Filters








1,273 Hits in 8.0 sec

Dynamic Message Propagation Network for RGB-D Salient Object Detection [article]

Baian Chen, Zhilei Chen, Xiaowei Hu, Jun Xu, Haoran Xie, Mingqiang Wei, Jing Qin
2022 arXiv   pre-print
This paper presents a novel deep neural network framework for RGB-D salient object detection by controlling the message passing between the RGB images and depth maps on the feature level and exploring  ...  the long-range semantic contexts and geometric information on both RGB and depth features to infer salient objects.  ...  BiANet [41] proposes a multi-scale bilateral attention module (MBAM) to exploit global salient information in a multi-level manner.  ... 
arXiv:2206.09552v1 fatcat:rzcne743q5ewvedczwzkzkilo4

Attention-guided Context Feature Pyramid Network for Object Detection [article]

Junxu Cao, Qi Chen, Jun Guo, Ruichao Shi
2020 arXiv   pre-print
For object detection, how to address the contradictory requirement between feature map resolution and receptive field on high-resolution inputs still remains an open question.  ...  fields via integrating attention-guided multi-path features.  ...  The Context Attention Module (CxAM) and Content Attention Module (CnAM) are devised to identify the salient dependencies among the extracted context.  ... 
arXiv:2005.11475v1 fatcat:em5vkhiltzespk2vx4co24mtbu

Scattering Keypoints Guided Network for Oriented Ship Detection in High-Resolution and Large-Scale SAR Images

Kun Fu, Jiamei Fu, Zhirui Wang, Xian Sun
2021 IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing  
Moreover, these detectors have limited performance in large-scale and complex scenes due to the strong interference of inshore background and the variability of object imaging characteristics.  ...  Second, a contextaware feature selection module is introduced to dynamically learn both local and context features.  ...  One direct way of acquiring the context information is multi-scale feature fusion.  ... 
doi:10.1109/jstars.2021.3109469 fatcat:4lxmv5pw5bagzbpp6cfkvles5q

HROM: Learning High-Resolution Representation and Object-Aware Masks for Visual Object Tracking

Dawei Zhang, Zhonglong Zheng, Tianxiang Wang, Yiran He
2020 Sensors  
Moreover, we exploit attention mechanisms to learn object-aware masks for adaptive feature refinement, and use deformable convolution to handle complex geometric transformations.  ...  The resulting representation is semantically richer and spatially more precise by a simple yet effective multi-scale feature fusion strategy.  ...  are exploited to perform up-sample process for object detection.  ... 
doi:10.3390/s20174807 pmid:32858872 fatcat:m2gcbfyklzfylbpehtqnm3m5bu

Deformable ConvNets v2: More Deformable, Better Results [article]

Xizhou Zhu, Han Hu, Stephen Lin, Jifeng Dai
2018 arXiv   pre-print
With the proposed contributions, this new version of Deformable ConvNets yields significant performance gains over the original model and produces leading results on the COCO benchmark for object detection  ...  The superior performance of Deformable Convolutional Networks arises from its ability to adapt to the geometric variations of objects.  ...  In a multi-path network for object detection [40] , multiple RoIpooling layers are employed for each input RoI to better exploit multi-scale and context information.  ... 
arXiv:1811.11168v2 fatcat:goo53jnvorgahpar4qdglm6bdy

iMSCGnet: Iterative Multi-scale Context-guided Segmentation of Skin Lesion in Dermoscopic Images

Yujiao Tang, Zhiwen Fang, Shaofeng Yuan, Changan Zhan, Yanyan Xing, Joey Tianyi Zhou, Feng Yang
2020 IEEE Access  
INDEX TERMS Skin lesion segmentation, multi-scale context, attention, deep supervision.  ...  To alleviate this problem, we propose a multi-scale context-guided network named as MSCGnet to segment the skin lesions accurately.  ...  A and + are the context-based attention structure CAs and the element-wise addition, respectively.  ... 
doi:10.1109/access.2020.2974512 fatcat:nwfoe4dthjbojpnbuwdh6wtmzi

Salience-Guided Cascaded Suppression Network for Person Re-Identification

Xuesong Chen, Canmiao Fu, Yong Zhao, Feng Zheng, Jingkuan Song, Rongrong Ji, Yi Yang
2020 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
Acknowledgement This work is supported in part by the National Natural Science Foundation of China under Grant 61972188, the Science and Technology Planning Project of Shenzhen (No.  ...  Channel-wise Attention: The high-level convolutional feature in a trained CNN module is well-known to have remarkable localization ability for a semantic-related object.  ...  Residual Dual Attention Module The Residual Dual Attention Module (RDAM) consists of a Channel-wise Attention Module(CAM) and a Residual Spatial Attention Module (RSAM), in which the channel-wise attention  ... 
doi:10.1109/cvpr42600.2020.00336 dblp:conf/cvpr/ChenFZZSJY20 fatcat:ujz4jyuirjabnicda3eemo547y

MPViT: Multi-Path Vision Transformer for Dense Prediction [article]

