Abstract: A method and an apparatus for embedding watermark information are disclosed in the present disclosure. The method trains an embedded neural network model using weight information of a target neural network model and target watermark information that is to be embedded into the target neural network model, updates the weight information of the target neural network model according to target watermark embedded data provided by the embedded neural network model, and obtains a target neural network model embedded with the target watermark information. Since the embedded neural network model includes multiple neural network layers, this method increases the complexity of the watermark embedding process, and is able to avoid the problem that watermark information of existing neural network models has poor robustness to watermarking attacks such as overwriting attacks and model compression.

Abstract: Methods and systems for compensating systematic errors across a fleet of metrology systems based on a trained error evaluation model to improve matching of measurement results across the fleet are described herein. In one aspect, the error evaluation model is a machine learning based model trained based on a set of composite measurement matching signals. Composite measurement matching signals are generated based on measurement signals generated by each target measurement system and corresponding model-based measurement signals associated with each target measurement system and reference measurement system. The training data set also includes an indication of whether each target system is operating within specification, an indication of the values of system model parameter of each target system, or both.

Abstract: A method for generating an output image from an input image and an input text instruction that specifies a location and a modification of an edit applied to the input image using a neural network is described. The neural network includes an image encoder, an image decoder, and an instruction attention network. The method includes receiving the input image and the input text instruction; extracting, from the input image, an input image feature that represents features of the input image using the image encoder; generating a spatial feature and a modification feature from the input text instruction using the instruction attention network; generating an edited image feature from the input image feature, the spatial feature and the modification feature; and generating the output image from the edited image feature using the image decoder.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for determining a visually imperceptible or a visually perceptible watermark and outputting a result based on the determination. A watermark decoder receives an input image. The watermark decoder applies a decoder machine learning model to decode a watermarks at different levels of zoom. The water mark decoder determines whether a watermark was decoded to obtain a decoded watermark. The watermark decoder outputs a result based on the determination whether the watermark was decoded through application of the decoder machine learning model to the input image that includes outputting a zoomed output decoded through application of the decoder machine learning model to the input image.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for detecting and decoding a visually imperceptible or perceptible watermark. A watermark detection apparatus determines whether the particular image includes a visually imperceptible or perceptible watermark using detector a machine learning model. If the watermark detection apparatus detects a watermark, the particular image is routed to a watermark decoder. If the watermark detection apparatus cannot detect a watermark in the particular image, the particular image is filtered from further processing. The watermark decoder decodes the visually imperceptible or perceptible watermark detected in the particular image. After decoding, an item depicted in the particular image is validated based data extracted from the decoded visually imperceptible or perceptible watermark.

Abstract: A method for generating an output image from an input image and an input text instruction that specifies a location and a modification of an edit applied to the input image using a neural network is described. The neural network includes an image encoder, an image decoder, and an instruction attention network. The method includes receiving the input image and the input text instruction; extracting, from the input image, an input image feature that represents features of the input image using the image encoder; generating a spatial feature and a modification feature from the input text instruction using the instruction attention network; generating an edited image feature from the input image feature, the spatial feature and the modification feature; and generating the output image from the edited image feature using the image decoder.

Abstract: A method for generating an output image from an input image and an input text instruction that specifies a location and a modification of an edit applied to the input image using a neural network is described. The neural network includes an image encoder, an image decoder, and an instruction attention network. The method includes receiving the input image and the input text instruction; extracting, from the input image, an input image feature that represents features of the input image using the image encoder; generating a spatial feature and a modification feature from the input text instruction using the instruction attention network; generating an edited image feature from the input image feature, the spatial feature and the modification feature; and generating the output image from the edited image feature using the image decoder.

Abstract: Disclosed herein are a preparation method and an application of an isoxazinone compound (I), where the preparation method includes: reacting compound (II) with a carboxylic acid (III) in the presence of a dehydrating agent and a base to produce the isoxazinone compound (I); and subjecting the isoxazinone compound (I) and a protonic acid salt of an amino compound (IV) or R3OH (VII) to ring-opening reaction in the presence of a base to produce a bisamide compound (V) or an N-acyl benzoate compound (VI).

Abstract: A method for generating an output image from an input image and an input text instruction that specifies a location and a modification of an edit applied to the input image using a neural network is described. The neural network includes an image encoder, an image decoder, and an instruction attention network. The method includes receiving the input image and the input text instruction; extracting, from the input image, an input image feature that represents features of the input image using the image encoder; generating a spatial feature and a modification feature from the input text instruction using the instruction attention network; generating an edited image feature from the input image feature, the spatial feature and the modification feature; and generating the output image from the edited image feature using the image decoder.

Abstract: Various embodiments of the present technology generally relate to robotic devices, artificial intelligence, and computer vision. More specifically, some embodiments relate to an imaging process for detecting failure modes in a robotic motion environment. In one embodiment, a method of detecting failure modes in a robotic motion environment comprises collecting one or more images of a multiple scenes throughout a robotic motion cycle. Images may be collected by one or more cameras positioned at one or more locations for collecting images with various views. Images collected throughout the robotic motion cycle may be processed in real-time to determine if any failure modes are present in their respective scenes, report when failure modes are present, and may be used to direct a robotic device accordingly.

