our sound-based object detector to effectively perform visual object detection even when only sound is provided. We believe that our work is a cornerstone study that offers a new perspective to conventional object detection studies that solely rely on the visual modality. Comprehensive experimental results demonstrate the effectiveness of the proposed method with the VMR memory.

关键词： Memory network modality recalling object sound visual object detection

来源：评论

学校读者我要写书评

暂无评论

Dual-stage feature specialization network for robust visual object detection in autonomous vehicles

引用

Scientific Reports 2025年第1期15卷 1-12页

作者： Liu, Ze Wu, Junhua Cai, Yingfeng Wang, Hai Chen, Long Liu, Qingchao Automotive Engineering Research Institute Jiangsu University Jiangsu Zhenjiang 212013 China School of Automotive and Traffic Engineering Jiangsu University Jiangsu Zhenjiang 212013 China

Efficient feature representation is critical for accurate visual perception in autonomous vehicles. Existing two-stage object detection methods often suffer from feature interference between candidate region generation and classification regression tasks, leading to suboptimal performance in complex scenes. To address this, we propose a Dual-Stage Feature Specialization Network (DSFSN) that decouples feature extraction: MobileNetV3 is employed for lightweight candidate region generation, while ResNet-FPN enhances multi-scale feature fusion for precise classification. Extensive experiments on PASCAL VOC and MS COCO datasets demonstrate state-of-the-art performance, achieving 81.6% mAP (9.3% higher than Faster R-CNN) and 29.3% AP on MS COCO, with a 14.9% improvement in small object detection. Real-world tests under diverse conditions (e.g., rain, night) validate the robustness of our method for autonomous driving applications. This work provides a novel framework for balancing accuracy and efficiency in visual perception systems. © The Author(s) 2025.

关键词： Autonomous vehicle Complex environment perception Complex problem application Two-stage feature extraction visual object detection

来源：评论

学校读者我要写书评

暂无评论

visual object detection by Specifying the Scale and Rotation Transformations

Visual Object Detection by Specifying the Scale and Rotation...

引用

17th International Conference on Neural Information Processing

作者： Sato, Yasuomi D. Jitsev, Jenia von der Malsburg, Christoph Kyushu Inst Technol Dept Brain Sci & Engn Grad Sch Life Sci & Syst Engn Wakamatsu Ku 2-4 Hibikino Kitakyushu Fukuoka 8080196 Japan Goethe Univ Frankfurt Frankfurt Inst Adv Studies D-60438 Frankfurt Germany

ISBN: (纸本)9783642175336

We here propose a simple but highly potential algorithm to detect a model object's position on an input image by determining the initially unknown transformational states of the model object, in particular, size and 2D-rotation. In this algorithm, a single feature is extracted around or at the center of the input image through 2D-Gabor wavelet transformation, in order to find not only the most likely relative size and rotation to the model object, but also the most appropriate positional region on the input image for detecting the correct relative transformational states. We also show the reliable function on the face images of different persons, or of different appearance in the same person.

关键词： visual object detection Gabor Filter Decomposition Transformation Specific Similarities Feature Correspondence

来源：评论

学校读者我要写书评

暂无评论

Revisiting knowledge distillation for light-weight visual object detection

引用

TRANSACTIONS OF THE INSTITUTE OF MEASUREMENT AND CONTROL 2021年第13期43卷 2888-2898页

作者： Gao, Tianze Gao, Yunfeng Li, Yu Qin, Peiyuan Harbin Intitute Technol Harbin Peoples R China HIT Wuhu Robot Technol Res Inst Wuhu Peoples R China

An essential element for intelligent perception in mechatronic and robotic systems (M&RS) is the visual object detection algorithm. With the ever-increasing advance of artificial neural networks (ANN), researchers have proposed numerous ANN-based visual object detection methods that have proven to be effective. However, networks with cumbersome structures do not befit the real-time scenarios in M&RS, necessitating the techniques of model compression. In the paper, a novel approach to training light-weight visual object detection networks is developed by revisiting knowledge distillation. Traditional knowledge distillation methods are oriented towards image classification is not compatible with object detection. Therefore, a variant of knowledge distillation is developed and adapted to a state-of-the-art keypoint-based visual detection method. Two strategies named as positive sample retaining and early distribution softening are employed to yield a natural adaption. The mutual consistency between teacher model and student model is further promoted through a hint-based distillation. By extensive controlled experiments, the proposed method is testified to be effective in enhancing the light-weight network's performance by a large margin.

