24小时热门版块排行榜

>论坛更新日志 (3656)
>导师招生 (599)
>考博 (156)
>文献求助 (143)
>虫友互识 (134)
>博后之家 (100)
>微米和纳米 (90)
>论文投稿 (49)
>硕博家园 (45)
>学术会议 (42)
>公派出国 (42)
>休闲灌水 (42)
>教师之家 (38)
>考研 (31)
>招聘信息布告栏 (19)
>基金申请 (19)

返回列表

【有奖交流】积极回复本帖子，参与交流，就有机会分得作者 sig102657 的 776 个金币，回帖就立即获得 2 个金币，每人有 1 次机会

sig102657

新虫 (著名写手)

应助: 0 (幼儿园)
金币: 216.7
帖子: 2437
在线: 4小时
虫号: 20772003

[交流] Call for Papers (IEEE Transactions on Neural Networks and Learning Systems Speci

截稿日期:

2020年11月30号

IEEE Transactions on Neural Networks and Learning Systems Call for Papers

Special Issue on

Effective Feature Fusion in Deep Neural Networks

https://cis.ieee.org/images/file ... efdnn_tnnls_cfp.pdf

Submission deadline: nov. 30, 2020. first notification: feb. 1, 2021

            ================================================================================

Due to the powerful ability of learning hierarchical features, Deep Deural Detworks (DNNs) have achieved great success in many intelligent perception systems with image data and/or point cloud data and have been widely used in developing robust automotive driving, visual surveillance, and human-machine interaction. For example, state-of-the-art performances in image classification, object detection, semantic segmentation, and cross-modal perception are obtained by different kinds of DNNs. To a great degree, the success of DNNs stems from properly fusing the hierarchical features which are diverse in semantic-levels, resolutions/scales, roles, sensitivity, and so on. Representative fusion schemes include dense connection, residual learning, skip connection, top-down feature pyramid, and attention-based feature weighting. However, there is a large room for developing more effective feature fusion to improve the performance of dnns so that machine perception can approach or exceed human perception.

This special issue focuses on investigating problems and phenomena of existing feature fusion schemes, tackling the challenges of semantic gap and perception of hard objects and scenarios, and providing new ideas, theories, solutions, and insights for effective feature fusion in DNNs for image and/or point cloud data. The topics of interest include, but are not limited to:

n Feature fusion for effective backbones and prediction

n Feature fusion for image/video data using deep neural networks

n Feature fusion for point cloud data using deep neural networks

n Adaptive feature fusion networks

n Criteria and loss functions for feature fusion in deep neural networks

n Feature fusion for detecting/recognizing small objects

n Feature fusion for detecting/recognizing occluded objects

n Attention-based feature fusion in deep neural networks

n Visualization and interpretation of feature fusion

n Feature fusion for semantic segmentation

n Feature fusion for object tracking

n Feature fusion for cross-modal/domain learning

n Feature fusion for 3D object detection

n New feature fusion problems and applications

IMPORTANT DATAS

n  November 30, 2020: Deadline for manuscript submission

n  February 1, 2021: Reviewer’s comments to authors

n  April 1, 2021: Submission deadline of revisions

n  June 1, 2021: Final decisions to authors

n  July 1, 2021: Publication date (Early access)

GUEST EDITORS

Yanwei Pang, Tianjin University, China, pyw@tju.edu.cn

Fahad Shahbaz Khan, Inception Institute of Artificial Intelligence, UAE, fahad.khan@liu.se

Xin Lu, Adobe Inc., USA, xinl@adobe.com

Fabio Cuzzolin, Oxford Brookes University, UK, fabio.cuzzolin@brookes.ac.uk

SUBMISSION INSTRUCTIONS

n  Read the Information for Authors at https://cis.ieee.org/tnnls.

n  Submit your manuscript at the TNNLS webpage (https://mc.manuscriptcentral.com/tnnls) and follow the submission procedure. Please, clearly indicate on the first page of the manuscript and in the cover letter that the manuscript is submitted to this special issue. Send an email to the leading editor Prof. Yanwei Pang (pyw@tju.edu.cn) with subject “TNNLS special issue submission” to notify your submission.

n  Early submissions are welcome. We will start the review process as soon as we receive your contributions.

回复此楼