Spatial context-aware network for salient object detection

Kong, Yuqiu; Feng, Mengyang; Li, Xin; Lu, Huchuan; Liu, Xiuping; Yin, Baocai

doi:10.1016/j.patcog.2021.107867

Cited by 27 publications

(8 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Early salient object detection approaches [ 22 , 23 , 24 , 25 ] mainly used hand-crafted features, such as brightness, color, and texture, to locate and segment salient objects in an image. In recent years, thanks to the development of CNNs, various deep learning-based saliency models [ 26 , 27 , 28 ] have been proposed, and they outperform the traditional methods by a large margin. Zhang et al [ 26 ], explored multi-level features in each scale and recursively generated saliency maps.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Absolute and Relative Depth-Induced Network for RGB-D Salient Object Detection

Kong

Wang

Kong

et al. 2023

Sensors

Self Cite

View full text Add to dashboard Cite

Detecting salient objects in complicated scenarios is a challenging problem. Except for semantic features from the RGB image, spatial information from the depth image also provides sufficient cues about the object. Therefore, it is crucial to rationally integrate RGB and depth features for the RGB-D salient object detection task. Most existing RGB-D saliency detectors modulate RGB semantic features with absolution depth values. However, they ignore the appearance contrast and structure knowledge indicated by relative depth values between pixels. In this work, we propose a depth-induced network (DIN) for RGB-D salient object detection, to take full advantage of both absolute and relative depth information, and further, enforce the in-depth fusion of the RGB-D cross-modalities. Specifically, an absolute depth-induced module (ADIM) is proposed, to hierarchically integrate absolute depth values and RGB features, to allow the interaction between the appearance and structural information in the encoding stage. A relative depth-induced module (RDIM) is designed, to capture detailed saliency cues, by exploring contrastive and structural information from relative depth values in the decoding stage. By combining the ADIM and RDIM, we can accurately locate salient objects with clear boundaries, even from complex scenes. The proposed DIN is a lightweight network, and the model size is much smaller than that of state-of-the-art algorithms. Extensive experiments on six challenging benchmarks, show that our method outperforms most existing RGB-D salient object detection models.

show abstract

Section: Related Workmentioning

confidence: 99%

“…Feng et al [ 27 ], proposed an attentive feedback module to explore the structure of salient objects better. Kong et al [ 28 ], designed propagation modules to combine multi-scale features of the network. The authors of [ 29 ], proposed an integrity cognition network, to enhance the integrity of the predicted salient objects.…”

Section: Related Workmentioning

confidence: 99%

Absolute and Relative Depth-Induced Network for RGB-D Salient Object Detection

Kong

Wang

Kong

et al. 2023

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…Murphy et al (2006) learn local and global context by object presence and localization and use a product of experts model (Hinton, 2002) to combine them. Kong et al (2021) proposes a short path context module which transforms the integrated feature maps by considering local feature affinities.…”

Section: Related Workmentioning

confidence: 99%

CoVA: Context-aware Visual Attention for Webpage Information Extraction

Kumar¹,

Morabia²,

Wang³

et al. 2022

Proceedings of the Fifth Workshop on E-Commerce and NLP (ECNLP 5)

View full text Add to dashboard Cite

Webpage information extraction (WIE) is an important step to create knowledge bases. For this, classical WIE methods leverage the Document Object Model (DOM) tree of a website. However, use of the DOM tree poses significant challenges as context and appearance are encoded in an abstract manner. To address this challenge we propose to reformulate WIE as a context-aware Webpage Object Detection task. Specifically, we develop a Contextaware Visual Attention-based (CoVA) detection pipeline which combines appearance features with syntactical structure from the DOM tree. To study the approach we collect a new large-scale dataset 1 of e-commerce websites for which we manually annotate every web element with four labels: product price, product title, product image and others. On this dataset we show that the proposed CoVA approach is a new challenging baseline which improves upon prior state-of-the-art methods.

show abstract

“…1. Background information has been utilized in salient object detection [29], [31], [32], [33], [34] and image segmentation tasks [30], [35], [36], [37], [38]. In multilabel image classification, the relations between the object and background have not been fully exploited.…”

Section: Introductionmentioning

confidence: 99%