Abstract: Systems and methods are described for recommending pairs or sets of clothing items for an individual to wear together, including learning a compatibility metric personalized to each individual. A framework is used to learn compatibility that is personalized to the user based on initial item feedback that may be received from the user via user interfaces that prompt the user to indicate whether the user would wear certain clothing items together and/or individually.

Abstract: Systems and methods are described for generating images of synthesized bodies wearing a garment. For instance, a source image of a human or mannequin wearing a garment may be submitted to a synthesized human generation system. In response to receiving the source image, the synthesized human generation system may use a classifier to classify the image as depicting one or more body types or orientations. The synthesized human generation system may also apply segmentation to the source image to segment the garment pixels. The synthesized human generation system may then select one or more body generation machine learning models based on the classification of the source image. The synthesized human generation system may utilize the selected machine learning models to generate one or more output images of synthesized bodies that appear to be wearing the garment, using the segmented garment as input.

Abstract: An example method of complementary consumer item selection includes: receiving, by a computer system, an image representing a first consumer item of a reference set of consumer items; identifying a target category of a complementary consumer item to be associated with the reference set of consumer items; generating, by a neural network processing the set of images, a feature embeddings representing the first consumer item in relation to the target category; selecting, using the feature embedding, from a set of available consumer items, a plurality of candidate consumer items associated with the target category; and selecting, among the plurality of candidate consumer items, the complementary consumer item to be associated with the reference set of consumer items.

Abstract: The present invention relates to a filter device for separating debris from a fluid. The filter device includes a housing having at least one inlet, at least one first outlet, and a second outlet. The filter device further includes a filter cartridge that allows fluid to pass therethrough but prevents passage of debris therethrough. The filter cartridge is positioned within the housing so as to define an upper chamber and a lower chamber within the housing. The at least one inlet is positioned so as to allow contaminated fluid to enter the lower chamber of the housing. Fluid must pass through the filter cartridge in an upward direction to reach the upper chamber, and the first outlet is positioned so as to allow filtered fluid to exit the upper chamber. The second outlet is positioned to allow debris accumulated within the lower chamber to be discharged.

Abstract: Multi-modal data representing driving events and corresponding actions related to the driving events can be obtained and used to train a neural network at least in part by using a triplet loss computed for the driving events as a regression loss to determine an embedding of driving event data. In some cases, using the trained neural network, a retrieval request for an input driving event and corresponding action can be processed by determining, from the neural network, one or more similar driving events or corresponding actions in the multi-modal data.

Abstract: Methods, systems, and computer-readable mediums storing computer executable code for visual recognition implementing a triplet loss function are provided. The method include receiving an image generated from an image source associated with a vehicle. The method may also include analyzing the image based on a convolutional neural network. The convolutional neural network may apply both a triplet loss function and a softmax loss function to the image to determine classification logits. The method may also include classifying the image into a predetermined class distribution based upon the determined classification logits. The method may also include instructing the vehicle to perform a specific task based upon the classified image.

Abstract: A method for attaching a rear frame suspension module to an existing vehicle that will operate on the existing automotive engine, heating, and cooling system. The rear frame suspension module supports passengers sitting straddled in a front to back position to give an existing vehicle a motorcycle-like appearance. The rear suspension module can be attached and removed from an existing automobile front frame suspension module. The resulting wider front structure of the vehicle makes for safer riding compared to a two wheel motorcycle. Vehicle maintenance can be done at most automotive repair shops.

Abstract: Existing vehicle front frame suspension module. The technical disclosure of the innovative vehicle will operate on the existing automotive engine, heating and cooling system. Vehicle wider front structure which makes safer riding compared to a two wheel motorcycle. The handicapped will be able to see this innovate vehicle is easier to ride than a two wheel motorcycle. Vehicle maintenance can be done at most automotive repair shops. Vehicle rear suspension module can be attached and removed from an existing premanufactured automobile front frame suspension module.

Abstract: The present invention relates to a filter device for separating debris from a fluid. The filter device includes a housing having at least one inlet, at least one first outlet, and a second outlet. The filter device further includes a filter cartridge that allows fluid to pass therethrough but prevents passage of debris therethrough. The filter cartridge is positioned within the housing so as to define an upper chamber and a lower chamber within the housing. The at least one inlet is positioned so as to allow contaminated fluid to enter the lower chamber of the housing. Fluid must pass through the filter cartridge in an upward direction to reach the upper chamber, and the first outlet is positioned so as to allow filtered fluid to exit the upper chamber. The second outlet is positioned to allow debris accumulated within the lower chamber to be discharged.

Abstract: The vehicle will support two or more passengers moving from Point A to Point B—the grocery store, a friend's house, to work or out on out-of-town trips. Because of its new ornamental design, the public will be pleased with its motorcycle and automobile characteristics. Passengers don't have to hold up the weight of the vehicle with their legs, compared to a two-wheel motorcycle. The public will enjoy the open seating compartment to Mother Nature, enjoying the hot or cold climate. The new vehicle will have its own heating and cooling system which can be adjusted by the passenger for climate control when there is a change in the temperature around them. Passengers will be seated in an open compartment, having fun, relieving stress, and seeing everything around them. Compared to a two-wheel motorcycle, the new vehicle is more visible on the road and highway, making it safer for passengers in case of a highway accident.

