Abstract: In some examples, an embolization device includes multiple sections with three-dimensional non-helical structures when deployed at a vascular site. The multiple sections include a first section and one or more second sections that are smaller than the first section. The first section may have a deployed structure configured to anchor the device at a vascular site (e.g., a blood vessel) of a patient while each of the one or more second sections may be formed from loops that configured to pack and obstruct the vascular site. In some cases, the embolization device also includes a third section having a deployed configuration with multiple helical windings or loops is configured to anchor the embolization device at the vascular site.

Abstract: Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a user equipment (UE) may receive configuration information that indicates an uplink transmit switching configuration for performing uplink transmit switching between a first component carrier and a second component carrier and a sounding reference signal (SRS) carrier switching configuration for performing SRS carrier switching between the second component carrier and a third component carrier, wherein the configuration information is associated with a maximum number of allowable switches over an amount of time. The UE may transmit, based at least in part on the configuration information, one or more signals associated with performing at least one of uplink transmit switching or SRS carrier switching. Numerous other aspects are described.

Abstract: A disclosed face detection system (and method) is based on a structure of a convolutional neural network (CNN). One aspect concerns a method for automatically training a CNN for face detection. The training is performed such that balanced number of face images and non-face images are used for training by deriving additional face images from the face images. The training is also performed by adaptively changing a number of trainings of a stage according to automatic stopping criteria. Another aspect concerns a system for performing image detection by integrating data at different scales (i.e., different image extents) for better use of data in each scale. The system may include CNNs automatically trained using the method disclosed herein.

Abstract: Provided are a living-body detection method and device and a computer program product, belonging to the technical field of face recognition. The living-body detection method comprises: detecting a facial movement from a photograph image; according to said detected facial movement, controlling the display of a virtual object on a display screen; and, if said virtual object satisfies predetermined conditions, determining that the face in said photographed image is a living-body face. By controlling virtual-object display on the basis of face movements and performing living-body detection according to virtual-object display, it is possible to effectively prevent an attack using such means as photograph, video, 3D face model, or face mask.

Abstract: The application relates to a video detection method, a video detection system, and a computer program product, which can implement liveness detection for a human body. The video detection method comprises: obtaining video data acquired by a video data acquisition device; determining a to-be-detected object based on the video data; obtaining a to-be-detected signal corresponding to the to-be-detected object; and determining whether the to-be-detected signal is a liveness physiological signal, wherein the to-be-detected signal is a frequency domain signal corresponding to the video data of the to-be-detected object.

Abstract: Disclosed are a method and a system for authenticating liveness face, and a computer program product thereof, which belong to a field of face recognition technique. The method for authenticating liveness face comprises: generating a sequence of action instructions randomly; and determining a success of the authentication of the liveness face when face actions are determined to be matched with the sequence of action instructions sequentially. The authentication of the liveness face can be performed based on fine head actions, so that a cost for authenticating the liveness face is decreased, an accuracy of authentication of the liveness face is increased.

Abstract: The application relates to a video detection method, a video detection system, and a computer program product, which can implement liveness detection for a human body.

Abstract: A disclosed facial recognition system (and method) includes face parsing. In one approach, the face parsing is based on hierarchical interlinked multiscale convolutional neural network (HIM) to identify locations and/or footprints of components of a face image. The HIM generates multiple levels of image patches from different resolution images of the face image, where image patches for different levels have different resolutions. Moreover, the HIM integrates the image patches for different levels to generate interlinked image patches for different levels, where interlinked image patches for different levels have different resolutions. Furthermore, the HIM combines the interlinked image patches to identify refined locations and/or footprints of components.

Abstract: Disclosed are a method and a system for authenticating liveness face, and a computer program product thereof, which belong to a field of face recognition technique. The method for authenticating liveness face comprises: generating a sequence of action instructions randomly; and determining a success of the authentication of the liveness face when face actions are determined to be matched with the sequence of action instructions sequentially. The authentication of the liveness face can be performed based on fine head actions, so that a cost for authenticating the liveness face is decreased, an accuracy of authentication of the liveness face is increased.

Abstract: Face hallucination using a bi-channel deep convolutional neural network (BCNN), which can adaptively fuse two channels of information. In one example, the BCNN is implemented to extract high level features from an input image. The extracted high level features are combined with low level details in the input image to produce the higher resolution image. Preferably, a proper coefficient is obtained to adaptively combine the high level features and the low level details.

