A group of researchers in Wuhan, China, evidently didn’t quite realize they were walking into a ridicule trap when they agreed to have their paper, “Face Recognition with Learning-based Descriptor,” published in IERI Procedia. The article appeared in 2012 and was part of an issue devote to that year’s International Conference on Future Computer Supported Education, which took place in Seoul.
And now comes this:
This article has been retracted at the request of the Author.
The authors have plagiarized part of a paper that had already appeared in [CVPR, IEEE (2010) 2707–2714. http://dx.doi.org/101109/CVPR.2010.5539992]. One of the conditions of submission of a paper for publication is that authors declare explicitly that their work is original and has not appeared in a publication elsewhere. Re-use of any data should be appropriately cited. As such this article represents a severe abuse of the scientific publishing system. The scientific community takes a very strong view on this matter and apologies are offered to readers of the journal that this was not detected during the submission process.
We’re curious about the “part of a paper” bit here. We found the plagiarized article, and judging by the title, at least, it seems like the two papers are awfully close. Indeed, the titles are identical, which ought to have been a red flag for the editors of IERI Procedia. Here’s the abstract of the lifted article:
We present a novel approach to address the representation issue and the matching issue in face recognition (verification). Firstly, our approach encodes the micro-structures of the face by a new learning-based encoding method. Unlike many previous manually designed encoding methods (e.g., LBP or SIFT), we use unsupervised learning techniques to learn an encoder from the training examples, which can automatically achieve very good tradeoff between discriminative power and invariance. Then we apply PCA to get a compact face descriptor. We find that a simple normalization mechanism after PCA can further improve the discriminative ability of the descriptor. The resulting face representation, learning-based (LE) descriptor, is compact, highly discriminative, and easy-to-extract. To handle the large pose variation in real-life scenarios, we propose a pose-adaptive matching method that uses pose-specific classifiers to deal with different pose combinations (e.g., frontal v.s. frontal, frontal v.s. left) of the matching face pair. Our approach is comparable with the state-of-the-art methods on the Labeled Face in Wild (LFW) benchmark (we achieved 84.45% recognition rate), while maintaining excellent compactness, simplicity, and generalization aability across different datasets.
We think there must be a lesson in there somewhere.