22,377 Hits in 5.5 sec

A Simple Pooling-Based Design for Real-Time Salient Object Detection [article]

Jiang-Jiang Liu, Qibin Hou, Ming-Ming Cheng, Jiashi Feng, Jianmin Jiang
2019 arXiv   pre-print
We solve the problem of salient object detection by investigating how to expand the role of pooling in convolutional neural networks.  ...  salient objects.  ...  research was supported by NSFC (61620106008, 61572264), the national youth talent support program, Tianjin Natural Science Foundation (17JCJQJC43700, 18ZXZNGX00110) and the Fundamental Research Funds for  ... 
arXiv:1904.09569v1 fatcat:uvbmpl2lqfgazhr4z5ha54rgii

RGBT Salient Object Detection: A Large-scale Dataset and Benchmark [article]

Zhengzheng Tu, Yan Ma, Zhun Li, Chenglong Li, Jieming Xu, Yongtao Liu
2022 arXiv   pre-print
directions for RGBT salient object detection.  ...  Most works focus on RGB-based salient object detection, which limits its performance of real-life applications when confronted with adverse conditions such as dark environments and complex backgrounds.  ...  To provide a powerful baseline for RGBT salient object detection, we design an end-to-end trained CNN-based framework.  ... 
arXiv:2007.03262v6 fatcat:6bulfkcrwzhszbxojdjdymkdhq

Agile Amulet: Real-Time Salient Object Detection with Contextual Attention [article]

Pingping Zhang, Luyao Wang, Dong Wang, Huchuan Lu, Chunhua Shen
2018 arXiv   pre-print
This paper proposes an Agile Aggregating Multi-Level feaTure framework (Agile Amulet) for salient object detection.  ...  Compared to other deep learning based saliency methods, Agile Amulet is of much lighter-weight, runs faster (30 fps in real-time) and achieves higher performance on seven public benchmarks in terms of  ...  The real-time speed will foster more applications. Conclusion In this paper, we propose an agile aggregating multi-level feature framework for salient object detection.  ... 
arXiv:1802.06960v1 fatcat:ug3xxxihu5hslob4kwc6cutlgq

A neural computational model for bottom-up attention with invariant and overcomplete representation

Zou Qi, Zhao Songnian, Wang Zhe, Huang Yaping
2012 BMC Neuroscience  
This finding can potentially be applied in task-dependent and supervised object detection. (2) A hierarchical coding model that can represent invariant features, is designed for the pre-attentive stage  ...  To address this problem, we constructed a two-layered network that satisfies the neurobiological constraints of the primary visual cortex to detect salient objects.  ...  Sarkar for invaluable help and suggestions. We greatly appreciate the reviewers for their suggestions. Author details  ... 
doi:10.1186/1471-2202-13-145 pmid:23190754 pmcid:PMC3599588 fatcat:bjwe4evwavhl3n3swavspw5j2m

Rethinking of the Image Salient Object Detection: Object-level Semantic Saliency Re-ranking First, Pixel-wise Saliency Refinement Latter [article]

Zhenyu Wu, Shuai Li, Chenglizhao Chen, Aimin Hao, Hong Qin
2020 arXiv   pre-print
Our method is simple yet effective, which is the first attempt to consider the salient object detection mainly as an object-level semantic re-ranking problem.  ...  Previous image salient object detection (SOD) works conduct their saliency predictions in a multi-task manner, i.e., performing pixel-wise saliency regression and segmentation-like saliency refinement  ...  INTRODUCTION Salient object detection aims to fast locate the most eyecatching objects in a given scene.  ... 
arXiv:2008.05397v1 fatcat:tlkjuqc26zfe7baweou4yzhngq

Contrast-Oriented Deep Neural Networks for Salient Object Detection

Guanbin Li, Yizhou Yu
2018 IEEE Transactions on Neural Networks and Learning Systems  
Deep convolutional neural networks have become a key element in the recent breakthrough of salient object detection.  ...  Though being very efficient, it is arduous for these methods to detect salient objects of different scales or salient regions with weak semantic information.  ...  Recently, deep learning based methods have been widely used for salient object detection and have promoted its research into a new phase.  ... 
doi:10.1109/tnnls.2018.2817540 pmid:29993934 fatcat:fvchrcr6sfclfgmimhg75otw6u

CNN-based temporal detection of motion saliency in videos

Léo Maczyta, Patrick Bouthemy, Olivier Le Meur
2019 Pattern Recognition Letters  
Temporal motion saliency detection is relevant for applications where one needs to trigger alerts or to monitor dynamic behaviours from videos.  ...  A frame will be classified as dynamically salient if it contains local motion departing from its context.  ...  Also, expected use cases of motion saliency detection methods are likely to require a real-time execution.  ... 
doi:10.1016/j.patrec.2019.09.016 fatcat:nebn7k5cnbcndekozyrkkljoca

Local Motion Analysis and Its Application in Video based Swimming Style Recognition

