投了一篇论文到Pattern Recognition, 审稿四个月。两个审稿人，审稿如下，没有收到第一个审稿人的意见，正在联系编辑。各位看下，是不是有重投的必要，希望大不？谢谢各位了。

Thank you for your interest and submission to Pattern Recognition. Unfortunately, based on evaluation, this manuscript, in the present state, is not suitable for publication in Pattern Recognition. The reasons for this decision are explained below in the Editor's comments.

However, resubmission of a thoroughly revised manuscript may be considered. In the revision, all issues raised in the review process should be addressed adequately. If you choose to submit a revision, please include the manuscript number of this current submission and a point by point response to the comments by the editor and/or reviewers in the resubmission cover letter.  

Thank you for choosing our journal as a possible publication medium.

Kind regards,


Editor in Chief
Pattern Recognition

Editor's comments:

The paper in its current form has several drawbacks. First, the experimental results, as indicated by the 1st reviewer is not up to the standards of the journal -- quantitative analysis and comparisons with appropriate literature should be included. Second, the references to the literature need to be updated to include seminal and other relevant works - as it stands 80% of the references are from CVPR and ICCV. Third, the use of language needs  significant improvement, even at the abstract.



Reviewer #1: Please find the .pdf attachment



Reviewer #2: In this an incremental approach of the SfM method is proposed. The technique is based on clustering merging among overlapping methods. The paper is not well written especially in its statements and how the originality and the positioning of the paper with respect to other techniques. Some comments are:

1) why this clustering algorithms are supported?
2) how the "extrinsic parameters of camera corresponding" how these parameters are estimated?
3) the comparison should be extended to give some different objective values and comparison with other methods.
4) some techniques for 3D reconstruction using data from the web data should be mentioned such as
Makantasis, Konstantinos, et al. "In the wild image retrieval and clustering for 3D cultural heritage landmarks reconstruction." Multimedia Tools and Applications 75.7 (2016): 3593-3629.
5) the state of the art is not well described. In its present form, they describe only how the SfM works. In think that this section should be re-structured from scratch so that
a) a state of the art is given
b)  visual features papers should be described
c) methods for 4D and 5D modelling should be given such as
Ioannides, Marinos, et al. "Online 4D reconstruction using multi-images available under Open Access." ISPRS Annals of the Photogrammetry, Remote Sensing and Saptial Information Sciences, II-5 W 1 (2013): 169-174.
Kyriakaki, G., Doulamis, A., Doulamis, N., Ioannides, M., Makantasis, K., Protopapadakis, E., ... & Weinlinger, G. (2014). 4D reconstruction of tangible cultural heritage objects from web-retrieved images. International Journal of Heritage in the Digital Era, 3(2), 431-451.
Doulamis, Anastasios, et al. "Selective 4D modelling framework for spatial-temporal land information management system." Third International Conference on Remote Sensing and Geoinformation of the Environment (RSCy2015). Vol. 9535. International Society for Optics and Photonics, 2015.
Doulamis, Anastasios, et al. "5D MODELLING: AN EFFICIENT APPROACH FOR CREATING SPATIOTEMPORAL PREDICTIVE 3D MAPS OF LARGE-SCALE CULTURAL RESOURCES." ISPRS Annals of Photogrammetry, Remote Sensing & Spatial Information Sciences (2015).
6)how different visual content affects the whole process? 返回小木虫查看更多