Abstract: Disclosed herein is a method of preparing N-acyl anthranilamide (I), including: reacting a substituted anthranilic acid (II) with pyrazolecarboxylic acid (III) under the action of a phosphorus reagent and a base to obtain an intermediate benzoxazinone (IV); and subjecting the intermediate benzoxazinone (IV) and a protonic acid salt of methylamine to a ring-opening reaction to obtain N-acyl anthranilamide (I), as shown in the following reaction scheme: where X is hydrogen, chloro or cyano group; and HY is hydrohalic acid, sulfuric acid, phosphoric acid or a carboxylic acid. The method has the advantages of simple operation, mild reaction conditions, less waste and high overall yield, and thus is suitable for industrial production.

Abstract: Disclosed herein are a preparation method and an application of an isoxazinone compound (I), where the preparation method includes: reacting compound (II) with a carboxylic acid (III) in the presence of a dehydrating agent and a base to produce the isoxazinone compound (I); and subjecting the isoxazinone compound (I) and a protonic acid salt of an amino compound (IV) or R3OH (VII) to ring-opening reaction in the presence of a base to produce a bisamide compound (V) or an N-acyl benzoate compound (VI).

Abstract: Disclosed herein is a method of preparing N-acyl anthranilamide (I), including: reacting a substituted anthranilic acid (II) with pyrazolecarboxylic acid (III) under the action of a phosphorus reagent and a base to obtain an intermediate benzoxazinone (IV); and subjecting the intermediate benzoxazinone (IV) and a protonic acid salt of methylamine to a ring-opening reaction to obtain N-acyl anthranilamide (I), as shown in the following reaction scheme: where X is hydrogen, chloro or cyano group; and HY is hydrohalic acid, sulfuric acid, phosphoric acid or a carboxylic acid. The method has the advantages of simple operation, mild reaction conditions, less waste and high overall yield, and thus is suitable for industrial production.

Abstract: A preparative method for carboxylic acids is disclosed in the present invention. The method is characterized in that: compounds (II) are reacted in the presence of hydrogen peroxide and base to produce target products (I), as represented by the following reaction scheme: wherein R1 is aryl, pyridyl, pyrimidyl, pyridazinyl, pyrazinyl, benzothienyl, benzofuranyl, quinolinyl, isoquinolinyl, thiadiazolyl, C1-6 alkyl, C3-6 cycloalkyl, C2-6 alkenyl, C2-6 alkynyl and hydrogen; R2 is alkoxycarbonyl, alkylaminocarbonyl, aminocarbonyl, alkylthiolcarbonyl, cyano, sulfonyl, sulfinyl, carbonyl, aldehyde, carboxyl, nitro, alkyl and hydrogen; R3 is alkoxycarbonyl, alkyl amido carbonyl, aminocarbonyl, cyano, sulfonyl, sulfinyl, carbonyl, carboxyl and nitro. The present invention has the following main benefits: cheap and readily available starting materials, safe processes, high yield, good quality, which facilitates industrial production.

Abstract: A preparative method for carboxylic acids is disclosed in the present invention. The method is characterized in that: compounds (II) are reacted in the presence of hydrogen peroxide and base to produce target products (I), as represented by the following reaction scheme: wherein R1 is aryl, pyridyl, pyrimidyl, pyridazinyl, pyrazinyl, benzothienyl, benzofuranyl, quinolinyl, isoquinolinyl, thiadiazolyl, C1-6 alkyl, C3-6 cycloalkyl, C2-6 alkenyl, C2-6 alkynyl and hydrogen; R2 is alkoxycarbonyl, alkylaminocarbonyl, aminocarbonyl, alkylthiolcarbonyl, cyano, sulfonyl, sulfinyl, carbonyl, aldehyde, carboxyl, nitro, alkyl and hydrogen; R3 is alkoxycarbonyl, alkyl amido carbonyl, aminocarbonyl, cyano, sulfonyl, sulfinyl, carbonyl, carboxyl and nitro. The present invention has the following main benefits: cheap and readily available starting materials, safe processes, high yield, good quality, which facilitates industrial production.

Abstract: Disclosed is a method and system for processing the tasks performed by an IC layout processing tool in parallel. In some approaches, the IC layout is divided into a plurality of layout portions and one or more of the layout portions are processed in parallel, where geometric select operations are performed in which data for different layout portions may be shared between different processing entities. One approach includes the following actions: select phase one operation for performing initial select actions within layout portions; distributed regioning action for local regioning; distributed regioning action for global regioning and binary select; count select aggregation for count-based select operations; and select phase two operations for combining results of selecting of internal shapes and interface shapes.

Abstract: Some embodiments provide a method for decomposing a region of an integrated circuit (“IC”) design layout into multiple mask layouts. The method identifies a number of sets of geometries in the design layout region that must be collectively assigned to the multiple mask layouts. The method assigns the geometries in a first group of collectively-assigned sets to different mask layouts without splitting any of the geometries. The method assigns the geometries in a second group of the collectively-assigned sets to different mask layouts in such a way so as to minimize the number of splits in the geometries of the second group.

Abstract: Disclosed is a method and system for processing the tasks performed by an IC layout processing tool in parallel. In some approaches, the IC layout is divided into a plurality of layout portions and one or more of the layout portions are processed in parallel, where geometric select operations are performed in which data for different layout portions may be shared between different processing entities. One approach includes the following actions: select phase one operation for performing initial select actions within layout portions; distributed regioning action for local regioning; distributed regioning action for global regioning and binary select; count select aggregation for count-based select operations; and select phase two operations for combining results of selecting of internal shapes and interface shapes.