Abstract: An apparatus, method and storage medium for controlling a pathologic microscope are provided. The method includes obtaining a pathological digital image from an incident optical path of the pathologic microscope; performing artificial intelligence (AI) analysis on the pathological digital image to generate AI analysis information; and controlling an augmented reality (AR) projection component to project the AI analysis information on a microscopic field of the pathologic microscope on an outgoing optical path.

Abstract: Various solutions for extended reality (XR) enhancement in mobile communications are described. An apparatus establishes a communication with a network node of a wireless network. The apparatus performs an operation with respect to XR-related computation offloading from a user end to result in XR enhancement at the user end.

Abstract: A neural network model is trained for fairness and accuracy using both real and synthesized training data, such as images. During training a first sampling ratio between the real and synthesized training data is optimized. The first sampling ratio may comprise a value for each group (or attribute), where each value is optimized. A second sampling ratio defines relative amounts of training data that are used for each one of the groups. Furthermore, a neural network model accuracy and a fairness metric are both used for updating the first and second sampling ratios during training iterations. The neural network model may be trained using different classes of training data. The second sampling ratio may vary for each class.

Abstract: The invention provides a light-emitting image sensing module and a method for fabricating the same. The light-emitting image sensing module includes a circuit board, an image sensor, conductive carriers, light sources, an opaque lens barrel, and a lens module. The image sensor and the conductive carriers are arranged on the circuit board. The light sources are arranged on the conductive carrier. The opaque lens barrel is penetrated by a first hole and a second hole and arranged on the circuit board. The first hole sleeves the image sensor, and the second hole sleeves the conductive carriers and the light sources. The lens module is fixed in the first hole and arranged above the image sensor. The invention uses the circuit board to carry out the packaging process of the image sensor and the light source, so as to achieve the economic benefit.

Abstract: A p-aminobenzoic acid-producing microorganism is provided. The p-aminobenzoic acid-producing microorganism is obtained by a method for preparing a p-aminobenzoic acid-producing microorganism. The method for preparing a p-aminobenzoic acid-producing microorganism includes (a) performing an acclimation process on a source microorganism with at least one sulfonamide antibiotic to obtain at least one acclimatized microorganism and (b) screening out at least one p-aminobenzoic acid-producing microorganism from the at least one acclimatized microorganism, wherein the at least one p-aminobenzoic acid-producing microorganism has a higher p-aminobenzoic acid titer than the source microorganism.

Abstract: Apparatuses, systems, and techniques to perform neural networks. In at least one embodiment, a most consistent output of one or more pre-trained neural networks is to be selected. In at least one embodiment, a most consistent output of one or more pre-trained neural networks is to be selected based, at least in part, on a plurality of variances of one or more inputs to the one or more neural networks.

Abstract: A device includes: a complementary transistor including: a first transistor having a first source/drain region and a second source/drain region; and a second transistor stacked on the first transistor, and having a third source/drain region and a fourth source/drain region, the third source/drain region overlapping the first source/drain region, the fourth source/drain region overlapping the second source/drain region. The device further includes: a first source/drain contact electrically coupled to the third source/drain region; a second source/drain contact electrically coupled to the second source/drain region; a gate isolation structure adjacent the first and second transistors; and an interconnect structure electrically coupled to the first source/drain contact and the second source/drain contact.

Abstract: Introduced here are computer programs and associated computer-implemented techniques for deriving insights into the health of patients through analysis of audio data generated by electronic stethoscope systems. A diagnostic platform may be responsible for examining the audio data generated by an electronic stethoscope system so as to gain insights into the health of a patient. The diagnostic platform may employ heuristics, algorithms, or models that rely on machine learning or artificial intelligence to perform auscultation in a manner that significantly outperforms traditional approaches that rely on visual analysis by a healthcare professional.

Abstract: Introduced here are computer programs and associated computer-implemented techniques for deriving insights into the health of patients through analysis of audio data generated by electronic stethoscope systems. A diagnostic platform may be responsible for examining the audio data generated by an electronic stethoscope system so as to gain insights into the health of a patient. The diagnostic platform may employ heuristics, algorithms, or models that rely on machine learning or artificial intelligence to perform auscultation in a manner that significantly outperforms traditional approaches that rely on visual analysis by a healthcare professional.

