Self-attention recurrent network for saliency detection

Sun, Fengdong; Li, Wenhui; Guan, Yuanyuan

doi:10.1007/s11042-018-6591-3

Cited by 14 publications

(13 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To further reduce the accumulated errors in the transmission of semantic information between layers, this paper adopts the self-attention model [19,20] to capture the spatial relationship between long-distance named entities in sports text. Because of the use of the transformer framework in encoding and decoding conversions, the self-attention mechanism model not only effectively solves the long-distance dependency problem of cyclic neural networks (RNN) [21,22], but also improves the overall operation efficiency of the model.…”

Section: Methodsmentioning

confidence: 99%

Named-Entity Recognition in Sports Field Based on a Character-Level Graph Convolutional Network

et al. 2020

View full text Add to dashboard Cite

Traditional methods for identifying naming ignore the correlation between named entities and lose hierarchical structural information between the named entities in a given text. Although traditional named-entity methods are effective for conventional datasets that have simple structures, they are not as effective for sports texts. This paper proposes a Chinese sports text named-entity recognition method based on a character graph convolutional neural network (Char GCN) with a self-attention mechanism model. In this method, each Chinese character in the sports text is regarded as a node. The edge between the nodes is constructed using a similar character position and the character feature of the named-entity in the sports text. The internal structural information of the entity is extracted using a character map convolutional neural network. The hierarchical semantic information of the sports text is captured by the self-attention model to enhance the relationship between the named entities and capture the relevance and dependency between the characters. The conditional random fields classification function can accurately identify the named entities in the Chinese sports text. The results conducted on four datasets demonstrate that the proposed method improves the F-Score values significantly to 92.51%, 91.91%, 93.98%, and 95.01%, respectively, in comparison to the traditional naming methods.

show abstract

Section: Methodsmentioning

confidence: 99%

Named-Entity Recognition in Sports Field Based on a Character-Level Graph Convolutional Network

et al. 2020

View full text Add to dashboard Cite

show abstract

“…The corresponding saliency maps are generated by Ref. Sun et al (2018). The parameter θ is the saliency guided seeded region growing method is set to 10.…”

Section: Experiments Settingsmentioning

confidence: 99%

Saliency guided deep network for weakly-supervised image segmentation

Sun

2019

Pattern Recognition Letters

Self Cite

View full text Add to dashboard Cite

Weakly-supervised image segmentation is an important task in computer vision. A key problem is how to obtain high quality objects location from image-level category. Classification activation mapping is a common method which can be used to generate high-precise object location cues. However these location cues are generally very sparse and small such that they can not provide effective information for image segmentation. In this paper, we propose a saliency guided image segmentation network to resolve this problem. We employ a self-attention saliency method to generate subtle saliency maps, and render the location cues grow as seeds by seeded region growing method to expand pixel-level labels extent. In the process of seeds growing, we use the saliency values to weight the similarity between pixels to control the growing. Therefore saliency information could help generate discriminative object regions, and the effects of wrong salient pixels can be suppressed efficiently. Experimental results on a common segmentation dataset PASCAL VOC2012 demonstrate the effectiveness of our method.

show abstract

“…The attention mechanism refers to selectively focusing on some certain useful visual information and ignoring other parts, which substantially is a weighted sharing idea. This idea applies widely in the computer vision tasks, especially for semantic segmentation [18], [19], saliency detection [20], [21], image caption [22], [23] and so on. The crowd counting task often presents the phenomenon of the uneven-distributed crowd, and thus this paper designs a Spatial Attention Conversion module for extracting crowd spatial feature as an accessory module to extract useful information and adds it to the method, on the basis of the attention mechanism.…”

Section: B Attention Mechanismmentioning

confidence: 99%

An Automatic Scale-Adaptive Approach With Attention Mechanism-Based Crowd Spatial Information for Crowd Counting

Kong

Xing

et al. 2019

IEEE Access

View full text Add to dashboard Cite

This paper proposes an automatic scale-adaptive approach with attention mechanism-based crowd spatial information addressing the crowd counting task, i.e. a novel cascaded crowd counting network. The proposed network is composed of a classification sub-network to estimate crowd scales and the main network to predict the corresponding density maps. First, the image serves as the input of the classification network and the main network. Second, according to the estimated crowd scale results, the main network structure is adjusted; simultaneously, the feature in the intermediate layer of the classification network is added stepwise into the main crowd counting network. Then, the semantic feature of the classification network is converted into the crowd spatial information mask via the proposed spatial attention conversion module, and the crowd spatial information mask is weighted into the specific feature of the main network. Last, the crowd density map and the crowd counting result are obtained. The experiments on challenging Mall, the Shanghaitech_A and Shanghaitech_B datasets prove the effectiveness, feasibility, and robustness of the proposed method, and the ablation study demonstrates the structure rationality of the proposed network.

show abstract

Self-attention recurrent network for saliency detection

Cited by 14 publications

References 44 publications

Named-Entity Recognition in Sports Field Based on a Character-Level Graph Convolutional Network

Named-Entity Recognition in Sports Field Based on a Character-Level Graph Convolutional Network

Saliency guided deep network for weakly-supervised image segmentation

An Automatic Scale-Adaptive Approach With Attention Mechanism-Based Crowd Spatial Information for Crowd Counting

Contact Info

Product

Resources

About