Welcome to Dr. Zhang's Personal Homepage

Pair-based metric learning has been widely adopted to learn sentence embedding in many NLP tasks. However, it is known that the sentence representation can be biased when the sampled sentence pairs deviate from the true distribution of all sentence pairs. In this paper, instead of one time pair selection and learning on equal weighted pairs, we propose a unified locality weighting and learning framework. Extensive experiments on four public available datasets and a self-collected place search benchmark with 1.4 million places clearly demonstrate that our model consistently outperforms existing sentence embedding methods with comparable efficiency. Published in ICDM2022.

With the rapid development of the influencer marketing industry in recent years, the cooperation between brands and micro-influencers on marketing has achieved much attention. As a key sub-task of influencer marketing, micro-influencer recommendation is gaining momentum. However, in influencer marketing campaigns, it is not enough to only consider marketing effectiveness. Towards this end, we propose a concept-based micro-influencer ranking framework, to address the problems of marketing effectiveness and self-development needs for the task of micro-influencer recommendation. Marketing effectiveness is improved by concept-based social media account representation and a micro-influencer ranking function. We conduct social media account representation from the perspective of historical activities and marketing direction. And two adaptive learned metrics, endorsement effect score and micro-influencer influence score, are defined to learn the micro-influencer ranking function. To meet self-development needs, we design a bi-directional concept attention mechanism to focus on brands and micro-influencers marketing direction over social media concepts. Interpretable concept-based parameters are utilized to help brands and micro-influencers make marketing decisions. Extensive experiments conducted on a real-world dataset demonstrate the advantage of our proposed method compared with the state-of-the-art methods. Published in IEEE Transactions on Multimedia 2021

Oral health has significant impact on people's over-all well-being. In this work, we propose Hygiea, an energy-efficient and highly-accurate toothbrushing monitoring system which exploits IMU-based wrist-worn gesture sensing using unmodified toothbrushes. Hygiea incorporates a number of novel signal preprocessing techniques to automatically transform the sensory input during arbitrary toothbrushing activities to the consistent user coordinate system. To distinguish different brushing actions, Hygiea leverages an emerging deep learning model to achieve fine-grained activity recognitions. Moreover, a POMDP model is incorporated for sampling control to balance activity detection and energy efficiency. Extensive real-world experiments show that the Hygiea system achieves a 11.7% accuracy gain compared to the state-of-the-art while maintaining energy-efficiency and zero modification on the toothbrushes. Published in INFOCCOM2019.

We present the novel concept of Controllable Face Privacy. Existing methods that alter face images to conceal identity inadvertently also destroy other facial attributes such as gender, race or age. This all-or-nothing approach is too harsh. Instead, we propose a flexible method that can independently control the amount of identity alteration while keeping unchanged other facial attributes. To achieve this flexibility, we apply a subspace decomposition onto our face encoding scheme, effectively decoupling facial attributes such as gender, race, age, and identity into mutually orthogonal subspaces, which in turn enables independent control of these attributes. Our method is thus useful for nuanced face de-identification, in which only facial identity is altered, but others, such gender, race and age, are retained. Published in FG2015(ORAL).

Identical twins pose an interesting challenge for recognition systems due to their similar appearance. Although various biometrics have been proposed for the problem, existing works are quite limited due to the difficulty of obtaining a twins database. To encourage the methods for twins recognition and make a fair comparison of them by using the same database, we collected an audio-visual twins database at the Sixth Mojiang International Twins Festival held on 1 May 2010,China. Our database contains 39 pairs of twins in total, including Chinese, American and Russian subjects. This database contains several face images, facial motion videos and audio records for each subject. To address twin recogntion, we propose to use face motion, talking pattern, voice, ear and face recognition. Eight papers are published and we won Best Hornorable Mention in FG2013.

We investigate large-scale face identification in unconstrained videos with 1000 subjects. This problem is very challenging, and until now most studies have only considered the scenarios with a small number of subjects and videos captured in controlled laboratory environments. First, we set up a large-scale video database in an unconstrained environment, Celebrity-1000, with data collected from video-sharing websites. Second, we boost the efficiency of multitask joint sparse representation (MTJSR) algorithm for video-based face identification on Celebrity-1000. Extensive experiments show several orders-of-magnitude speedup with this new optimization method, and also demonstrate the superiorities of the accelerated MTJSR algorithm over several popular baseline algorithms. Published in IEEE Transactions on Circuits and Systems for Video Technology 2014.