Abstract: Disclosed is an image segmentation device. The image segmentation device may include: a storage unit storing a segmentation model learned so as to segment at least one predetermined object; and at least one processor inputting input data into the segmentation model and segmenting at least one predetermined object in the input data, in which the segmentation model may include an encoder including at least one dimension reduction block reducing a dimension of the input data, a decoder including at least one dimension increase block increasing the dimension of output data output from the encoder by using data output from at least one dimension reduction block, and an auxiliary classification model receiving the output data and recognizing whether a specific object is included in the output data.

Abstract: Disclosed herein are an apparatus for detecting a moment described by a sentence query in a video and a method using the same. A method for detecting a moment described by a sentence query in a video includes dividing an input video into units of chunks and generating a chunk-level feature sequence based on features that are extracted in a form of vectors from respective chunks, dividing an input sentence query into units of words and generating a sentence-level feature sequence based on features that are extracted in a form of vectors from respective words, generating a chunk-sentence relation feature sequence including contextual information of the video by extracting a relation between the chunk-level feature sequence and the sentence-level feature sequence, and estimating a temporal interval corresponding to the sentence query in the video based on the chunk-sentence relation feature sequence.

Abstract: A domain adaptation-based object recognition apparatus includes a memory configured to store a domain adaptation-based object recognition program and a processor configured to execute the program. The processor learns a generative model for generating a feature or an image similar to a gallery image on the basis of domain adaptation in association with an input probe image and learns an object recognition classification model by using a learning database corresponding to the gallery image and the input probe image, thereby performing object recognition using the input probe image.

Abstract: A method includes setting an output of each memory cell in an array of memory cells to a same first value, decreasing power to the array of memory cells and then increasing power to the array of memory cells. Memory cells in the array of memory cells with outputs that switched to a second value different from the first value are then identified in response to decreasing and then increasing the power. A set of memory cells is then selected from the identified memory cells to use in hardware security.

Abstract: A test apparatus includes a first module configured to structurally support a target semiconductor device, and a second module reversibly attachable to the first module. The first module includes a first housing including one or more inner surfaces at least partially defining an inner space, a volume control unit configured to control a volume of the inner space, a mounting unit at least partially exposed to the inner space and configured to be exposed to the target semiconductor device, and a magnetic force control unit in the first housing. The second module includes a second housing, a test board in the second housing, and an attachable/detachable member in the second housing. The test board may be electrically connected to the target semiconductor device. The magnetic force control unit may control a magnetic property of the attachable/detachable member to cause the attachable/detachable member to attach/detach to/from the magnetic force control unit.

Abstract: A method includes setting an output of each memory cell in an array of memory cells to a same first value, decreasing power to the array of memory cells and then increasing power to the array of memory cells. Memory cells in the array of memory cells with outputs that switched to a second value different from the first value are then identified in response to decreasing and then increasing the power. A set of memory cells is then selected from the identified memory cells to use in hardware security.

Abstract: Provided is an apparatus for online action detection, the apparatus including a feature extraction unit configured to extract a chunk-level feature of a video chunk sequence of a streaming video, a filtering unit configured to perform filtering on the chunk-level feature, and an action classification unit configured to classify an action class using the filtered chunk-level feature.

Abstract: Compute engine circuitry configured to represent a spin network mapping of a graph representing a combinatorial optimization problem includes a plurality of ring oscillator cells, each of which includes a ring oscillator having an oscillator output, at least one coupling block, and a read block. Each coupling block connects the ring oscillator of the cell to the ring oscillator of one of a plurality of neighboring cells to form a coupled ring oscillator. The read block generates a state output for each coupled ring oscillator that indicates whether the coupled ring oscillator is in one of a same-phase state, in which the connected ring oscillators oscillate in phase with each other, and an opposite-phase state, in which the connected ring oscillators oscillate in an opposite phase from each other. A controller is configured to output a total energy of the mapping based on the state outputs.

Abstract: Disclosed is an optical coherence tomography (OCT) system according to an exemplary embodiment of the present disclosure.

Abstract: An electronic device according to an embodiment disclosed herein may include a memory including at least one instruction and a processor. By executing the at least one instruction, the processor may check feature information corresponding to a video and including at least one of an appearance-related feature value and a motion-related feature value from the video, calculate at least one of a starting score related to a starting point of an action instance, an ending score related to an ending point of an action instance, and a relatedness score between action instances on the basis of the feature information corresponding to the video, the action instances being included in the video, and generate an action proposal included in the video on the basis of the at least one score.

