检索结果-内蒙古大学图书馆

Adaptive and Collaborative Multi-scale Alignment for Text-Based Person Search

学校读者我要写书评

暂无评论

Adaptive and Collaborative Multi-scale Alignment for Text-Ba...

IEEE Visual communications and image processing (VCIP)

作者： Xinxin Yang Renjie Pan Hua Yang Shanghai Key Lab of Digital Media Processing and Transmission Institute of Image Communication and Network Engineering Shanghai Jiao Tong University Shanghai China China MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University China

Text-to-image person search is challenging due to the cross-scale correspondences and information inequality between modalities. Specifically, images and text are complexly linked at different scales and images are usually more informative and complete than text. It is crucial to establish semantic correlations between modalities and focus on task-relevant information in images. In this paper, we propose a novel Adaptive and Collaborative Multi-scale Alignment network (ACMA) for text-based person search that learns semantically consistent and information-aligned multi-modal representations. Firstly, we introduce a novel joint embedding module that adaptively integrates features of different pixels and words, thereby extracting semantically consistent multi-modal features at different scales. Second, we design a cross-modal fusion feature-based auxiliary visual branch to guide the extraction of key visual features that are beneficial for cross-modal matching. Extensive experiments validate that ACMA outperforms the state-of-the-art method.

关键词：

Bacterial Foraging Based Edge Detection for Cell image Segmentation

学校读者我要写书评

暂无评论

Bacterial Foraging Based Edge Detection for Cell Image Segme...

Annual International Conference of the IEEE Engineering in Medicine and Biology Society

作者： Yongsheng Pan Tao Zhou Yong Xia the Shaanxi Key Lab of Speech & Image Information Processing (SAIIP) School of Computer Science Northwestern Polytechnical University Xi'an 710072 China the School of Science Ningxia Medical University Yinchuan 750004 China

ISBN: (纸本)9781424492695

Edge detection is the most popular and common choices for cell image segmentation, in which local searching strategies are commonly used. In spite of their computational efficiency, traditional edge detectors, however, may either produce discontinued edges or rely heavily on initializations. In this paper, we propose a bacterial foraging based edge detection (BFED) algorithm for cell image segmentation. We model the gradients of intensities as the nutrient concentration and propel bacteria to forage along nutrient-rich locations via mimicking the behavior of Escherichia coli, including the chemotaxis, swarming, reproduction, elimination and dispersal. As a nature-inspired evolutionary technique, this algorithm can identify the desired edges and mark them as the tracks of bacteria. We have evaluated the proposed algorithm against the Canny, SUSAN, Verma's and an active contour model (ACM) based edge detectors on both synthetic and real cell images. Our results suggest that the BFED algorithm can identify boundaries more effectively and provide more accurate cell image segmentation.

关键词： BFED SUSAN ACM

3D Cinemagraphy from a Single image

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Li, Xingyi Cao, Zhiguo Sun, Huiqiang Zhang, Jianming Xian, Ke Lin, Guosheng Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology China Adobe Research S-Lab Nanyang Technological University Singapore

We present 3D Cinemagraphy, a new technique that marries 2D image animation with 3D photography. Given a single still image as input, our goal is to generate a video that contains both visual content animation and camera motion. We empirically find that naively combining existing 2D image animation and 3D photography methods leads to obvious artifacts or inconsistent animation. Our key insight is that representing and animating the scene in 3D space offers a natural solution to this task. To this end, we first convert the input image into feature-based layered depth images using predicted depth values, followed by unprojecting them to a feature point cloud. To animate the scene, we perform motion estimation and lift the 2D motion into the 3D scene flow. Finally, to resolve the problem of hole emergence as points move forward, we propose to bidirectionally displace the point cloud as per the scene flow and synthesize novel views by separately projecting them into target image planes and blending the results. Extensive experiments demonstrate the effectiveness of our method. A user study is also conducted to validate the compelling rendering results of our method. Copyright © 2023, The Authors. All rights reserved.

关键词： Animation

Towards cross-granularity few-shot learning: Coarse-to-fine pseudo-labeling with visual-semantic meta-embedding

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Yang, Jinhai Yang, Hua Chen, Lin Institute of Image Communication and Network Engineering Shanghai Jiao Tong University China Shanghai Key Lab of Digital Media Processing and Transmission Shanghai China MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University China

