检索结果-南通市图书馆

Dual Frequency Transformer for Efficient SDR-to-HDR Translation

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Machine Intelligence Research 2024年第3期21卷 538-548页

作者： Gang Xu Qibin Hou ming-ming cheng Tianjin Media Computing Center College of Computer ScienceNankai UniversityTianjin300000China

The SDR-to-HDR translation technique can convert the abundant standard-dynamic-range (SDR) media resources to high-dynamic-range (HDR) ones, which can represent high-contrast scenes, providing more realistic visual experiences. While recent vision Transformers have achieved promising performance in many low-level vision tasks, there are few works attempting to leverage Transformers for SDR-to-HDR translation. In this paper, we are among the first to investigate the performance of Transformers for SDR-to-HDR translation. We find that directly using the self-attention mechanism may involve artifacts in the results due to the inappropriate way to model long-range dependencies between the low-frequency and high-frequency components. Taking this into account, we advance the self-attention mechanism and present a dual frequency attention (DFA), which leverages the self-attention mechanism to separately encode the low-frequency structural information and high-frequency detail information. Based on the proposed DFA, we further design a multi-scale feature fusion network, named dual frequency Transformer (DFT), for efficient SDR-to-HDR translation. Extensive experiments on the HDRTV1K dataset demonstrate that our DFT can achieve better quantitative and qualitative performance than the recent state-of-the-art methods. The code of our DFT is made publicly available at https://***/CS-GangXu/DFT.

关键词： Standard-dynamic-range to high-dynamic-range(SDR-to-HDR)translation Transformer dual frequency attention(DFA) frequency-aware feature decomposition efficient model

Visual attention network

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computational Visual Media 2023年第4期9卷 733-752页

作者： Meng-Hao Guo cheng-Ze Lu Zheng-Ning Liu ming-ming cheng Shi-Min Hu Department of Computer Science Tsinghua UniversityBeijingChina Nankai University TianjinChina Fitten Tech BeijingChina

While originally designed for natural language processing tasks,the self-attention mechanism has recently taken various computer vision areas by ***,the 2D nature of images brings three challenges for applying self-attention in computer vision:(1)treating images as 1D sequences neglects their 2D structures;(2)the quadratic complexity is too expensive for high-resolution images;(3)it only captures spatial adaptability but ignores channel *** this paper,we propose a novel linear attention named large kernel attention(LKA)to enable self-adaptive and long-range correlations in self-attention while avoiding its ***,we present a neural network based on LKA,namely Visual Attention Network(VAN).While extremely simple,VAN achieves comparable results with similar size convolutional neural networks(CNNs)and vision transformers(ViTs)in various tasks,including image classification,object detection,semantic segmentation,panoptic segmentation,pose estimation,*** example,VAN-B6 achieves 87.8%accuracy on ImageNet benchmark,and sets new state-of-the-art performance(58.2%PQ)for panoptic ***,VAN-B2 surpasses Swin-T 4%mloU(50.1%vs.46.1%)for semantic segmentation on ADE20K benchmark,2.6%AP(48.8%vs.46.2%)for object detection on COCO *** provides a novel method and a simple yet strong baseline for the *** code is available at https://***/Visual-Attention-Network.

关键词： vision backbone deep learning ConvNets attention

Geometry-Aware ICP for Scene Reconstruction from RGB-D Camera

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Computer Science & Technology 2019年第3期34卷 581-593页

作者： Bo Ren Jia-cheng Wu Ya-Lei Lv ming-ming cheng Shao-Ping Lu College of Computer Science Nankai UniversityTianjin 300350China

The Iterative Closest Point (ICP) scheme has been widely used for the registration of surfaces and point ***, when working on depth image sequences where there are large geometric planes with small (or even without) details,existing ICP algorithms are prone to tangential drifting and erroneous rotational estimations due to input device *** this paper, we propose a novel ICP algorithm that aims to overcome such drawbacks, and provides significantly stabler registration estimation for simultaneous localization and mapping (SLAM) tasks on RGB-D camera inputs. In our approach,the tangential drifting and the rotational estimation error are reduced by: 1) updating the conventional Euclidean distance term with the local geometry information, and 2) introducing a new camera stabilization term that prevents improper camera movement in the calculation. Our approach is simple, fast, effective, and is readily integratable with previous ICP algorithms. We test our new method with the TUM RGB-D SLAM dataset on state-of-the-art real-time 3D dense reconstruction platforms, i.e., ElasticFusion and Kintinuous. Experiments show that our new strategy outperforms all previous ones on various RGB-D data sequences under different combinations of registration systems and solutions.