Abstract: The present invention overcomes the limitations of the prior art by performing facial landmark localization in a coarse-to-fine manner with a cascade of neural network levels, and enforcing geometric constraints for each of the neural network levels. In one approach, the neural network levels may be implemented with deep convolutional neural network. One aspect concerns a system for localizing landmarks on face images. The system includes an input for receiving a face image, and an output for presenting landmarks identified by the system. Neural network levels are coupled in a cascade from the input to the output for the system. Each neural network level produces an estimate of landmarks. The estimate of landmarks is more refined than an estimate of landmark of a previous neural network level.

Abstract: A deep learning framework jointly optimizes the compactness and discriminative ability of face representations. The compact representation can be as compact as 32 bits and still produce highly discriminative performance. In another aspect, based on the extreme compactness, traditional face analysis tasks (e.g. gender analysis) can be effectively solved by a Look-Up-Table approach given a large-scale face data set.

Abstract: Face representation is a crucial step of face recognition systems. An optimal face representation should be discriminative, robust, compact, and very easy to implement. While numerous hand-crafted and learning-based representations have been proposed, considerable room for improvement is still present. A very easy-to-implement deep learning framework for face representation is presented. The framework bases on pyramid convolutional neural network (CNN). The pyramid CNN adopts a greedy-filter-and-down-sample operation, which enables the training procedure to be very fast and computation efficient. In addition, the structure of Pyramid CNN can naturally incorporate feature sharing across multi-scale face representations, increasing the discriminative ability of resulting representation.

Abstract: A disclosed face detection system (and method) is based on a structure of a convolutional neural network (CNN). One aspect concerns a method for automatically training a CNN for face detection. The training is performed such that balanced number of face images and non-face images are used for training by deriving additional face images from the face images. The training is also performed by adaptively changing a number of trainings of a stage according to automatic stopping criteria. Another aspect concerns a system for performing image detection by integrating data at different scales (i.e., different image extents) for better use of data in each scale. The system may include CNNs automatically trained using the method disclosed herein.

Abstract: A disclosed facial recognition system (and method) includes face parsing. In one approach, the face parsing is based on hierarchical interlinked multiscale convolutional neural network (HIM) to identify locations and/or footprints of components of a face image, The HIM generates multiple levels of image patches from different resolution images of the face image, where image patches for different levels have different resolutions. Moreover, the HIM integrates the image patches for different levels to generate interlinked image patches for different levels, where interlinked image patches for different levels have different resolutions. Furthermore, the HIM combines the interlinked image patches to identify refined locations and/or footprints of components.

Abstract: Face hallucination using a bi-channel deep convolutional neural network (BCNN), which can adaptively fuse two channels of information. In one example, the BCNN is implemented to extract high level features from an input image. The extracted high level features are combined with low level details in the input image to produce the higher resolution image. Preferably, a proper coefficient is obtained to adaptively combine the high level features and the low level details.

Abstract: A deep learning framework jointly optimizes the compactness and discriminative ability of face representations. The compact representation can be as compact as 32 bits and still produce highly discriminative performance. In another aspect, based on the extreme compactness, traditional face analysis tasks (e.g. gender analysis) can be effectively solved by a Look-Up-Table approach given a large-scale face data set.

Abstract: The present invention overcomes the limitations of the prior art by performing facial landmark localization in a coarse-to-fine manner with a cascade of neural network levels, and enforcing geometric constraints for each of the neural network levels. In one approach, the neural network levels may be implemented with deep convolutional neural network. One aspect concerns a system for localizing landmarks on face images. The system includes an input for receiving a face image, and an output for presenting landmarks identified by the system. Neural network levels are coupled in a cascade from the input to the output for the system. Each neural network level produces an estimate of landmarks. The estimate of landmarks is more refined than an estimate of landmark of a previous neural network level.

Abstract: Face representation is a crucial step of face recognition systems. An optimal face representation should be discriminative, robust, compact, and very easy to implement. While numerous hand-crafted and learning-based representations have been proposed, considerable room for improvement is still present. A very easy-to-implement deep learning framework for face representation is presented. The framework bases on pyramid convolutional neural network (CNN). The pyramid CNN adopts a greedy-filter-and-down-sample operation, which enables the training procedure to be very fast and computation efficient. In addition, the structure of Pyramid CNN can naturally incorporate feature sharing across multi-scale face representations, increasing the discriminative ability of resulting representation.

Abstract: Described herein are techniques for obtaining compact face descriptors and using pose-specific comparisons to deal with different pose combinations for image comparison.