Special Offer: Get 50% off your first 2 months when you do one of the following
Personalized offer codes will be given in each session

(AIMS 2020) Attention-based Asymmetric Fusion Network for Saliency Prediction in 3D Images

About This Webinar

Abstract: Nowadays the visual saliency prediction has become a fundamental problem in 3D imaging area. In this paper, we proposed a saliency prediction model from the perspective of addressing three aspects of challenges. First, to adequately extract features of RGB and depth information, we designed an asymmetric encoder structure on the base of U-shape architecture. Second, to prevent the semantic information between salient objects and corresponding contexts from diluting in cross-modal distillation stream, we devised a global guidance module to capture high-level feature maps and deliver them into feature maps in shallower layers. Third, to locate and emphasize salient objects, we introduced a channel-wise attention model. Finally we built the refinement stream with integrated fusion strategy, gradually refining the saliency maps from coarse to fine-grained. Experiments on two widely-used datasets demonstrate the effectiveness of the proposed architecture, and the results show that our model outperforms six selective state-of-the-art models.

Authors: Xinyue Zhang and Ting Jin (Hainan University, China)

Email: 18085212210042@hainanu.edu.cn, tingj@fudan.edu.cn

Who can view: Everyone
Webinar Price: Free
Featured Presenters
Webinar hosting presenter Services Society
Xinyue Zhang was born in Sichuan, China, in 1996. She received the B.S. degree in computer science and technology from Hainan University, in 2018. She is currently pursuing the M.S. degree under the supervision of Dr. Ting Jin in School of Computer Science and Cyberspace Security, Hainan University. Her research interests include saliency prediction and action recognition.
Hosted By
Services Society webinar platform hosts (AIMS 2020) Attention-based Asymmetric Fusion Network for Saliency Prediction in 3D Images
Services Society's Channel