检索结果-内蒙古大学图书馆

LucIE: Language-guided local image editing for fashion images

Computational Visual Media 2025年第1期11卷 179-194页

作者： Huanglu Wen Shaodi You Ying Fu School of Computer Science and Technology Beijing Institute of TechnologyBeijingChina Computer Vision Research Group in the Institute of Informatics University of AmsterdamAmsterdamthe Netherlands

Language-guided fashion image editing is challenging,as fashion image editing is local and requires high precision,while natural language cannot provide precise visual information for *** this paper,we propose LucIE,a novel unsupervised language-guided local image editing method for fashion *** adopts and modifies recent text-to-image synthesis network,DF-GAN,as its ***,the synthesis backbone often changes the global structure of the input image,making local image editing *** increase structural consistency between input and edited images,we propose Content-Preserving Fusion Module(CPFM).Different from existing fusion modules,CPFM prevents iterative refinement on visual feature maps and accumulates additive modifications on RGB *** achieves local image editing explicitly with language-guided image segmentation and maskguided image blending while only using image and text *** on the DeepFashion dataset shows that LucIE achieves state-of-the-art *** with previous methods,images generated by LucIE also exhibit fewer *** provide visualizations and perform ablation studies to validate LucIE and the *** also demonstrate and analyze limitations of LucIE,to provide a better understanding of LucIE.

关键词： deep learning language-guided image editing local image editing content preservation fashion images

来源：评论

学校读者我要写书评

暂无评论

Patch Attention Excitation Based vision Transformer for Small-Sized Datasets

Patch Attention Excitation Based Vision Transformer for Smal...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Verma, Akash Dubey, Shiv Ram Singh, Satish Kumar Computer Vision and Biometrics Lab Indian Institute of Information Technology Allahabad India

ISBN: (纸本)9798350368741

vision Transformers have proven their mettle across a variety of computer vision problems, however, their reliance on pretraining with very large-scale datasets such as JFT-300M is also no secret, as large amounts of data is very conductive to effective feature learning. In this paper, however, we propose a novel vision Transformer architecture PAEViT that aims to effectively learn generalized features from small-sized datasets, usually having only a few hundred images per class at most. By refining the attention scores based on patch-level interactions and modulating it to enhance the trained model's ability to focus more on task relevant patches, PAEViT is able to significantly improve upon the performance of the regular ViT model, as well as other variants of the same, when the model is being trained solely on small-sized datasets. In data-constrained situations and visual recognition tasks that do not conform well with the existing large-scale datasets, PAEViT can be used to create effective and scalable solutions with all the features and attention scores being based only on relevant data. Our code is publicly available at https://***/AkashVermaIN/PAEViT. © 2025 IEEE.

关键词： Attention Mechanisms Data Efficiency Patch Attention vision Transformers

来源：评论

学校读者我要写书评

暂无评论

TSC:Efficient FRB Signal Search by a Two-stage Cascade Deep Learning Model on FAST

引用

Research in Astronomy and Astrophysics 2025年第3期25卷 60-69页

作者： Ronghuan Yan Junlin Li Weixin Tian Nyasha Mkwanda Hubei Key Laboratory of Intelligent Vision Based Monitoring for Hydroelectric Engineering China Three Gorges University College of Computer and Information Technology China Three Gorges University

Fast Radio Bursts(FRBs) have emerged as one of the most intriguing and enigmatic phenomena in the field of radio astronomy. The key of current related research is to obtain enough FRB signals. computer-aided search is necessary for that task. Considering the scarcity of FRB signals and massive observation data, the main challenge is about searching speed, accuracy and recall. in this paper, we propose a new FRB search method based on Commensal Radio Astronomy FAST Survey(CRAFTS) data. The CRAFTS drift survey data provide extensive sky coverage and high sensitivity, which significantly enhance the probability of detecting transient signals like FRBs. The search process is separated into two stages on the knowledge of the FRB signal with the structural isomorphism, while a different deep learning model is adopted in each stage. To evaluate the proposed method,FRB signal data sets based on FAST observation data are developed combining simulation FRB signals and real FRB signals. Compared with the benchmark method, the proposed method F-score achieved 0.951, and the associated recall achieved 0.936. The method has been applied to search for FRB signals in raw FAST data. The code and data sets used in the paper are available at ***/aoxipo.

关键词： techniques: high angular resolution techniques: image processing techniques: interferometric

来源：评论

学校读者我要写书评

暂无评论

Real-Time Multi-object Tracking Using YOLOv8 and SORT on a SoC FPGA 21st

Real-Time Multi-object Tracking Using YOLOv8 and SORT on a...