关键词： visual object detection artificial neural network knowledge distillation

来源：评论

学校读者我要写书评

暂无评论

Multiple-Kernel, Multiple-Instance Similarity Features for Efficient visual object detection

引用

IEEE TRANSACTIONS ON IMAGE PROCESSING 2013年第8期22卷 3050-3061页

作者： Sun, Chensheng Lam, Kin-Man Hong Kong Polytech Univ Dept Elect & Informat Engn Ctr Signal Proc Hong Kong Hong Kong Peoples R China

We propose to use the similarity between the sample instance and a number of exemplars as features in visual object detection. Concepts from multiple-kernel learning and multiple-instance learning are incorporated into our scheme at the feature level by properly calculating the similarity. The similarity between two instances can be measured by various metrics and by using the information from various sources, which mimics the use of multiple kernels for kernel machines. Pooling of the similarity values from multiple instances of an object part is introduced to cope with alignment inaccuracy between object instances. To deal with the high dimensionality of the multiple-kernel multiple-instance similarity feature, we propose a forward feature-selection technique and a coarse-to-fine learning scheme to find a set of good exemplars, hence we can produce an efficient classifier while maintaining a good performance. Both the feature and the learning technique have interesting properties. We demonstrate the performance of our method using both synthetic data and real-world visual object detection data sets.

关键词： Multiple instance multiple kernel similarity feature visual object detection

来源：评论

学校读者我要写书评

暂无评论

A Maximum Margin Segmentation Selection for visual object detection

A Maximum Margin Segmentation Selection for Visual Object De...

引用

2011 Fourth International Conference on Intelligent Computation Technology and Automation(2011年第四届智能计算技术与自动化国际会议 ICICTA 2011)

作者： Yang Yang Shanping Li Dept. of Computer Science Zhejiang University Hangzhou 310027 China

visual object detection is to predict the bounding box and the label of each object from the target classes in realistic scenes. Previous detection algorithms focus on training models to fit presegmented local patches. However, the patches themselves are not always meaningful due to the unsupervised segmentation mistakes. In this paper, a maximum margin method is proposed to get the optimal patches and the corresponding models simultaneously. The learning task is formulated as a quadratic programming (QP) problem and implemented in its dual form. When testing, we compute multiple segmentations of each image and select one segmentation with the maximum margin to predict their labels. We evaluate the detection performance of our algorithm on Pascal VOC2007 challenge data set and show some improved results with other detection algorithms.

关键词： visual object detection classification maximum margin method

来源：评论

学校读者我要写书评

暂无评论

ReTrackVLM: Transformer-Enhanced Multi-object Tracking with Cross-Modal Embeddings and Zero-Shot Re-Identification Integration

引用

APPLIED SCIENCES-BASEL 2025年第4期15卷 1907-1907页

作者： Bayraktar, Ertugrul Yildiz Tech Univ Dept Mechatron Engn TR-34349 Istanbul Turkiye

Multi-object tracking (MOT) is an important task in computer vision, particularly in complex, dynamic environments with crowded scenes and frequent occlusions. Traditional tracking methods often suffer from identity switches (IDSws) and fragmented tracks (FMs), which limits their ability to maintain consistent object trajectories. In this paper, we present a novel framework, called ReTrackVLM, that integrates multimodal embedding from a visual language model (VLM) with a zero-shot re-identification (ReID) module to enhance tracking accuracy and robustness. ReTrackVLM leverages the rich semantic information from VLMs to distinguish objects more effectively, even under challenging conditions, while the zero-shot ReID mechanism enables robust identity matching without additional training. The system also includes a motion prediction module, powered by Kalman filtering, to handle object occlusions and abrupt movements. We evaluated ReTrackVLM on several widely used MOT benchmarks, including MOT15, MOT16, MOT17, MOT20, and DanceTrack. Our approach achieves state-of-the-art results, with improvements of 1.5% MOTA and a reduction of 10. 3% in IDSws compared to existing methods. ReTrackVLM also excels in tracking precision, recording a 91.7% precision on MOT17. However, in extremely dense scenes, the framework faces challenges with slight increases in IDSws. Despite the computational overhead of using VLMs, ReTrackVLM demonstrates the ability to track objects effectively in diverse scenarios.