Xiaofeng Tong, Lingyu Duan, Changsheng Xu, Qi Tian, Hanqing Lu
2006 18th International Conference on Pattern Recognition (ICPR'06)  
Finally, we employ a hierarchical classifier to distinguish local motion based on periodicity and salient frames.  ...  For each period, we locate a so-called salient frame within which we derive a compact representation to distinctly characterize an image sequence with repeated actions.  ...  Introduction Motion plays a critical role in video analysis. It is unique and intrinsic for characterizing the dynamics and evolution of an object or a scene along time.  ... 
doi:10.1109/icpr.2006.770 dblp:conf/icpr/TongDXTL06 fatcat:33mhyo7rj5dytgh3527yhtgslq

Salient Object Ranking with Position-Preserved Attention [article]

Hao Fang, Daoxin Zhang, Yi Zhang, Minghao Chen, Jiawei Li, Yao Hu, Deng Cai, Xiaofei He
2021 arXiv   pre-print
A closely related task, salient object detection, predicts a binary map highlighting a visually salient region while hard to distinguish multiple objects.  ...  In this paper, we study the Salient Object Ranking (SOR) task, which manages to assign a ranking order of each detected object according to its visual saliency.  ...  We design a simple SOR branch as the baseline. Proposals' features first pass four convolution layers.  ... 
arXiv:2106.05047v2 fatcat:bkmvkkcn4fflhatv665qi5cnqe

S4Net: Single stage salient-instance segmentation

Ruochen Fan, Ming-Ming Cheng, Qibin Hou, Tai-Jiang Mu, Jingdong Wang, Shi-Min Hu
2020 Computational Visual Media  
Taking into account the category-independent property of each target, we design a single stage salient instance segmentation framework, with a novel segmentation branch.  ...  In this paper, we consider salient instance segmentation.  ...  Foundation of China (61521002, 61572264, 61620106008), the National Youth Talent Support Program, Tianjin Natural Science Foundation (17JCJQJC43700, 18ZXZNGX00110), and the Fundamental Research Funds for  ... 
doi:10.1007/s41095-020-0173-9 fatcat:c2vbqx2r3zfclbnpoh2sxar3jy

Object Detection with Deep Learning: A Review [article]

Zhong-Qiu Zhao and Peng Zheng and Shou-tao Xu and Xindong Wu
2019 arXiv   pre-print
In this paper, we provide a review on deep learning based object detection frameworks.  ...  Finally, several promising directions and tasks are provided to serve as guidelines for future work in both object detection and relevant neural network based learning systems.  ...  To achieve real-time detection on mobile platform, Kalinovskii and Spitsyn proposed a new solution of frontal face detection based on compact CNN cascades [177] .  ... 
arXiv:1807.05511v2 fatcat:iu4apzqmnjgmhb2myrs5x7qkia


2022 Zenodo  
The objective of this paper is to automate the method of estimating BCS. This paper proposed an efficient method for estimating BCS using the salient object and Convolutional Neural Network.  ...  The cow's body is identified from the edge map from which the width is used as a feature. The edge map is given to CNN for another feature.  ...  The edges are also used to find the salient object. From the salient object, deep features are extracted using simple CNN. At the same time, the oval shape of the cow is also identified.  ... 
doi:10.5281/zenodo.6613366 fatcat:67aabxmrezajtn3uy5q5itp4me

Object Detection in Video Frames using Deep Learning

Krishna Kumar, Krishan Kumar, C.L.P. Gupta
2022 International Journal of Computer Applications  
The paper focuses on the framework design and the working principle of the models and examines the model performance in the real-time environment and hence for the accuracy of object detection.  ...  Furthermore, a survey of several specific tasks including salient object detection features, face detection and pedestrian detection has also been briefly discussed.  ...  Cong Tang et. al [13] discuss on the framework design and the working principle of the models and analyzes the model performance in the real-time and the accuracy of detection.  ... 
doi:10.5120/ijca2022921930 fatcat:2lnkdxa425dcpev6ubfosgxeim

Attention Guided Network for Salient Object Detection in Optical Remote Sensing Images [article]

Yuhan Lin, Han Sun, Ningzhong Liu, Yetong Bian, Jun Cen, Huiyu Zhou
2022 arXiv   pre-print
Due to the extreme complexity of scale and shape as well as the uncertainty of the predicted location, salient object detection in optical remote sensing images (RSI-SOD) is a very difficult task.  ...  Specifically, the position enhancement stage consists of a semantic attention module and a contextual attention module to accurately describe the approximate location of salient objects.  ...  In this paper, we aim at designing an attention guided network for accurate salient object detection in optical RSIs, called AGNet.  ... 
arXiv:2207.01755v1 fatcat:fcar6p4uz5cq3kvkpaxhv6xon4

Edge-guided Non-local Fully Convolutional Network for Salient Object Detection [article]

Zhengzheng Tu, Yan Ma, Chenglong Li, Jin Tang, Bin Luo
2019 arXiv   pre-print
To maintain the clear edge structure of salient objects, we propose a novel Edge-guided Non-local FCN (ENFNet) to perform edge guided feature learning for accurate salient object detection.  ...  Fully Convolutional Neural Network (FCN) has been widely applied to salient object detection recently by virtue of high-level semantic feature extraction, but existing FCN based methods still suffer from  ...  To handle this problem, we propose a novel method based on an edge-guided non-local FCN, named ENFNet, for salient object detection.  ... 
arXiv:1908.02460v2 fatcat:e7sjjjwpfbh6roglc4ujrjae5e
« Previous Showing results 1 — 15 out of 22,377 results