Abstract: Automated person re-identification may be assisted by consideration of attributes of the person in a joint classification with matching of the person. By both solving for similarities in a plurality of attributes and identities, discriminative interactions may be captured. Automated person re-identification may be assisted by consideration of a semantic color name. Rather than a color histogram, probability distributions are mapped to color terms of the semantic color name. Using other descriptors as well, similarity measures for the various descriptors are weighted and combined into a score. Either or both considerations may be used.

Abstract: The invention relates to 2-alkyl-6-cycloamino-3-(pyridin-4-yl)imidazo[1,2-b]pyridazine derivatives of the general formula (I) where: R2 is a C1-6-alkyl, C3-7-cycloalkyl, C3-7-cycloalkyl-C1-4-alkyl, C1-4-alkyloxy-C-M-alkyl, C3-7-cycloalkyloxy-C1-4-alkyl>C3-7-cycloalkyl-C1-4-alkyloxy-C1-4-alkyl, hydroxy-C1-6-alkyl, C1-4-fluoroalkyl group; R3 is a hydrogen atom or a substituent selected from halogen atoms and the C1-3 alkyl, —NR4R5, hydroxyl or C1-4 alkyloxy groups; A is a C1-7-alkylene group optionally substituted by one or two Ra groups; B is a C1-7-alkylene group optionally substituted by one or two Rb groups; L is either a nitrogen atom optionally substituted by an Rc or Rd group or a carbon atom substituted by an Re1 group and an Rd group or by two Re2 groups; Rd is a group selected from a hydrogen atom or a C1-6-alkyl, C3-7-cycloalkyl, C3-7-cycloalkyl-C1-6-alkyl, C1-6-alkylthio-C1-6-alkyl, C1-6-alkyloxy-C1-6-alkyl, C1-6-fluoroalkyl, hydroxy-C1-6-alkyl group; Rf is a C1-6-alkyl, C3-7-cycloalkyl, C3-7-cyc

Abstract: A multi-camera system that collects images and videos of moving objects in dynamic and crowded scenes, subject to task constraints is disclosed. The system constructs “task visibility intervals” comprising information about what can be sensed in future time intervals. Methods for constructing these intervals applying prediction of future object motion and including consideration of factors such as object occlusion and camera control parameters are also disclosed. Using a plane-sweep algorithm, these atomic intervals can be combined in a method to form multi-task intervals, during which a single camera can collect videos suitable for multiple tasks simultaneously. Methods for fast camera scheduling that yield solutions within a small constant factor of an optimal solution are also disclosed.

Abstract: An improved animal tag for application to an animal's ear which comprises a male portion that includes a flat segment and a projection segment, a female portion that includes a generally square or generally oval shaped flat segment and a raised segment with an aperture; wherein the projection segment of the male portion is adapted to be inserted through the animal's ear and into the aperture when pressure is applied thereto.

Abstract: A method for eliminating errors in foreground object detection in digitized images comprises providing a reference camera and a secondary camera, vertically aligning each said camera with a baseline that is approximately perpendicular to a ground plane, wherein said reference camera is placed lower than said secondary camera, selecting a foreground pixel in a reference view of a first point in a foreground object, finding a conjugate pixel of the foreground pixel in a secondary view, using the foreground and conjugate pixels to determine an image base pixel of a base point in the reference view, wherein said base point is a point on the ground plane below the first point, and using the foreground and image base pixels to find a location where the ground plane is first visible.

Abstract: The present invention extends to the compound of formula I: or a prodrug, pharmaceutically acceptable salt, or solvate of said compound. Furthermore, the present invention is directed to a pharmaceutical composition comprising a pharmaceutically effective amount of the compound of formula I, and a pharmaceutically acceptable carrier. Furthermore, the present invention is directed to the use of a compound of formula I as an inhibitor of tryptase, comprising introducing the compound into a composition comprising tryptase. In addition, the present invention is directed to the use of a compound of formula I for treating a patient suffering from, or subject to, a physiological condition in need of amelioration of an inhibitor of tryptase comprising administering to the patient a therapeutically effective amount of the compound of claim 1 The present invention is directed also to the preparation of a compound of formula I.

Abstract: A crane tower device includes a basket that supports a tower crane and sits within a bay formed by the vertical columns of a building under construction. The basket and the tower crane are supported by support stubs that are attached to the vertical columns. Because the lateral and vertical load is principally distributed vertically to the vertical columns rather than horizontally, no reinforcement of the horizontal beams, floors or any other portion of the building structure are needed, which results in substantial cost savings.

Abstract: A multi-camera system that collects images and videos of moving objects in dynamic and crowded scenes, subject to task constraints is disclosed. The system constructs “task visibility intervals” comprising information about what can be sensed in future time intervals. Methods for constructing these intervals applying prediction of future object motion and including consideration of factors such as object occlusion and camera control parameters are also disclosed. Using a plane-sweep algorithm, these atomic intervals can be combined in a method to form multi-task intervals, during which a single camera can collect videos suitable for multiple tasks simultaneously. Methods for fast camera scheduling that yield solutions within a small constant factor of an optimal solution are also disclosed.