Few-shot learning aims at rapidly adapting to novel categories with only a handful of samples at test time, which has been predominantly tackled with the idea of meta-learning. However, meta-learning approaches essentially learn across a variety of few-shot tasks and thus still require large-scale training data with fine-grained supervision to derive a generalized model, thereby involving prohibitive annotation cost. In this paper, we advance the few-shot classification paradigm towards a more challenging scenario, i.e., cross-granularity few-shot classification, where the model observes only coarse labels during training while is expected to perform fine-grained classification during testing. This task largely relieves the annotation cost since fine-grained labeling usually requires strong domain-specific expertise. To bridge the cross-granularity gap, we approximate the fine-grained data distribution by greedy clustering of each coarse-class into pseudo-fine-classes according to the similarity of image embeddings. We then propose a meta-embedder that jointly optimizes the visual- and semantic-discrimination, in both instance-wise and coarse class-wise, to obtain a good feature space for this coarse-to-fine pseudo-labeling process. Extensive experiments and ablation studies are conducted to demonstrate the effectiveness and robustness of our approach on three representative datasets. Copyright © 2020, The Authors. All rights reserved.

关键词： Embeddings

Intra-Guided Dual-Energy Material Decomposition Method for Dual-Source CBCT Systems 46

学校读者我要写书评

暂无评论

Intra-Guided Dual-Energy Material Decomposition Method for D...

46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2024

作者： Zhong, Xinyun Lyu, Tianling Wu, Zhan Gao, Wei Xi, Yan Zhao, Wei Zhu, Wentao Chen, Yang Zhejiang Lab Hangzhou China First-Imaging Tech. Shanghai China Beihang University Beijing China Southeast University School of Computer Science and Engineering Laboratory of Image Science and Technology Nanjing China Southeast University Jiangsu Provincial Joint International Research Laboratory of Medical Information Processing Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications Nanjing China

ISBN: (纸本)9798350371499

Dual-energy CBCT imaging plays a crucial role in advanced imaging applications due to its ability to quantify material components. Although there are multiple established systems for dual-energy imaging, they often come with high deployment costs. This study investigates the feasibility of dual-energy material decomposition on a less expensive dual-source CBCT system. Due to the specific geometry of dual-source CBCT, cone-beam (CB) artifacts seriously degrade the material decomposition quality when the direct inversion method is adopted. In this paper, a novel dual-source intra-guided material decomposition framework is proposed to suppress CB artifacts in the material maps. Firstly, a dual-source two-pass algorithm is developed for artifact pre-correction during image reconstruction. Then, the structure of small cone-angle regions from one X-ray source is utilized to guide cone beam artifact removal in large cone-angle regions from another source. Finally, direct matrix inverse material decomposition is applied to the filtered image. Extensive experiments have been conducted on the authentic human phantom and demonstrate that the proposed framework achieves excellent performance in cone beam artifact reduction compared to other methods, and significantly enhances the quality of the material maps. © 2024 IEEE.

关键词： image reconstruction

An Active Landing Recovery Method for Quadrotor UAV: Localization, Tracking and Buffering Landing

学校读者我要写书评

暂无评论

IFAC-PapersOnLine 2023年第2期56卷 3366-3372页

作者： Yongkang Xu Zhihua Chen Shoukun Wang Junzheng Wang National Key Lab of Autonomous Intelligent Unmanned Systems Beijing Institute of Technology Beijing CO 100081 P.R.China Key Laboratory of Jiangxi Province for Image Processing and Pattern Recognition and MOE Key Lab of Nondestructive Testing Technology School of Information Engineering Nanchang Hangkong University Nanchang CO 330063 P.R. China

This paper proposes a principle of fully autonomous ground mobile landing recovery of Unmanned Aerial Vehicles (UAV) for the problems of relatively fixed landing point, passive recovery, poor flexibility, and environmental adaptability, which mainly includes localization, landing point tracking, and buffering landing for quadrotor UAV. Firstly, aiming at the problem that it is difficult to accurately obtain the position of a UAV in dynamic mobile landing recovery, a target location method based on Asynchronous Multisensor Information Fusion(AMIF) and servo turntable focus tracking is proposed. Secondly, to achieve fast and high-precision tracking of UAVs, a tracking control strategy of an independently driven landing recovery system and a Stewart six-degree of freedom platform is proposed. Then, to solve the problems of large impact force and center of gravity instability in the landing process of UAV, a stationarity control algorithm based on model prediction and a compliance control algorithm based on adaptive variable impedance are designed to achieve active compliance control while adjusting the position and attitude of the receiving surface in real-time. Finally, a quadrotor unmanned landing and recovery experimental platform is built to verify the feasibility of the ground mobile landing and recovery strategy proposed in this paper and the effectiveness of the control algorithm.

关键词： Quadrotor UAV Mobile Autonomous recovery Target localization Falling point tracking Buffering landing

Transformer-based Lossless Compression of Aurora Spectral images: A Spatial-Temporal-Spectral Joint Approach

学校读者我要写书评

暂无评论

Transformer-based Lossless Compression of Aurora Spectral Im...

