Systems and methods are provided for receiving a plurality of images corresponding to a listing in an online marketplace, generating a scene type for each image of the plurality of images, and grouping each image into a scene type group of a set of predefined scene types. Each group of images are input into a respective machine learning model specific to the scene type of the group of images to generate a visual score for each image in each group of images, and an attractiveness score is generated for the listing in the online marketplace based on the visual scores for each image in each group of images.

Techniques for improved image classification are provided. Face embeddings are generated for each face depicted in a collection of images, and the face embeddings are clustered based on the individual whose face is depicted. Based on these clusters, each embedding is assigned a label reflecting the cluster assignments. Some or all of the face embeddings are then used to train a classifier model to generate cluster labels for new input images. This classifier model can then be used to process new images in an efficient manner, and classify them into appropriate clusters.

Biometrics fingerprint matching has been done with a heavily hand-tuned and designed process of classical computer vision techniques for several decades. This approach has led to accurate solutions for solving crimes today and, as such, little effort has been devoted to using deep learning in this domain. Exemplary embodiments disclosed herein leverage synthetic data generators to train a neural fingerprint enhancer to improve matching accuracy on real fingerprint images.

A system described herein may provide a technique for identifying states associated with service providers based on biometric, sensor, and/or other information associated with a set of service providers. A request for service may be received, and a particular service provider may be selected based on a particular state associated with the particular service provider, as determined based on the biometric, sensor, and/or other information associated with the particular service provider. State information associated with a requestor of the service may be identified and used as a factor in selecting the particular service provider to respond to the service request.

Various disclosed examples pertain to digital pathology, more specifically to training of a segmentation algorithm for segmenting whole-slide images depicting tissue of multiple types. An initial annotation of a whole-slide image is refined to yield a refined annotation based on which parameters of the segmentation algorithm can be set. Techniques of patch-wise weak supervision can be employed for such refinement.

A method and apparatus for recognizing a sign language or a gesture by using a three-dimensional (3D) Euclidean distance matrix (EDM) are disclosed. The method includes a two-dimensional (2D) EDM generation step for generating a 2D EDM including information about distances between feature points of a body recognized in image information by a 2D EDM generator, a 3D EDM generation step for receiving the 2D EDM and generating a 3D EDM by using a first deep learning neural network trained with training data in which input data is a 2D EDM and correct answer data is a 3D EDM by a 3D EDM generator, and a recognition step for recognizing a sign language or a gesture based on the 3D EDM.

Conventionally, activity detection has been through one mode i.e., smart watch. Though it works in reasonable cases, there are chances of false positives considerably. Other approaches include surveillance which limits itself to object detection. Embodiments of present disclosure provide systems and methods for detecting activities performed by user from data captured from multiple sensors. A first input (FI) comprising accelerometer data, heart rate and gyroscope data and second input (SI) comprising video data are obtained. Features are extracted from FI and pre-processed for a first activity (FA) detection using activity prediction model. Frames from SI are processed for creating bounding box of user and resized thereof to extract pose coordinates vector. Distance between vector of pose coordinates and training vectors of pose coordinates stored in the system is computed and a second activity (SA) is detected accordingly. Both the FA and SA are validated for determining true and/or false positive.

Generating visual data by defining a first action into a first set of objects and corresponding first set of motions, and defining a second action into a second set of objects and corresponding second set of motions. A relationship is then determined for the second action to the first action in terms of relationships between corresponding constituent objects and motions. Objects and motions are detected from visual data of first action. Visual data is composed for the second action from the data by transforming the constituent objects and motions detected in first action based on the corresponding determined relationships.

An information processing device of the present invention includes: an image processing means that extracts a feature value of an object within a captured image obtained by capturing a pre-passing region of a gate, and stores matching information relating to matching of the object based on the feature value; a distance estimating means that estimates a distance from the gate to the object within the captured image; and a matching means that executes matching determination based on the estimated distance and the stored matching information of the object that the distance has been estimated.

A display module includes: a liquid crystal module, a cover plate, and a texture recognition unit. The texture recognition unit includes a first light source and a texture sensing module. The first light source is located at a side of the cover plate proximate to the liquid crystal module, and is configured to emit invisible light. The texture sensing module is located at a side of the liquid crystal module facing away from the cover plate. A light wavelength range of light allowed to pass through the cover plate and the liquid crystal module includes a light wavelength range of the invisible light. The texture sensing module is configured to collect reflected light after the invisible light is irradiated to a target object, so as to identify a texture of the target object.