关键词： ICP(iterative closest point) RGB-D tangential drifting rotational estimation covariance matrix

Salient object detection: A survey

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computational Visual Media 2019年第2期5卷 117-150页

作者： Ali Borji ming-ming cheng Qibin Hou Huaizu Jiang Jia Li MarkableAI New YorkUSA TKLNDST College of Computer ScienceNankai UniversityTianjinChina University of Massachusetts Amherst AmherstMAUSA State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and EngineeringBeihang UniversityBeijingChina

Detecting and segmenting salient objects from natural scenes, often referred to as salient object detection, has attracted great interest in computer vision. While many models have been proposed and several applications have emerged, a deep understanding of achievements and issues remains lacking. We aim to provide a comprehensive review of recent progress in salient object detection and situate this field among other closely related areas such as generic scene segmentation, object proposal generation, and saliency for fixation prediction. Covering 228 publications, we survey i) roots, key concepts, and tasks, ii) core techniques and main modeling trends, and iii) datasets and evaluation metrics for salient object detection. We also discuss open problems such as evaluation metrics and dataset bias in model performance, and suggest future research directions.

关键词： salient object detection saliency visual attention regions of interest

RGB-D salient object detection:A survey

在线全文

学校读者我要写书评

暂无评论

Computational Visual Media 2021年第1期7卷 37-69页

作者： Tao Zhou Deng-Ping Fan ming-ming cheng Jianbing Shen Ling Shao Inception Institute of Artificial Intelligence(IIAI) Abu DhabiUnited Arab Emirates

Salient object detection,which simulates human visual perception in locating the most significant object(s)in a scene,has been widely applied to various computer vision ***,the advent of depth sensors means that depth maps can easily be captured;this additional spatial information can boost the performance of salient object *** various RGB-D based salient object detection models with promising performance have been proposed over the past several years,an in-depth understanding of these models and the challenges in this field remains *** this paper,we provide a comprehensive survey of RGBD based salient object detection models from various perspectives,and review related benchmark datasets in ***,as light fields can also provide depth maps,we review salient object detection models and popular benchmark datasets from this domain ***,to investigate the ability of existing models to detect salient objects,we have carried out a comprehensive attribute-based evaluation of several representative RGB-D based salient object detection ***,we discuss several challenges and open directions of RGB-D based salient object detection for future *** collected models,benchmark datasets,datasets constructed for attribute-based evaluation,and related code are publicly available at https://***/taozh2017/RGBD-SODsurvey.

关键词： RGB-D saliency light fields benchmarks

Joint salient object detection and existence prediction

在线全文

学校读者我要写书评

暂无评论

Frontiers of Computer Science 2019年第4期13卷 778-788页

作者： Huaizu JIANG ming-ming cheng Shi-Jie LI Ali BORJI Jingdong WANG College of Information and Computer Sciences University of Massachusetts Amherst Amherst MA 01003 USA CCCE Nankai University Jinnan Campus Tianjin 300353 China Center for Research in Computer Vision University of Central Florida Orlando FL 32816 USA Microsoft Research Beijing 100080 China

Recent advances in supervised salient object detection modeling has resulted in significant performance improvements on benchmark datasets. However, most of the existing salient object detection models assume that at least one salient object exists in the input image. Such an assumption often leads to less appealing saliency maps on the background images with no salient object at all. Therefore, handling those cases can reduce the false positive rate of a model. In this paper, we propose a supervised learning approach for jointly addressing the salient object detection and existence prediction problems. Given a set of background-only images and images with salient objects, as well as their salient object annotations, we adopt the structural SVM framework and formulate the two problems jointly in a single integrated objective function: saliency labels of superpixels are involved in a classification term conditioned on the salient object existence variable, which in turn depends on both global image and regional saliency features and saliency labels assignments. The loss function also considers both image-level and regionlevel mis-classifications. Extensive evaluation on benchmark datasets validate the effectiveness of our proposed joint approach compared to the baseline and state-of-the-art models.

