Article
Engineering, Electrical & Electronic
Vivek Kumar Singh, Nitin Kumar
Summary: This paper proposes an efficient features combination model using a teacher-learning-based optimization algorithm, which is demonstrated to outperform seven state-of-the-art methods on six benchmark datasets.
SIGNAL IMAGE AND VIDEO PROCESSING
(2021)
Article
Computer Science, Artificial Intelligence
Avishek Siris, Jianbo Jiao, Gary K. L. Tam, Xianghua Xie, Rynson W. H. Lau
Summary: This paper proposes to predict the saliency rank of multiple objects by inferring human attention shift. By constructing a new dataset and using a deep learning-based model, the authors achieve state-of-the-art performance on the salient object ranking task.
INTERNATIONAL JOURNAL OF COMPUTER VISION
(2023)
Article
Computer Science, Information Systems
Vivek Kumar Singh, Nitin Kumar
Summary: This paper proposes a Convex Hull Based Random Walks (CoBRa) approach for salient object detection. In this approach, an image is segmented into superpixels and a Convex Hull is constructed to partition the image into foreground and background regions. The centroid of the foreground region is calculated and used to compute initial saliency. Two thresholds are applied to produce binary segmented images, and foreground and background seeds are collected and refined. A random walk is then constructed to generate a pixel-wise saliency map. Experimental results on six datasets demonstrate the superiority of the proposed approach.
MULTIMEDIA TOOLS AND APPLICATIONS
(2022)
Article
Computer Science, Software Engineering
Wen-Kai Tsai, Ting-Hao Hsu
Summary: This study proposes an efficient and fast-performing image saliency detection algorithm, which consists of initiation saliency map generation and saliency map refinement. Experimental evaluation shows that the proposed method achieves sufficient accuracy and reliability while having the lowest execution time.
Article
Automation & Control Systems
Shigang Wang, Shuyuan Yang, Min Wang, Licheng Jiao
Summary: A hybrid saliency model proposed in this paper fuses contour cues and cues from different domains for robust salient object detection. Compared with traditional methods, this model has better modeling capability in diversified scenes and has been demonstrated to be superior in experiments.
IEEE TRANSACTIONS ON CYBERNETICS
(2021)
Article
Engineering, Electrical & Electronic
Anzhi Wang
Summary: A three-stream cross-modal feature aggregation network is proposed for 4D light field saliency detection, which analyzes different visual features of light field images to identify salient objects, showing effectiveness and superiority compared to state-of-the-art methods in experiments.
IEEE SIGNAL PROCESSING LETTERS
(2021)
Article
Automation & Control Systems
Shuo Li, Fang Liu, Licheng Jiao, Xu Liu, Puhua Chen
Summary: This paper introduces an unsupervised salient object detection method that achieves salient object detection by learning salient features from the data itself. The method enhances salient features, suppresses nonsalient features, and roughly locates the salient features to obtain the salient activation map. A saliency map update strategy is then used to remove noise and strengthen boundaries. The results show that the proposed method can effectively learn salient visual objects.
IEEE TRANSACTIONS ON CYBERNETICS
(2023)
Article
Computer Science, Artificial Intelligence
Keren Fu, Jing He, Xiao Yang
Summary: RGB-D salient object detection is an important research task, but existing models often suffer from poor generalizability. This paper treats RGB-D salient object detection as a few-shot learning problem and introduces prior knowledge from a closely related task, RGB salient object detection, to enhance performance. Experimental results validate the feasibility of using few-shot learning techniques to improve RGB-D salient object detection.
Article
Computer Science, Artificial Intelligence
Yuzhu Ji, Haijun Zhang, Zequn Jie, Lin Ma, Q. M. Jonathan Wu
Summary: This article introduces a novel cross-attention based encoder-decoder model called CASNet for video salient object detection, incorporating self- and cross-attention modules to improve accuracy and consistency. Extensive experimental results demonstrate the effectiveness of CASNet model surpassing existing image- and video-based methods on multiple datasets.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2021)
Article
Computer Science, Information Systems
Bhagyashree V. Lad, Mohammad Farukh Hashmi, Avinash G. Keskar
Summary: This paper proposes a unique approach for salient object detection, combining wavelet transform with learning-based methods. The method first applies superpixel segmentation to the input image for visually uniform regions and reduced computational cost. It then generates global and local saliency maps using wavelet transform and learning-based random forest regression, respectively. The two saliency maps are fused to create a final saliency map. Experimental results demonstrate the significant improvement of the proposed method in detecting salient regions compared to state-of-the-art methods.
Article
Engineering, Electrical & Electronic
Xiaoyang Zheng, Xin Tan, Jie Zhou, Lizhuang Ma, Rynson W. H. Lau
Summary: This paper introduces the use of saliency subitizing as weak supervision for salient object detection, with two modules generating and refining saliency masks. Experimental results demonstrate its superiority over other weakly-supervised methods and comparable performance to some fully-supervised methods.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2021)
Article
Computer Science, Artificial Intelligence
Ziyun Yang, Somayyeh Soltanian-Zadeh, Sina Farsiu
Summary: Traditional deep learning-based methods view salient object detection as a pixel-wise saliency modeling task, but often lack sufficient utilization of inter-pixel information. To address this limitation, a connectivity-based approach called bilateral connectivity network (BiconNet) is proposed, which has been demonstrated to effectively model inter-pixel relationships and object saliency through comprehensive experiments.
PATTERN RECOGNITION
(2022)
Article
Computer Science, Artificial Intelligence
Seyed Abbas Daneshyar, Nasrollah Moghadam Charkari
Summary: This paper introduces a new object tracking approach based on modified biogeography based optimization (mBBO) method and compares it with other tracking methods. Experimental results demonstrate that the proposed method achieves high accuracy in estimating the location of targets and performs better in terms of performance and robustness.
APPLIED SOFT COMPUTING
(2022)
Article
Computer Science, Artificial Intelligence
Ming-Ming Cheng, Shang-Hua Gao, Ali Borji, Yong-Qiang Tan, Zheng Lin, Meng Wang
Summary: This study proposes a lightweight salient object detection model and investigates the semantics of SOD models. By reducing representation redundancy and using a dynamic weight decay scheme, the model achieves comparable performance to state-of-the-art with significantly fewer parameters. The study shows that SOD and classification methods use different mechanisms, SOD models are category-insensitive, and SOD training does not require ImageNet pre-training.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2022)
Article
Computer Science, Artificial Intelligence
Jia Li, Shengye Qiao, Zhirui Zhao, Chenxi Xie, Xiaowu Chen, Changqun Xia
Summary: This article introduces a lightweight framework for salient object detection, which addresses the dilution of semantic context, loss of spatial structure, and absence of boundary detail by decoupling the U-shape structure into three branches. The proposed Scale-Adaptive Pooling Module is used to obtain multi-scale receptive field. Experimental results demonstrate that the method achieves a better balance between efficiency and accuracy.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2023)