Abstract: A method of combinatorial optimization using hybrid temporo-attentional branching. Variable embeddings for the variable features, constraint embeddings for constraint features and edge embeddings for edge features are generated for each mixed integer linear program (MILP) sample in a dataset. The constraint embeddings are updated by a first graph attention network (GAT) of a neural network based on an attention of neighbouring nodes using the variable embeddings, constraint embeddings and edge embeddings. The variable embeddings are updated by a second GAT of the neural network based on an attention of neighbouring nodes using the variable embeddings, updated constraint embeddings and edge embeddings. A Gated Recurrent Unit (GRU) of the neural network generates a representation vector based on the updated variable embeddings for an input sequence consisting of all MILP samples in the dataset. Variables for a first MILP sample are selected from the representation vector in accordance with a branching policy.

Abstract: Embodiments described herein provide various examples of an age and gender estimation system capable of performing age and gender classifications on face images having sizes greater than the maximum number of input pixels supported by a given small-scale hardware convolutional neural network (CNN) module. In some embodiments, the proposed age and gender estimation system can first divide a high-resolution input face image into a set of image patches with judiciously designed overlaps among neighbouring patches. Each of the image patches can then be processed with a small-scale CNN module, such as the built-in CNN module in Hi3519 SoC. The outputs corresponding to the set of image patches can be subsequently merged to obtain the output corresponding to the input face image, and the merged output can be further processed by subsequent layers in the age and gender estimation system to generate age and gender classifications for the input face image.

Abstract: Embodiments described herein provide various examples of a real-time face-detection, face-tracking, and face-pose-selection subsystem within an embedded video system. In one aspect, a process for performing real-time face-pose-estimation and best-pose selection for a detected person captured in a video is disclosed. This process includes the steps of: receiving a video image among a sequence of video frames of a video; performing a face detection operation on the video image to detect a set of faces in the video image; detecting a new person appears in the video based on the set of detected faces; tracking the new person through subsequent video images in the video by detecting a sequence of face images of the new person in the subsequent video images; and for each of the subsequent video images which contains a detected face of the new person being tracked: estimating a pose associated with the detected face and updating a best pose for the new person based on the estimated pose.

Abstract: Embodiments described herein provide various examples of a joint face-detection and head-pose-angle-estimation system based on using a small-scale hardware CNN module such as the built-in CNN module in HiSilicon Hi3519 system-on-chip. In some embodiments, the disclosed joint face-detection and head-pose-angle-estimation system is configured to jointly perform multiple tasks of detecting most or all faces in a sequence of video frames, generating pose-angle estimations for the detected faces, tracking detected faces of a same person across the sequence of video frames, and generating “best-pose” estimation for the person being tracked. The disclosed joint face-detection and pose-angle-estimation system can be implemented on resource-limited embedded systems such as smart camera systems that are only integrated with one or more small-scale CNN modules.

Abstract: Embodiments described herein provide various examples of a real-time face-detection, face-tracking, and face-pose-selection subsystem within an embedded video system. In one aspect, a process for performing real-time face-pose-estimation and best-pose selection for a detected person captured in a video is disclosed. This process includes the steps of: receiving a video image among a sequence of video frames of a video; performing a face detection operation on the video image to detect a set of faces in the video image; detecting a new person appears in the video based on the set of detected faces; tracking the new person through subsequent video images in the video by detecting a sequence of face images of the new person in the subsequent video images; and for each of the subsequent video images which contains a detected face of the new person being tracked: estimating a pose associated with the detected face and updating a best pose for the new person based on the estimated pose.

Abstract: Embodiments described herein provide various examples of a face detection system, based on using a small-scale hardware convolutional neural network (CNN) module configured into a multi-task cascaded CNN. In some embodiments, a subimage-based CNN system can be configured to be equivalent to a large-scale CNN that processes the entire input image without partitioning such that the output of the subimage-based CNN system can be exactly identical to the output of the large-scale CNN. Based on this observation, some embodiments of this patent disclosure make use of the subimage-based CNN system and technique on one or more stages of a cascaded CNN or a multitask cascaded CNN (MTCNN) so that a larger input image to a given stage of the cascaded CNN or the MTCNN can be partitioned into a set of subimages of a smaller size. As a result, each stage of the cascaded CNN or the MTCNN can use the same small-scale hardware CNN module that is associated with a maximum input image size constraint.

Abstract: Embodiments described herein provide various examples of a joint face-detection and head-pose-angle-estimation system based on using a small-scale hardware CNN module such as the built-in CNN module in HiSilicon Hi3519 system-on-chip. In some embodiments, the disclosed joint face-detection and head-pose-angle-estimation system is configured to jointly perform multiple tasks of detecting most or all faces in a sequence of video frames, generating pose-angle estimations for the detected faces, tracking detected faces of a same person across the sequence of video frames, and generating “best-pose” estimation for the person being tracked. The disclosed joint face-detection and pose-angle-estimation system can be implemented on resource-limited embedded systems such as smart camera systems that are only integrated with one or more small-scale CNN modules.

Abstract: Embodiments described herein provide various examples of an age and gender estimation system capable of performing age and gender classifications on face images having sizes greater than the maximum number of input pixels supported by a given small-scale hardware convolutional neutral network (CNN) module. In some embodiments, the proposed age and gender estimation system can first divide a high-resolution input face image into a set of image patches with judiciously designed overlaps among neighbouring patches. Each of the image patches can then be processed with a small-scale CNN module, such as the built-in CNN module in Hi3519 SoC. The outputs corresponding to the set of image patches can be subsequently merged to obtain the output corresponding to the input face image, and the merged output can be further processed by subsequent layers in the age and gender estimation system to generate age and gender classifications for the input face image.

Abstract: Embodiments described herein provide various examples of a face detection system, based on using a small-scale hardware convolutional neutral network (CNN) module configured into a multi-task cascaded CNN. In some embodiments, a subimage-based CNN system can be configured to be equivalent to a large-scale CNN that processes the entire input image without partitioning such that the output of the subimage-based CNN system can be exactly identical to the output of the large-scale CNN. Based on this observation, some embodiments of this patent disclosure make use of the subimage-based CNN system and technique on one or more stages of a cascaded CNN or a multitask cascaded CNN (MTCNN) so that a larger input image to a given stage of the cascaded CNN or the MTCNN can be partitioned into a set of subimages of a smaller size. As a result, each stage of the cascaded CNN or the MTCNN can use the same small-scale hardware CNN module that is associated with a maximum input image size constraint.