引用

21st International Symposium on Applied Reconfigurable Computing, ARC 2025

作者： Danilowicz, Michal Kryjak, Tomasz Embedded Vision Systems Group Computer Vision Laboratory Department of Automatic Control and Robotics AGH University of Science and Technology Krakow Poland

ISBN: (纸本)9783031879944

Multi-object tracking (MOT) is one of the most important problems in computer vision and a key component of any vision-based perception system used in advanced autonomous mobile robotics. Therefore, its implementation on low-power and real-time embedded platforms is highly desirable. Modern MOT algorithms should be able to track objects of a given class (e.g. people or vehicles). In addition, the number of objects to be tracked is not known in advance, and they may appear and disappear at any time, as well as be obscured. For these reasons, the most popular and successful approaches have recently been based on the tracking paradigm. Therefore, the presence of a high quality object detector is essential, which in practice accounts for the vast majority of the computational and memory complexity of the whole MOT system. In this paper, we propose an FPGA (Field-Programmable Gate Array) implementation of an embedded MOT system based on a quantized YOLOv8 detector and the SORT (Simple Online Realtime Tracker) tracker. We use a modified version of the FINN framework to utilize external memory for model parameters and to support operations necessary required by YOLOv8. We discuss the evaluation of detection and tracking performance using the COCO and MOT15 datasets, where we achieve 0.21 mAP and 38.9 MOTA respectively. As the computational platform, we use an MPSoC system (Zynq UltraScale+ device from AMD/Xilinx) where the detector is deployed in reprogrammable logic and the tracking algorithm is implemented in the processor system. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： System-on-chip

来源：评论

学校读者我要写书评

暂无评论

SAda-Net: A Self-supervised Adaptive Stereo Estimation CNN For Remote Sensing Image Data 27th

SAda-Net: A Self-supervised Adaptive Stereo Estimation CNN F...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Hirner, Dominik Fraundorfer, Friedrich Institute of Computer Graphics and Vision Graz University of Technology Graz Austria Cologne Germany

ISBN: (纸本)9783031781919

Stereo estimation has made many advancements in recent years with the introduction of deep-learning. However the traditional supervised approach to deep-learning requires the creation of accurate and plentiful ground-truth data, which is expensive to create and not available in many situations. This is especially true for remote sensing applications, where there is an excess of available data without proper ground truth. To tackle this problem, we propose a self-supervised CNN with self-improving adaptive abilities. In the first iteration, the created disparity map is inaccurate and noisy. Leveraging the left-right consistency check, we get a sparse but more accurate disparity map which is used as an initial pseudo ground-truth. This pseudo ground-truth is then adapted and updated after every epoch in the training step of the network. We use the sum of inconsistent points in order to track the network convergence. The code for our method will be made available after acceptance at https://***/thedodo/SAda-Net. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Adjustable Visual Appearance for Generalizable Novel View Synthesis 4th

Adjustable Visual Appearance for Generalizable Novel View S...

引用

4th International Conference on Pattern Recognition and Artificial Intelligence, ICPRAI 2024

作者： Bengtson, Josef Nilsson, David Lin, Che-Tsung Büsching, Marcel Kahl, Fredrik Computer Vision Group Chalmers University of Technology Gothenburg Sweden KTH Royal Institute of Technology Stockholm Sweden

ISBN: (纸本)9789819787012

We present a generalizable novel view synthesis method which enables modifying the visual appearance of an observed scene so rendered views match a target weather or lighting condition, without any scene specific training or access to reference views at the target condition. Our method is based on a pretrained generalizable transformer architecture and is fine-tuned on synthetically generated scenes under different appearance conditions. This allows for rendering novel views in a consistent manner for 3D scenes that were not included in the training set, along with the ability to (i) modify their appearance to match the target condition and (ii) smoothly interpolate between different conditions. Experiments on real and synthetic scenes show that our method is able to generate 3D consistent renderings while making realistic appearance changes, including qualitative and quantitative comparisons. Please refer to our project page for video results: https://***. © The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： 3D modeling

来源：评论

学校读者我要写书评

暂无评论

PSTNet: A Progressive Sparse Transformer Network for Image Deraining 27th

PSTNet: A Progressive Sparse Transformer Network for Image ...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Shaik, Raj Ahamed Singh, Navjot Verriboina, Antony Shandilya, Debesh Kumar Computer Vision and Biometrics Lab Department of Information Technology Indian Institute of Information Technology Uttar Pradesh Allahabad India

ISBN: (纸本)9783031781247

Image deraining aims to transform a rainy input image into an image of high quality. Transformer-based techniques have demonstrated remarkable efficacy in image deraining because of their capacity to represent non-local information, a crucial element for high-quality image reconstruction. Our findings indicate that most transformers used for feature aggregation nowadays leverage all token similarities between query-key pairs. If the query tokens differ from the key tokens, the quality of the recovered image is compromised by the self-attention values derived from these tokens if these are considered during feature aggregation. For this purpose, we propose the Progressive Sparse Transformer Network (PSTNet), which progressively learns to restore degraded inputs by retaining the helpful self-attention information during feature aggregation and discarding the remaining values which obstruct the restoration. Transformer blocks help to capture interactions between distant pixels. Thorough experimental outcomes on widely used benchmarks show that the suggested approach performs better than most existing techniques. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Image quality