Abstract: Apparatuses, systems, and techniques to identify a goal of a demonstration. In at least one embodiment, video data of a demonstration is analyzed to identify a goal. Object trajectories identified in the video data are analyzed with respect to a task predicate satisfied by a respective object trajectory, and with respect to motion predicate. Analysis of the trajectory with respect to the motion predicate is used to assess intentionality of a trajectory with respect to the goal.

Abstract: Apparatuses, systems, and techniques to track one or more objects in one or more frames of a video. In at least one embodiment, one or more objects in one or more frames of a video are tracked based on, for example, one or more sets of embeddings.

Abstract: One embodiment of a method for training a machine learning model includes receiving a training data set that includes at least one image, text referring to at least one object included in the at least one image, and at least one bounding box annotation associated with the at least one object, and performing, based on the training data set, one or more operations to generate a trained machine learning model to segment images based on text, where the one or more operations to generate the trained machine learning model include minimizing a loss function that comprises at least one of a multiple instance learning loss term or an energy loss term

Abstract: Introduced here are computer programs and associated computer-implemented techniques for deriving insights into the health of patients through analysis of audio data generated by electronic stethoscope systems. A diagnostic platform may be responsible for examining the audio data generated by an electronic stethoscope system so as to gain insights into the health of a patient. The diagnostic platform may employ heuristics, algorithms, or models that rely on machine learning or artificial intelligence to perform auscultation in a manner that significantly outperforms traditional approaches that rely on visual analysis by a healthcare professional.

Abstract: An interdigital transducer for a surface-acoustic-wave resonator includes a conductive grid and a plurality of practical electrodes. The conductive grid includes a bus bar, a plurality of dummy electrodes and a conductive bar. The bus bar has a signal transmission terminal, and is disposed on a first side of the first conductive grid. The plurality of dummy electrodes directly extend from the bus bar. The conductive bar is disposed on a second side of the first conductive grid, and is opposite to the bus bar. Each of the plurality of practical electrodes extends from the conductive bar.

Abstract: A real-time monitoring device for human body is disclosed. The real-time monitoring device includes a sensor module and a processor module, wherein the sensor module is adopted for contacting a human body like a baby's, so as to conduct a sensing work. The processor module is coupled to the sensor module for receiving a body temperature sensing signal, a first sound signal and a body activity sensing signal, and is configured for generating a second sound signal by collecting a sound emitted from the body. According to the present invention, the processor module is configured for determining whether the baby has a physical condition after applying processing and analyzing the body temperature sensing signal, the first sound signal, the second sound signal, and the body activity sensing signal. Moreover, the processor is also configured for to estimating physiological parameters of the baby.

Abstract: A maternal and fetal monitoring device using multiple sensing units is disclosed. The maternal and fetal monitoring device comprises: a processor module and a plurality of sensor modules, wherein each said sensor module comprises: an inertial sensor, a temperature sensor and a first acoustic sensor. After being attached onto a maternal body, each said sensor module collects a body temperature signal, an inertia signal and a sound signal. Subsequently, the processor module determines a maternal body posture by analyzing the inertia signal, determines a maternal physical condition and a fetal physical condition by analyzing the inertial signal, the plurality of first sound signals and the second sound signal, and estimates physiological parameters of the maternal body and a fetus by analyzing the body temperature sensing signal, the plurality of first sound signals, and the second sound signals.

Abstract: A method for scene perception using video captioning based on a spatio-temporal graph model is described. The method includes decomposing the spatio-temporal graph model of a scene in input video into a spatial graph and a temporal graph. The method also includes modeling a two branch framework having an object branch and a scene branch according to the spatial graph and the temporal graph to learn object interactions between the object branch and the scene branch. The method further includes transferring the learned object interactions from the object branch to the scene branch as privileged information. The method also includes captioning the scene by aligning language logits from the object branch and the scene branch according to the learned object interactions.

Abstract: Introduced here are computer programs and associated computer-implemented techniques for deriving insights into the health of patients through analysis of audio data generated by electronic stethoscope systems. A diagnostic platform may be responsible for examining the audio data generated by an electronic stethoscope system so as to gain insights into the health of a patient. The diagnostic platform may employ heuristics, algorithms, or models that rely on machine learning or artificial intelligence to perform auscultation in a manner that significantly outperforms traditional approaches that rely on visual analysis by a healthcare professional.