Abstract: Methods, systems, and computer programs are presented for adding new features to a network service. A method includes receiving an image depicting an object of interest. A category set is determined for the object of interest and an image signature is generated for the image. Using the category set and the image signature, the method identifies a set of publications within a publication database and assigns a rank to each publication. The method causes presentation of the ranked list of publications at a computing device from which the image was received.

Abstract: Disclosed are a fill light device, a method for controlling a fill light device, and a computer readable storage medium. The fill light device includes a flash light; and a light guide, the light guide being located on a light-exiting side of the flash light and being configured to be controlled to change a shape and/or a light-transmitting area to change a light-exiting area and/or a light-emitting angle of the fill light device. The method includes obtaining a control parameter of the light guide; and changing a shape and/or a light-transmitting area of the light guide according to the control parameter to change a light-exiting area and/or a light-emitting angle of the fill light device.

Abstract: An image processing method, device, storage medium and camera are provided. The method, applied to the camera, comprises: capturing a target image; acquiring a target feature map of the target image through a preset target convolution layer, wherein the target convolution layer includes at least one of a plurality of convolution layers of a convolutional neural network (CNN); and outputting the target feature map. That is to say, after the target image is captured by the camera, the target feature map may be acquired by processing the target image through the target convolution layer pre-integrated in the camera. In this way, the camera transmits the target feature map only to reduce the transmitted data volume, thereby being capable of shortening transmission delay and saving bandwidth required by image transmission.

Abstract: Disclosed herein is a system and method for augmenting data by generating a plurality of pose-altered images of an item from one or more 2D images of the item and using the augmented data to train a train a feature extractor. In other aspects of the invention, the trained feature extractor is used to enroll features extracted from images of new products in a library database of known products or to identify images of unknown products by matching features of an image of the unknown product with features stored in the library database.

Abstract: An information processing device is configured to output work information related to work performed by a serving person, the information processing device including an image acquisition unit configured to acquire an original image including a served person and a plurality of served objects that the serving person serves, an image division unit configured to divide the original image into a served-person image, in which the served person is captured, and a plurality of served-object images, in which each served object is captured, a scene estimation unit configured to estimate a scene, which is the situation the serving person is in, by using a first trained model, a chunk estimation unit configured to estimate a chunk, which is information dividing or suggesting the work information, by using one of a plurality of second trained models, and an output unit configured to output the chunk.

Abstract: In a case where the operation program is started, a CPU of the mini-batch learning apparatus functions as a calculation unit, a specifying unit, and an update unit. The calculation unit calculates an area ratio of each of a plurality of classes in mini-batch data. The specifying unit specifies a rare class of which the area ratio is lower than a setting value. The update unit sets an update level of the machine learning model in a case where the rare class is specified by the specifying unit to be lower than an update level of the machine learning model in a case where the rare class is not specified by the specifying unit.

Abstract: Techniques are disclosed for identifying and presenting video content that demonstrates features of a target product. The video content can be accessed, for example, from a media database of user-generated videos that demonstrate one or more features of the target product so that a user can see and hear the product in operation via a product webpage before making a purchasing decision. The product functioning videos supplement any static images of the target product and the textual product description to provide the user with additional context for each of the product's features, depending on the textual product description. The user can quickly and easily interact with the product webpage to access and playback the product functioning video to see and/or hear the product in operation.

Abstract: Examples are disclosed that relate to the restoration of degraded images acquired via a behind-display camera. One example provides a method of training a machine learning model, the method comprising inputting training image pairs into the machine learning model, each training image pair comprising an undegraded image and a degraded image that represents an appearance of the undegraded image to a behind-display camera, and training the machine learning model using the training image pairs to generate frequency information that is missing from the degraded images.

Abstract: Embodiments of an electronic device include an integrated circuit, a reconfigurable stream switch formed in the integrated circuit along with a plurality of convolution accelerators and a decompression unit coupled to the reconfigurable stream switch. The decompression unit decompresses encoded kernel data in real time during operation of convolutional neural network.

Abstract: An improved system architecture uses a pipeline including a Generative Adversarial Network (GAN) including a generator neural network and a discriminator neural network to generate an image. An input image in a first domain and information about a target domain are obtained. The domains correspond to image styles. An initial latent space representation of the input image is produced by encoding the input image. An initial output image is generated by processing the initial latent space representation with the generator neural network. Using the discriminator neural network, a score is computed indicating whether the initial output image is in the target domain. A loss is computed based on the computed score. The loss is minimized to compute an updated latent space representation. The updated latent space representation is processed with the generator neural network to generate an output image in the target domain.

Abstract: A method for detecting blurriness of a human face in an image includes: performing a face detection in a target image; when a human face is detected in the target image, cropping the human face from the target image to obtain a face image and inputting the face image to a first neural network model to perform preliminary detection on a blurriness of the human face in the face image to obtain a preliminary detection result; and when the preliminary detection result meets a deep detection condition, inputting the face image to a second neural network model to perform deep detection on the blurriness of the human face in the face image to obtain a deep detection result.