关键词： salient object detection existence prediction joint inference saliency detection

Intelligent Visual Media Processing： When Graphics Meets Vision

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Computer Science & Technology 2017年第1期32卷 110-121页

作者： ming-ming cheng Qi-Bin Hou Song-Hai Zhang Paul L. Rosin College of Computer Science and Control Engineering Nankai University Tianjin 300071 China TNList Tsinghua University Beijing 100084 China School of Computer Science and Informatics Cardiff University Wales CF10 3EU U.K.

The computer graphics and computer vision communities have been working closely together in recent years and a variety of algorithms and applications have been developed to analyze and manipulate the visual media around us. There are three major driving forces behind this phenomenon： 1） the availability of big data from the Internet has created a demand for dealing with the ever-increasing, vast amount of resources; 2） powerful processing tools, such as deep neural networks, provide effective ways for learning how to deal with heterogeneous visual data; 3） new data capture devices, such as the Kilxect, the bridge betweea algorithms for 2D image understanding and 3D model analysis. These driving forces have emerged only recently, and we believe that the computer graphics and computer vision communities are still in the beginning of their honeymoon phase. In this work we survey recent research on how computer vision techniques benefit computer graphics techniques and vice versa, and cover research on analysis, manipulation, synthesis, and interaction. We also discuss existing problems and suggest possible further research directions.

关键词： computer graphics computer vision survey scene understanding image manipulation

FLIC: Fast linear iterative clustering with active search

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computational Visual Media 2018年第4期4卷 333-348页

作者： Jiaxing Zhao Ren Bo Qibin Hou ming-ming cheng Paul Rosin Nankai University Tianjin 300350China. Cardiff University WalesUnited Kingdom.

In this paper, we reconsider the clustering problem for image over-segmentation from a new perspective. We propose a novel search algorithm called"active search" which explicitly considers neighbor continuity. Based on this search method, we design a back-and-forth traversal strategy and a joint assignment and update step to speed up the algorithm. Compared to earlier methods, such as simple linear iterative clustering(SLIC) and its variants, which use fixed search regions and perform the assignment and the update steps separately, our novel scheme reduces the number of iterations required for convergence,and also provides better boundaries in the oversegmentation results. Extensive evaluation using the Berkeley segmentation benchmark verifies that our method outperforms competing methods under various evaluation metrics. In particular, our method is fastest,achieving approximately 30 fps for a 481 × 321 image on a single CPU core. To facilitate further research, our code is made publicly available.

关键词： image over-segmentation SLIC neighbor continuity back-and-forth traversal

S4Net: Single stage salient-instance segmentation

在线全文

学校读者我要写书评

暂无评论

Computational Visual Media 2020年第2期6卷 191-204页

作者： Ruochen Fan ming-ming cheng Qibin Hou Tai-Jiang Mu Jingdong Wang Shi-Min Hu BNRist Tsinghua UniversityBeijing100086China Nankai University Tianjin300071China MSRA Beijing100086China

In this paper, we consider salient instance segmentation. As well as producing bounding boxes,our network also outputs high-quality instance-level segments as initial selections to indicate the regions of interest. Taking into account the category-independent property of each target, we design a single stage salient instance segmentation framework, with a novel segmentation branch. Our new branch regards not only local context inside each detection window but also the surrounding context, enabling us to distinguish instances in the same scope even with partial *** network is end-to-end trainable and is fast(running at 40 fps for images with resolution 320 × 320). We evaluate our approach on a publicly available benchmark and show that it outperforms alternative solutions. We also provide a thorough analysis of our design choices to help readers better understand the function of each part of our network. Source code can be found at https://***/Ruochen Fan/S4 Net.

关键词： salient-instance segmentation salient object detection single stage region-of-interest masking