International Conference on Signal processing Proceedings (ICSP)

作者： Xinlong Cao Jiaojiao Li Yuanqing Li Jiapeng Yan Zhenxing Zheng School of Communications and Information Engineering & School of Artificial Intelligence Xi'an University of Posts & Telecommunications Xi'an China Xi’an Key Laboratory of Image Processing Technology and Applications for Public Security Xi'an China International Joint Research Center for Wireless Communication and Information Processing Technology of Shaanxi Province Xi'an China

ISBN: (数字)9798350387384

ISBN: (纸本)9798350387391

Aurora spectral image lossless compression has seen significant advancements in recent years. However, most compression algorithms are based on traditional image compression techniques, focusing solely on spectral and spatial correlations without considering temporal correlations. To further enhance compression performance, this paper proposes a Transformer-based point-by-point prediction algorithm for auroral spectral images, which simultaneously uses spatial, spectral and temporal contexts for prediction. Our prediction network consists of two parts: an encoder and a decoder. The encoder is composed of the encoding unit of the original Transformer and is used to extract features from spatial, spectral and temporal contexts. The decoder consists of fully connected layers and is used for prediction. Experimental results show that the average bitrate of this method is reduced by 0.179 bpp compared with the JPEG2000 algorithm, and the average bitrate is reduced by 0.054 bpp compared with the online DPCM algorithm.

关键词： Ion radiation effects image coding Correlation Signal processing algorithms Transformers Prediction algorithms Feature extraction Decoding Magnetosphere Compression algorithms

Fast Low-parameter Video Activity Localization in Collaborative Learning Environments

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Jatla, Venkatesh Teeparthi, Sravani Egala, Ugesh Pattichis, Sylvia Celedón Pattichis, Marios S. Image and Video Processing and Communications Lab Dept. of Electrical and Computer Engineering University of New Mexico AlbuquerqueNM87131 United States Department of Curriculum and Instruction The University of Texas at Austin AustinTX78712-1293 United States

Research on video activity detection has primarily focused on identifying well-defined human activities in short video segments. The majority of the research on video activity recognition is focused on the development of large parameter systems that require training on large video datasets. This paper develops a low-parameter, modular system with rapid inferencing capabilities that can be trained entirely on limited datasets without requiring transfer learning from large-parameter systems. The system can accurately detect and associate specific activities with the students who perform the activities in real-life classroom videos. Additionally, the paper develops an interactive web-based application to visualize human activity maps over long real-life classroom videos. Long-term video activity detection in real-life classroom videos present unique challenges, such as the need to detect multiple simultaneous activities, rapid transitions between activities, long-term occlusions, durations exceeding 15 minutes, and numerous individuals performing similar activities in the background. Moreover, subtle hand movements further complicate the need to differentiate between actual typing and writing activities as opposed to unrelated hand movements. The system processes the input videos using fast activity initializations and current methods for object detection to determine the location and the the person performing the activities. These regions are then processed through an optimal low-parameter dyadic 3D-CNN classifier to identify the activity. The proposed system processes 1 hour of video in 15 minutes for typing and 50 minutes for writing activities. The system uses several methods to optimize the inference pipeline. For each activity, the system determines an optimal low-parameter 3D CNN architecture selected from a family of low-parameter architectures. The input video is broken into smaller video regions that are transcoded at an optimized frame rate. For inference, a

关键词： Object detection

RGB-D based action recognition with light-weight 3D convolutional networks

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Zhang, Haokui Li, Ying Wang, Peng Liu, Yu Shen, Chunhua Shaanxi Provincial Key Lab of Speech and Image Information Processing School of Computer Science Northwestern Polytechnical University Xi’an710129 China School of Computer Science University of Adelaide AdelaideSA5005 Australia

Different from RGB videos, depth data in RGB-D videos provide key complementary information for tristimulus visual data which potentially could achieve accuracy improvement for action recognition. However, most of the existing action recognition models solely using RGB videos limit the performance capacity. Additionally, the state-of-the-art action recognition models, namely 3D convolutional neural networks (3D-CNNs) contain tremendous parameters suffering from computational inefficiency. In this paper, we propose a series of 3D lightweight architectures for action recognition based on RGB-D data. Compared with conventional 3D-CNN models, the proposed lightweight 3D-CNNs have considerably less parameters involving lower computation cost, while it results in favorable recognition performance. Experimental results on two public benchmark datasets show that our models can approximate or outperform the state-of-the-art approaches. Specifically, on the RGB+DNTU (NTU) dataset, we achieve 93.2% and 97.6% for cross-subject and cross-view measurement, and on the Northwestern-UCLA Multiview Action 3D (N-UCLA) dataset, we achieve 95.5% accuracy of cross-view. Copyright © 2018, The Authors. All rights reserved.

关键词： Convolution