Abstract: A normalization method for machine learning and an apparatus thereof are provided. The normalization method according to some embodiments of the present disclosure may calculate a value of a normalization parameter for an input image through a normalization model before inputting the input image to a target model and normalize the input image using the calculated value of the normalization parameter. Because the normalization model is updated based on a prediction loss of the target model, the input image can be normalized to an image suitable for a target task, so that stability of the learning and performance of the target model can be improved.

Abstract: A neural network is trained to process input data and generate a classification value that characterizes the input with respect to an ordered continuum of classes. For example, the input data may comprise an image and the classification value may be indicative of a quality of the image. The ordered continuum of classes may represent classes of quality of the image ranging from “worst”, “bad”, “normal”, “good”, to “best”. During training, loss values are determined using an ordered classification loss function. The ordered classification loss function maintains monotonicity in the loss values that corresponds to placement in the continuum. For example, the classification value for a “bad” image will be less than the classification value indicative of a “best” image. The classification value may be used for subsequent processing. For example, biometric input data may be required to have a minimum classification value for further processing.

Abstract: A system includes receiving data associated with an account, the data having a plurality of members; generating based on an ensemble teacher model, a deep learning model having a number of layers; inputting a plurality of members determined to be daily inputs into the deep learning model; extracting a daily pattern from the daily inputs and aggregating a deep learning model output; inputting the global inputs and an aggregated deep learning model output into a classifier; outputting from the classifier, a number of scores combined into a single score for the account. Further, the device may include alerting a user if the single score falls outside of a predetermined threshold.

Abstract: Systems and methods for clustering data are disclosed. For example, a system may include one or more memory units storing instructions and one or more processors configured to execute the instructions to perform operations. The operations may include receiving data from a client device and generating preliminary clustered data based on the received data, using a plurality of embedding network layers. The operations may include generating a data map based on the preliminary clustered data using a meta-clustering model. The operations may include determining a number of clusters based on the data map using the meta-clustering model and generating final clustered data based on the number of clusters using the meta-clustering model. The operations may include and transmitting the final clustered data to the client device.

Abstract: A system and method of re-identifying players in a broadcast video feed are provided herein. A computing system retrieves a broadcast video feed for a sporting event. The broadcast video feed includes a plurality of video frames. The computing system generates a plurality of tracks based on the plurality of video frames. Each track includes a plurality of image patches associated with at least one player. Each image patch of the plurality of image patches is a subset of the corresponding frame of the plurality of video frames. For each track, the computing system generates a gallery of image patches. A jersey number of each player is visible in each image patch of the gallery. The computing system matches, via a convolutional autoencoder, tracks across galleries. The computing system measures, via a neural network, a similarity score for each matched track and associates two tracks based on the measured similarity.

Abstract: Techniques for performing visual clustering with a hierarchical graph neural network framework including a joint linkage prediction and density estimation graph model are described. Embodiments herein recurrently run the joint linkage prediction and density estimation graph model to generate intermediate clusters in multiple iterations (e.g., until convergence) to obtain a final clustering result. In certain embodiments, for each iteration, the input graph contains nodes that are merged from nodes assigned to intermediate clusters from the previous iteration. By using a small and fixed bandwidth k in each iteration, embodiments herein alleviate the sensitivity to the k selection for different clustering applications. Certain embodiments herein remove the tuning of a different k (e.g., k-bandwidth) for k-nearest neighbor graph construction over different clustering applications.

Abstract: Aspects of the disclosure can provide a method, a corresponding target video processing package may be automatically obtained through matching according to scene description information, so that an operation of manually making a selection by a user in the related art is omitted. Therefore, matching efficiency of video processing manners may be improved. In addition, a plurality of video processing manners may be obtained through matching at a time, so that the matching efficiency is further improved. In addition, because the target video processing package is dynamically and correspondingly obtained through matching based on the scene description information, the target video processing package obtained through matching can be caused to accord with actual video content as much as possible. Further, accuracy of video processing may be improved, to satisfy an actual requirement of a user as much as possible.

Abstract: A mobile client device includes a photo controller to identify when a client device captures a picture. Photo filters are designated based upon attributes of the mobile client device. The picture with a selected photo filter is sent to a server for routing to other client devices.

Abstract: An image processing device includes an image acquisition unit that acquires a captured image to be processed from a storage unit in which a captured image having first date/time information indicating a time of imaging is stored, a date/time information acquisition unit that acquires the first date/time information and acquires second date/time information indicating a date/time when the captured image to be processed is acquired, an elapsed date/time calculation unit that calculates an elapsed date/time from the time of imaging by making a comparison between the first date/time information and the second date/time information, and an image processing unit that selects image processing based on a length of the elapsed date/time from among a plurality of kinds of image processing that change according to the length of the elapsed date/time and performs the selected image processing on the captured image to be processed.