关键词： multimodal embeddings transformer-based multi-object tracking visual language models visual object detection zero-shot re-identification

来源：评论

学校读者我要写书评

暂无评论

MFP-DETR: Marine UAV target detection based on multi-scale fuzzy perception

引用

NEUROCOMPUTING 2025年 635卷

作者： Zou, Ting Ge, Quanbo Huang, Yanjun Shanghai Maritime Univ Shanghai 200000 Peoples R China Nanjing Univ Informat Sci & Technol Collaborat Innovat Ctr Big Data Syst Lab Nanjing 210044 Jiangsu Peoples R China Tongji Univ Shanghai 200120 Jiading Peoples R China

An end-to-end object detection algorithm based on multi-scale fuzzy perception and feature enhancement, MFP-DETR, is proposed to solve the problem of image blur caused by the fast motion of Unmanned Aerial Vehicle (UAV) and pixel limitation of cameras in Unmanned Surface Vehicle (USV) images. Firstly, a learnable image mapping network - LPNet is designed to improve the representation of the target region and the quality of the input image. Secondly, the features of S3 and S4 and the features of S5 in the backbone Network were extracted, and they were input into the Squeeze and Excitation Network V2 (SENetV2) feature fusion module for feature fusion to enhance the detection ability of small targets. Finally, replace the Attention on the Intermediate Feature Interaction (AIFI) module in the Real-Time detection TRansformer (RT-DETR) with a Contextual Transformer(CoT) module. Context information is fully used to guide the learning of dynamic attention matrix and enhance the ability of global visual representation, to improve the accuracy of the model for different targets. The experimental results show that this method can enhance the fuzzy image effectively and detect the UAV accurately under background interference in the natural environment.

关键词： visual object detection Motion blur Image enhancement Transformer

来源：评论

学校读者我要写书评

暂无评论

Domain Contrast for Domain Adaptive object detection

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2022年第12期32卷 8227-8237页

作者： Liu, Feng Zhang, Xiaosong Wan, Fang Ji, Xiangyang Ye, Qixiang Univ Chinese Acad Sci Sch Microelect Beijing 100049 Peoples R China Univ Chinese Acad Sci Sch Elect Elect & Commun Engn Beijing 100049 Peoples R China Univ Chinese Acad Sci Sch Comp Sci & Technol Beijing 100049 Peoples R China Tsinghua Univ Dept Automat Beijing 100084 Peoples R China

Despite of the substantial progress of visual object detection, models trained in one video domain often fail to generalize well to others due to the change of camera configurations, lighting conditions, and object person views. In this paper, we present Domain Contrast (DC), a simple yet effective approach inspired by contrastive learning for training domain adaptive detectors. DC is deduced from the error bound minimization perspective of a transferred model, and is implemented with cross-domain contrast loss which is plug-and-play. By minimizing cross-domain contrast loss, DC transfers detectors across domains while naturally alleviating the class imbalance issue in the target domain. DC can be applied at either image level or region level, consistently improving detectors' discriminability while maintaining the transferability. Extensive experiments on commonly used benchmarks show that DC improves the baseline and state-of-the-art by significant margins, while demonstrating great potential for large domain divergence.

关键词： Detectors Adaptation models object detection Feature extraction Minimization Training Task analysis Domain adaptation visual object detection contrastive learning transfer learning

来源：评论

学校读者我要写书评

暂无评论

Intelligent Hoisting with Car-Like Mobile Robots

引用

JOURNAL OF CONSTRUCTION ENGINEERING AND MANAGEMENT 2020年第12期146卷

作者： Li, Heng Luo, Xiaochun Skitmore, Martin Hong Kong Polytech Univ Dept Bldg & Real Estate Hong Kong Peoples R China Queensland Univ Technol Sch Built Environm 2 George St Brisbane Qld 4001 Australia

The construction industry's traditional hoisting system always needs workers to complete the tasks involved, with concomitant extra labor costs and attention to the workers' safety. This paper describes the development of an intelligent hoisting system to optimize the hoisting process, involving the application of robotic cars and vision-based recognition. In the design of the hoisting system, electric hooks were used and maneuvered by a robotic car while the vision-based recognition system-based on capturing images by the camera-arranges the robotic motion. The Yolo v2 recognition algorithm was used, which provides fast and efficient vision-based recognition. More than 30 trials in an experimental prefabrication factory indicated that the system had a significant success rate of approximately 92.5% (3.7/4)-the proportion of hooks successfully grappling the hoist points-verifying the feasibility of the system. The primary contribution of this paper is in the development and demonstration of an intelligent hoisting system to optimize the hoisting process, involving the application of robotic cars and vision-based recognition, thus furthering the application of computer vision techniques and robotics to construction work. (C) 2020 American Society of Civil Engineers.

关键词： Intelligent hoisting Car-like mobile robots visual object detection Deep learning

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：