Abstract: In some examples, a device includes an analog-to-digital converter (ADC) configured to receive an analog signal and output digital codes based on values of the analog signal. The device also includes a plurality of counters, where each counter of the plurality of counters is configured to increment in response to a respective digital code outputted by the ADC.

Abstract: In some examples, a device includes an analog-to-digital converter (ADC) configured to receive an analog signal and output digital codes based on values of the analog signal. The device also includes a plurality of counters, where each counter of the plurality of counters is configured to increment in response to a respective digital code outputted by the ADC.

Abstract: A domain adaptation-based object recognition apparatus includes a memory configured to store a domain adaptation-based object recognition program and a processor configured to execute the program. The processor learns a generative model for generating a feature or an image similar to a gallery image on the basis of domain adaptation in association with an input probe image and learns an object recognition classification model by using a learning database corresponding to the gallery image and the input probe image, thereby performing object recognition using the input probe image.

Abstract: Disclosed is an optical probe of an optical coherence tomography (OCT) system according to an exemplary embodiment of the present disclosure. The optical probe of the OCT system includes: an optical fiber receiving light generated from a light source and transferring the received light to a plurality of lenses and receiving light reflected from tissue from the plurality of lenses and transferring the received light to an optical coherence system; a plurality of lenses including a first lens positioned at a distal end of the optical fiber and a second lens positioned at a predetermined point in a longitudinal direction of the optical fiber; and a sheath capable of accommodating the optical fiber therein.

Abstract: Smart glasses for selectively tracking a target of visual cognition according to the present invention include a first camera configured to capture a first input image that is a first-person view image of a user, a second camera configured to capture a second input image containing sight line information of the user, a display configured to output additional information corresponding to the first input image, a memory configured to store a program for selectively tracking a target of visual cognition on the basis of the first and second input images, and a processor configured to execute the program stored in the memory, wherein upon executing the program, the processor is configured to detect the target of visual cognition from the first input image and determine, from the second input image, whether the user is in an inattentive state with respect to the target of visual cognition.

Abstract: Methods of manufacturing polymeric stents by forming a pattern on a polylactic acid tube using a second harmonic generator laser and polylactic acid polymeric stents having a pattern formed using a second harmonic generator laser.

Abstract: A method includes setting an output of each memory cell in an array of memory cells to a same first value, decreasing power to the array of memory cells and then increasing power to the array of memory cells. Memory cells in the array of memory cells with outputs that switched to a second value different from the first value are then identified in response to decreasing and then increasing the power. A set of memory cells is then selected from the identified memory cells to use in hardware security.

Abstract: A time-based decision feedback equalizer (TB-DFE) circuit may include a voltage-to-time converter configured to convert a communication signal into a time-based signal. A timing of when an edge of the time-based signal occurs is indicative of a voltage level of the communication signal. The circuit may include a plurality of delay circuits arranged to process the time-based signal in series to generate a delay data signal. The delay circuits may adjust the timing of when the edge of the time-based signal occurs, and a corresponding time delay introduced by each of the delay circuits may be based on a respective weighting factor applied to one or more samples of an output digital signal previously generated by the TB-DFE circuit. A phase detector may compare a timing of an edge of the delay data signal with a reference clock signal and generate the output digital signal based on the comparison.

Abstract: An apparatus includes a finite state machine and a physical structure capable of providing a response to a challenge, the physical structure such that before the physical structure is ever provided with the challenge, the response to the challenge is unpredictable. The finite state machine moves from an initial state to an intermediate state due to receiving the response from the physical structure, and moves from the intermediate state to a final state due to receiving a key. The final state indicates whether the physical structure is a counterfeit physical structure.

Abstract: In some examples, an electronic device comprising an input ferroelectric (FE) capacitor, an output FE capacitor, and a channel positioned beneath the input FE capacitor and positioned beneath the output FE capacitor. In some examples, the channel is configured to carry a magnetic signal from the input FE capacitor to the output FE capacitor to cause a voltage change at the output FE capacitor. In some examples, the electronic device further comprises a transistor-based drive circuit electrically connected to an output node of the output FE capacitor. In some examples, the transistor-based drive circuit is configured to deliver, based on the voltage change at the output FE capacitor, an output signal to an input node of a second device.