Powered by machine learning techniques, online advertising platforms have launched various automated bidding strategy services to facilitate intelligent decision-making for advertisers. However, advertisers experience heterogeneous advertising environments, and thus the unified bidding strategies widely used in both academia and industry suffer from severe unfairness issues, resulting in significant ad performance disparity among advertisers. In this work, to resolve the unfairness issue and improve the overall system performance, we propose a personalized automated bidding framework, namely PerBid, shifting the classical automated bidding strategy with a unified agent to multiple context-aware agents corresponding to different advertiser clusters. Specifically, we first design an ad campaign profiling network to model dynamic advertising environments. By clustering the advertisers with similar profiles and generating context-aware automated bidding agents for each cluster, we can match advertisers with personalized automated bidding strategies. Experiments conducted on the real-world dataset and online A/B test on Alibaba display advertising platform demonstrate the effectiveness of PerBid in improving overall ad performance and guaranteeing fairness among heterogeneous advertisers.

Efficiently identifying the mated gallery fingerprint of a latent fingerprint in a large database requires a highly accurate and efficient fingerprint matching algorithm. The common strategy to achieve this goal is to combine an efficient indexing algorithm with a slow but accurate matching algorithm. Despite of the importance of latent indexing, it has received far less attention than rolled and plain fingerprint indexing. Due to the small fingerprint area, poor image quality and huge variety in information quantity of latent fingerprints, existing rolled and plain fingerprint indexing approaches cannot be simply migrated to the latent fingerprint indexing. In this paper, we propose (1) a multi-scale fixed-length representation approach for latent fingerprint indexing, and (2) a fingerprint information quantity estimation approach for adaptive candidate list reduction. The representation scheme is designed to deal with small finger area and low image quality of latents. The information quantity of a latent is a predictor of the indexing score of its mated gallery fingerprint and thus can be used to determine a proper threshold for its candidate list. Extensive experimental results on NIST SD27, MOLF, N2N, and Hisign latent fingerprint databases show that the proposed method achieved the state-of-the-art indexing accuracy on latent fingerprints, and significantly improved the efficiency of state-of-the-art latent matching algorithm.

Latent fingerprint matching is a very important but unsolved problem. As a key step of fingerprint matching, fingerprint registration has a great impact on the recognition performance. Existing latent fingerprint registration approaches are mainly based on establishing correspondences between minutiae, and hence will certainly fail when there are no sufficient number of extracted minutiae due to small fingerprint area or poor image quality. Minutiae extraction has become the bottleneck of latent fingerprint registration. In this paper, we propose a non-minutia latent fingerprint registration method which estimates the spatial transformation between a pair of fingerprints through a dense fingerprint patch alignment and matching procedure. Given a pair of fingerprints to match, we bypass the minutiae extraction step and take uniformly sampled points as key points. Then the proposed patch alignment and matching algorithm compares all pairs of sampling points and produces their similarities along with alignment parameters. Finally, a set of consistent correspondences are found by spectral clustering. Extensive experiments on NIST27 database and MOLF database show that the proposed method achieves the state-of-the-art registration performance, especially under challenging conditions. Code is made publicly available at: https://github.com/Gus233/Latent-Fingerprint-Registration.

Recently, distortion rectification based on a single fingerprint image has been shown to be able to significantly improve the recognition rate of distorted fingerprints. However, the computational complexity of such a method is too high to be useful in practice. In this paper, we propose a novel method for the rectification of distorted fingerprints, whose speed is over 30 times faster than the existing method. This significant speedup is due to a Hough-forest-based two-step fingerprint pose estimation algorithm and a support vector regressor-based fingerprint distortion field estimation algorithm. Experimental results on public domain databases show that our method can achieve as good rectification performance as the existing method but meanwhile is significantly faster.

A non-scan design for testability method for RTL circuits based on conflict analysis is proposed. Conflict analysis is presented based on a new 5-valued system to estimate testability of data paths. New test point structures for RTL circuit design for testability are introduced. Nonscan design for testability is proposed based on conflict resolution. Unlike most of the previous methods, our method considers testability of data paths and the controller simultaneously. Different classes of test points can be inserted into data paths and the controller. Intensive techniques are presented to connect extra inputs of test points with PI ports, which avoids generating reconvergent fanouts that cause new conflicts.

A new scan architecture is proposed for full scan designed circuits. Scan flip-flops are grouped together if they do not have any common successors. This technique produces no new redundant faults. Scan flip-flops in the same group have the same values in all test vectors. All scan flip-flop groups form a scan forest, where each primary input drives the root of one scan tree. Test application time and test power based on the proposed scan forest architecture can be reduced drastically while pin overhead and delay overhead should be the same as that of conventional scan design. It is shown that test application cost and test power with the proposed scan forest architecture can be reduced to the level of non-scan design circuits.

A two stage non-scan design for testability method is proposed. The first stage selects test points based on an earlier testability measure conflict. A new testability measure conflict+ based on conflict analysis of hard-faults in the process of test generation is introduced, which emulates most general features of sequential ATPG. A new design for testability algorithm is proposed to select test points by using conflict+. Test points are selected in the second stage based on the hard faults after the initial ATPG run of the design for testability circuit in the preliminary stage. Effective approximation schemes are adopted to get reasonable estimation of the testability measure. Several effective techniques are adopted to accelerate the process of the proposed design for testability algorithm.