来源：评论

学校读者我要写书评

暂无评论

Multi-teacher Importance Preserving Knowledge Distillation for Early Violence Prediction 27th

Multi-teacher Importance Preserving Knowledge Distillation f...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Basak, Suvramalya Vaishy, Aditya Gautam, Anjali Computer Vision and Biometrics Lab Indian Institute of Information Technology Allahabad U.P. Prayagraj India

ISBN: (纸本)9783031781094

The real-world applicability of automated violence recognition systems has drawn much attention from researchers. The current techniques for recognizing violence are centered on creating efficient models that can predict violent events quickly and accurately in real-time. However, early violence prediction, which is crucial for real-time systems, is not considered in these methods. In this paper, we present an early violence prediction method that can accurately predict violent activities from partially observed video frames. We propose a two-stream architecture which employs our proposed efficient Squeeze-Excitation ShuffleNet (SESNet) model that effectively extracts spatial and temporal features. We leverage spatio-temporal and channel-wise squeeze and excitation to incorporate attention information into the ShuffleNet V2 architecture. To enable early violence recognition, we train our model in a teacher-student framework, where the teacher model trained on full-length videos distils privileged information to the student model, which has access to partial videos. For this purpose, we introduce a novel multi-teacher importance preservation learning methodology which can effectively distill important features from multiple teacher networks. We evaluate our approach on the challenging RWF-2000 public violence recognition dataset. Experimental results show that our teacher-student training framework performed well for early violence prediction. Additionally, our proposed model also outperforms several state-of-the-art violence recognition methods on full-length videos. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Advancing Handwritten Text Detection by Synthetic Text 27th

Advancing Handwritten Text Detection by Synthetic Text

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Muth, Markus Peer, Marco Kleber, Florian Sablatnig, Robert Computer Vision Lab Institute of Visual Computing and Human-Centered Technology TU Wien Wien1040 Austria

ISBN: (纸本)9783031784941

In this paper, the usability of synthetic handwritten text to improve machine learning models is examined for the domain of handwritten text detection. We generate synthetic handwritten text by using an existing model based on a style conditioned GAN, and add those texts to scanned documents to mimic handwritten annotations. Object detection models (YOLOv5 and YOLOv8) are trained using synthetic data as a baseline to distinguish handwritten text from remaining content. We study different granularity labels (word-, line- and paragraph-level) and model sizes in our evaluation and show that applying those models to real data results in a mAP@50 of 0.88 and a pixel-level F1@50 of 0.96 for the CVL dataset, and a mAP@50 of 0.72 and F1@50 of 0.89 for SCAN, a custom dataset, created by adding real handwritten annotations to a scientific paper. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

DLCR: A Generative Data Expansion Framework via Diffusion for Clothes-Changing Person Re-Id

DLCR: A Generative Data Expansion Framework via Diffusion fo...

引用

2025 IEEE/CVF Winter Conference on Applications of computer vision, WACV 2025

作者： Siddiqui, Nyle Croitoru, Florinel Alin Nayak, Gaurav Kumar Ionescu, Radu Tudor Shah, Mubarak University of Central Florida Center for Research in Computer Vision United States University of Bucharest Romania Indian Institute of Technology Roorkee India

ISBN: (纸本)9798331510831

With the recent exhibited strength of generative diffusion models, an open research question is if images generated by these models can be used to learn better visual representations. While this generative data expansion may suffice for easier visual tasks, we explore its efficacy on a more difficult discriminative task: clothes-changing person re-identification (CC-ReID). CC-ReID aims to match people appearing in non-overlapping cameras, even when they change their clothes across cameras. Not only that current CC-ReID models are constrained by the limited diversity of clothing in current CC-ReID datasets, but generating additional data that retains important personal features for accurate identification is a current challenge. To address this issue we propose DLCR, a novel data expansion frame-work that leverages pretrained diffusion and large language models (LLMs) to accurately generate diverse images of in-dividuals in varied attire. We generate additional data for five benchmark CC-ReID datasets (PRCC, CCVID, LaST, VC-Clothes, and LTCC) and increase their clothing diversity by 10 x, totaling over 2.1M generated images. DLCR employs diffusion-based text-guided inpainting, conditioned on clothing prompts constructed using LLMs, to generate synthetic data that only modifies a subject's clothes, while preserving their personally identifiable features. With this massive increase in data, we introduce two novel strategies - progressive learning and test-time prediction refinement - that reduce training time and boost CC-ReID performance. We validate our method through extensive ablations and experiments, showing massive improvements when training previous CC-ReID methods on our generated data. On the PRCC dataset, we obtain a large top-1 accuracy improvement of 11.3% by training CAL, a state-of-the-art (SOTA) method, with DLCR-generated data. We publicly release our code and generated data for each dataset here: https://***/CroitoruAlin/dlcr. © 2025 IEEE.

关键词： Interdiffusion (solids)

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：