References of "Wang, Jun"
     in
Bookmark and Share    
Full Text
Peer Reviewed
See detailAutomatic Test Suite Generation for Key-Points Detection DNNs using Many-Objective Search (Experience Paper)
Ul Haq, Fitash UL; Shin, Donghwan UL; Briand, Lionel UL et al

in 2021 ACM SIGSOFT International Symposium on Software Testing and Analysis (ISSTA) (2021, July)

Automatically detecting the positions of key-points (e.g., facial key-points or finger key-points) in an image is an essential problem in many applications, such as driver's gaze detection and drowsiness ... [more ▼]

Automatically detecting the positions of key-points (e.g., facial key-points or finger key-points) in an image is an essential problem in many applications, such as driver's gaze detection and drowsiness detection in automated driving systems. With the recent advances of Deep Neural Networks (DNNs), Key-Points detection DNNs (KP-DNNs) have been increasingly employed for that purpose. Nevertheless, KP-DNN testing and validation have remained a challenging problem because KP-DNNs predict many independent key-points at the same time---where each individual key-point may be critical in the targeted application---and images can vary a great deal according to many factors. In this paper, we present an approach to automatically generate test data for KP-DNNs using many-objective search. In our experiments, focused on facial key-points detection DNNs developed for an industrial automotive application, we show that our approach can generate test suites to severely mispredict, on average, more than 93% of all key-points. In comparison, random search-based test data generation can only severely mispredict 41% of them. Many of these mispredictions, however, are not avoidable and should not therefore be considered failures. We also empirically compare state-of-the-art, many-objective search algorithms and their variants, tailored for test suite generation. Furthermore, we investigate and demonstrate how to learn specific conditions, based on image characteristics (e.g., head posture and skin color), that lead to severe mispredictions. Such conditions serve as a basis for risk analysis or DNN retraining. [less ▲]

Detailed reference viewed: 291 (50 UL)
Full Text
Peer Reviewed
See detailNovel Collaborative Filtering Recommender Friendly to Privacy Protection
Wang, Jun; Tang, Qiang; Delerue Arriaga, Afonso UL et al

in International Joint Conference on Artificial Intelligence (IJCAI 2019), Macao 10-16 August 2019 (2019)

Nowadays, recommender system is an indispensable tool in many information services, and a large number of algorithms have been designed and implemented. However, fed with very large datasets, state-of-the ... [more ▼]

Nowadays, recommender system is an indispensable tool in many information services, and a large number of algorithms have been designed and implemented. However, fed with very large datasets, state-of-the-art recommendation algorithms often face an efficiency bottleneck, i.e., it takes huge amount of computing resources to train a recommendation model. In order to satisfy the needs of privacy-savvy users who do not want to disclose their information to the service provider, the complexity of most existing solutions becomes prohibitive. As such, it is an interesting research question to design simple and efficient recommendation algorithms that achieve reasonable accuracy and facilitate privacy protection at the same time. In this paper, we propose an efficient recommendation algorithm, named CryptoRec, which has two nice properties: (1) can estimate a new user's preferences by directly using a model pre-learned from an expert dataset, and the new user's data is not required to train the model; (2) can compute recommendations with only addition and multiplication operations. As to the evaluation, we first test the recommendation accuracy on three real-world datasets and show that CryptoRec is competitive with state-of-the-art recommenders. Then, we evaluate the performance of the privacy-preserving variants of CryptoRec and show that predictions can be computed in seconds on a PC. In contrast, existing solutions will need tens or hundreds of hours on more powerful computers. [less ▲]

Detailed reference viewed: 41 (3 UL)
Full Text
Peer Reviewed
See detailKnow Your Enemies and Know Yourself in the Real-Time Bidding Function Optimisation
Du, Manxing UL; Cowen-Rivers, Alexander I.; Wen, Ying et al

in Proceedings of the 19th IEEE International Conference on Data Mining Workshops (ICDMW 2019) (2019)

Detailed reference viewed: 407 (5 UL)
Full Text
Peer Reviewed
See detailDistinct antimicrobial peptide expression determines host species-specific bacterial associations
Franzenburg, Sören; Walter, Jonas UL; Künzel, Sven et al

in Proceedings of the National Academy of Sciences of the United States of America (2013), 110(39), 37303738

Animals are colonized by coevolved bacterial communities, which contribute to the host’s health. This commensal microbiota is often highly specific to its host-species, inferring strong selective ... [more ▼]

Animals are colonized by coevolved bacterial communities, which contribute to the host’s health. This commensal microbiota is often highly specific to its host-species, inferring strong selective pressures on the associated microbes. Several factors, including diet, mucus composition, and the immune system have been proposed as putative determinants of host-associated bacterial communities. Here we report that species-specific antimicrobial peptides account for different bacterial communities associated with closely related species of the cnidarian Hydra. Gene family extensions for potent antimicrobial peptides, the arminins, were detected in four Hydra species, with each species possessing a unique composition and expression profile of arminins. For functional analysis, we inoculated arminin-deficient and control polyps with bacterial consortia characteristic for different Hydra species and compared their selective preferences by 454 pyrosequencing of the bacterial microbiota. In contrast to control polyps, arminin-deficient polyps displayed decreased potential to select for bacterial communities resembling their native microbiota. This finding indicates that species-specific antimicrobial peptides shape species-specific bacterial associations. [less ▲]

Detailed reference viewed: 152 (7 UL)