Face anti-spoofing is crucial to prevent face recognition systems from a security breach. Previous deep learning approaches formulate face anti-spoofing as a binary classification problem. Many of them struggle to grasp adequate spoofing cues and generalize poorly. In this paper, we argue the importance of auxiliary supervision to guide the learning toward discriminative and generalizable cues. A CNN-RNN model is learned to estimate the face depth with pixel-wise supervision, and to estimate rPPG signals with sequence-wise supervision. The estimated depth and rPPG are fused to distinguish live vs. spoof faces. Further, we introduce a new face anti-spoofing database that covers a large range of illumination, subject, and pose variations. Experiments show that our model achieves the state-of-theart results on both intra-and cross-database testing.

No abstract

Face anti-spoofing is designed to prevent face recognition systems from recognizing fake faces as the genuine users. While advanced face anti-spoofing methods are developed, new types of spoof attacks are also being created and becoming a threat to all existing systems. We define the detection of unknown spoof attacks as Zero-Shot Face Anti-spoofing (ZSFA). Previous ZSFA works only study 1-2 types of spoof attacks, such as print/replay, which limits the insight of this problem. In this work, we investigate the ZSFA problem in a wide range of 13 types of spoof attacks, including print, replay, 3D mask, and so on. A novel Deep Tree Network (DTN) is proposed to partition the spoof samples into semantic sub-groups in an unsupervised fashion. When a data sample arrives, being know or unknown attacks, DTN routes it to the most similar spoof cluster, and makes the binary decision. In addition, to enable the study of ZSFA, we introduce the first face anti-spoofing database that contains diverse types of spoof attacks. Experiments show that our proposed method achieves the state of the art on multiple testing protocols of ZSFA.

Many prior face anti-spoofing works develop discriminative models for recognizing the subtle differences between live and spoof faces. Those approaches often regard the image as an indivisible unit, and process it holistically, without explicit modeling of the spoofing process. In this work, motivated by the noise modeling and denoising algorithms, we identify a new problem of face despoofing, for the purpose of anti-spoofing: inversely decomposing a spoof face into a spoof noise and a live face, and then utilizing the spoof noise for classification. A CNN architecture with proper constraints and supervisions is proposed to overcome the problem of having no ground truth for the decomposition. We evaluate the proposed method on multiple face anti-spoofing databases. The results show promising improvements due to our spoof noise modeling. Moreover, the estimated spoof noise provides a visualization which helps to understand the added spoof noise by each spoof medium.

Grasslands occupy nearly three quarters of the land surface of the Qinghai-Tibet plateau (QTP) and play a critical role in regulating the ecological functions of the QTP. Ongoing climate change and human interference have greatly affected grasslands on the QTP. Differentiating human-induced and climate-driven vegetation changes is vital for both ecological understanding and the management of husbandry. In this study, we employed statistical analysis of annual records, various sources of remote sensing data, and an ecosystem process model to calculate the relative contribution of climate and human activities to vegetation vigor on the QTP. The temperature, precipitation and the intensity and spatial pattern of livestock grazing differed between the periods prior to and after the year 2000, which led to different vegetation dynamics. Overall, increased temperature and enhanced precipitation favored vegetation growth. However, their combined effects exhibited strong spatial heterogeneity. Specifically, increased temperature restrained vegetation growth in dry steppe regions during a period of slightly increasing precipitation from 1986 to 2000 and in meadow regions during a period of precipitation decline during 2000-2011, thereby making precipitation a dominant factor. An increase in precipitation tended to enhance vegetation growth in wet meadow regions during warm periods, and temperature was the limiting factor in Tibet during dry periods. The dominant role played by climate and human activities differed with location and targeted time period. Areas dominated by human activities are much smaller than those dominated by climate. The effects of grazing on grassland pasture were more obvious under unfavorable climate conditions than under suitable ones.