A vision transformer includes L layers, and H attention heads in each layer. An h′ of the attention heads include an attention mask added before a Softmax operation, and an h of the attention heads include unmasked attention heads in which H=h′+h. Each attention mask multiplies a Query vector and a Key vector for form element-wise products. At least one attention mask is a hard mask that selects closest neighbors of a patch and ignores patches further away than the closest neighbors of the patch. Alternatively, at least one attention mask includes a soft mask that multiplies weights of closest neighbors of a patch by a magnification factor and passes weights of patches that are further away than the closest neighbors of the patch. A learnable bias α may be added to diagonal elements of the at least one attention map.

A system determines an amount of paint required for a painting job. It performs the following: (a) receive an image of a surface, e.g. part of an automobile. The image comprises an indication of a region of the image, including a sub-region of the surface to be painted; (b) receive a user identification of a painter who will perform a painting job; (c) receive an indication of a paint coverage capability associated with the painter; (d) process the image to determine the sub-region; (e) calculate an area of the sub-region; (f) received an indication of a coverage capability of the paint to be utilized in the painting job; (g) determine the amount of paint, based at least on the area of the sub-region and on the painter paint coverage capability; (h) output an indication of the amount of paint required.

A system determines an amount of paint required for a painting job. It performs the following: (a) receive an image of a surface, e.g. part of an automobile. The image comprises an indication of a region of the image, including a sub-region of the surface to be painted; (b) receive a user identification of a painter who will perform a painting job; (c) receive an indication of a paint coverage capability associated with the painter; (d) process the image to determine the sub-region; (e) calculate an area of the sub-region; (f) received an indication of a coverage capability of the paint to be utilized in the painting job; (g) determine the amount of paint, based at least on the area of the sub-region and on the painter paint coverage capability; (h) output an indication of the amount of paint required.

A method for tracing pollution at a drainage outlet of a culvert. (1) The main line of the culvert is fully detected through an inspection robot to obtain the image data, water quality data, coordinates and other basic data of the outlet. (2) The type of the outlet is determined according to the data information obtained in step (1). (3) Pollutants in the drainage outlet with suspected rainwater-sewage connection are traced, and sources of the pollutants flowing to the outlet are all located.

A method for tracing pollution at a drainage outlet of a culvert. (1) The main line of the culvert is fully detected through an inspection robot to obtain the image data, water quality data, coordinates and other basic data of the outlet. (2) The type of the outlet is determined according to the data information obtained in step (1). (3) Pollutants in the drainage outlet with suspected rainwater-sewage connection are traced, and sources of the pollutants flowing to the outlet are all located.

Disclosed is an optical system which includes a first lens that receives input data from an object, a kernel that performs a first Fourier transform on the input data and generates learning data by performing calculation on a result of the first Fourier transform and pattern data, and a second lens that generates result data by performing a second Fourier transform on the learning data, and the input data, the learning data, and the result data include both a positive number and a negative number.

Disclosed frameworks for generating an image including a salient object and a staged background include extracting a salient object from a source image and applying a generative model to the salient object to generate the image. According to some embodiments, extracting a salient object from a source image involves using salient object detection method to identify the relevant portions of the source image corresponding to the salient object. In some embodiments, the generative model is a generative adversarial network trained using a domain relevant dataset.

Disclosed frameworks for generating an image including a salient object and a staged background include extracting a salient object from a source image and applying a generative model to the salient object to generate the image. According to some embodiments, extracting a salient object from a source image involves using salient object detection method to identify the relevant portions of the source image corresponding to the salient object. In some embodiments, the generative model is a generative adversarial network trained using a domain relevant dataset.

A method for authenticating an object, comprising determining a physical dispersion pattern of a set of elements, determining a physical characteristic of the set of elements which is distinct from a physical characteristic producible by a transfer printing technology, determining a digital code associated with the object defining the physical dispersion pattern, and authenticating the object by verifying a correspondence of the digital code with the physical dispersion pattern, and verifying the physical characteristic.

An intelligent item receptacle, system, and method for providing supplemental media content in response to depositing an item having media indicia disposed thereon. An intelligent item receptacle includes an item receptacle securely enclosing an interior volume, an item sensor configured to detect an inserted item, a camera within the interior volume configured to capture an image of the item, and an output configured to play audio or visual content to bystanders outside the item receptacle. Processing circuitry within the item receptacle analyzes the image to determine if the media indicia are present on the item and, if present, causes the output to play the audio or visual content associated with the media indicia.