Youngwan Lee, Jonghee Kim, Jeff Willette, Sung Ju Hwang
2021 arXiv   pre-print
Dense computer vision tasks such as object detection and segmentation require effective multi-scale feature representation for detecting or classifying objects or regions with varying sizes.  ...  classification, object detection, instance segmentation, and semantic segmentation.  ...  These results demonstrate the proposed multi-scale patch embedding and multipath structure can represent more diverse multi-scale features than simpler multi-scale structured models for object detection  ... 
arXiv:2112.11010v2 fatcat:mk6uiqrinbborohzy7s2jj7cri

Research on Salient Object Detection using Deep Learning and Segmentation Methods

2019 International journal of recent technology and engineering  
Detecting and segmenting salient objects in natural scenes, often referred to as salient object detection has attracted a lot of interest in computer vision and recently various heuristic computational  ...  The aim of this review work is to study about the details of methods in salient object detection.  ...  Low-frequency content in the image. 8 Automatic Salient Object Detection in UAV Imagery Sokalski, [2010] Multi-scale mean-shift segmentation with novel histogram enhancement.  ... 
doi:10.35940/ijrte.b1046.0982s1119 fatcat:6ofq53vb7zhx7boq4ndpraphs4

2020 Index IEEE Transactions on Image Processing Vol. 29

2020 IEEE Transactions on Image Processing  
., +, TIP 2020 8590-8605 Reverse Attention-Based Residual Network for Salient Object Detection. Chen, S., +, TIP 2020 3763-3776 RGB-T Salient Object Detection via Fusing Multi-Level CNN Features.  ...  ., +, TIP 2020 670-678 Dynamic Feature Integration for Simultaneous Detection of Salient Object, Edge, and Skeleton.  ... 
doi:10.1109/tip.2020.3046056 fatcat:24m6k2elprf2nfmucbjzhvzk3m

Visual Object Tracking with Saliency Refiner and Adaptive Updating

Wei Zhang, Baosheng Kang, Shunli Zhang, Mei Gao
2018 International Journal of Innovative Computing, Information and Control  
Meanwhile, a separate scale filter is exploited to estimate the scale variation.  ...  In this paper, we propose a novel correlation tracking approach with saliency refiner and adaptive updating.  ...  This work is supported by the National Natural Science Foundation of China (Grant Nos: 61772421, 61572400) and the Key Research Project of Baoji University of Arts and Sciences (No: ZK15032).  ... 
doi:10.24507/ijicic.14.05.1855 fatcat:wkgqs4xcnvgc5l4uthec2bqg6m

Instance-Level Relative Saliency Ranking with Graph Reasoning [article]

Nian Liu, Long Li, Wangbo Zhao, Junwei Han, Ling Shao
2021 arXiv   pre-print
Conventional salient object detection models cannot differentiate the importance of different salient objects.  ...  However, one of these models cannot differentiate object instances and the other focuses more on sequential attention shift order inference.  ...  Some models [19] , [24] , [25] treat salient object detection as a pixel/superpixel-wise classification problem and run deep classification models on multi-scale regions.  ... 
arXiv:2107.03824v1 fatcat:2hhm6p3jv5h2fhtiefrpm55aee

Heterogeneous Grid Convolution for Adaptive, Efficient, and Controllable Computation [article]

Ryuhei Hamaguchi, Yasutaka Furukawa, Masaki Onishi, Ken Sakurada
2021 arXiv   pre-print
We have evaluated the proposed approach on four image understanding tasks, semantic segmentation, object localization, road extraction, and salient object detection.  ...  Especially, the method outperforms a strong baseline with more than 90% reduction in floating-point operations for semantic segmentation, and achieves the state-of-the-art result for road extraction.  ...  Acknowledgement This paper is partially based on results obtained from a project commissioned by the New Energy and Industrial Technology Development Organization (NEDO) and supported by JSPS KAKENHI Grant  ... 
arXiv:2104.11176v1 fatcat:4lkbvzvkgzadfe7dgqm6ah4sgq

An Adaptive Sample Assignment Strategy Based on Feature Enhancement for Ship Detection in SAR Images

Hao Shi, Zhonghao Fang, Yupei Wang, Liang Chen
2022 Remote Sensing  
Recently, ship detection in synthetic aperture radar (SAR) images has received extensive attention.  ...  In order to alleviate false alarms, a feature aggregation enhancement pyramid network (FAEPN) is proposed to enhance multi-scale feature representations and suppress the interference of background noise  ...  [26] designed a novel two-way structure to extract multi-scale context features efficiently.  ... 
doi:10.3390/rs14092238 fatcat:eb42cvyg2venpc3zd4eo3yneuy

2021 Index IEEE Transactions on Image Processing Vol. 30

2021 IEEE Transactions on Image Processing  
Departments and other items may also be covered if they have been judged to have archival value. The Author Index contains the primary entry for each item, listed under the first author's name.  ...  The primary entry includes the coauthors' names, the title of the paper or other item, and its location, specified by the publication abbreviation, year, month, and inclusive pagination.  ...  ., +, TIP 2021 4526-4539 Looking for the Detail and Context Devils: High-Resolution Salient Object Detection.  ... 
doi:10.1109/tip.2022.3142569 fatcat:z26yhwuecbgrnb2czhwjlf73qu
« Previous Showing results 1 — 15 out of 1,273 results