Abstract: Provided are an edge gateway system for providing device use and resource sharing suggestions and an operating method thereof. The edge gateway system includes at least one edge gateway and an edge gateway management server connected to the at least one edge gateway. The edge gateway is connected to one or more edge devices and transmits an operation status of the edge gateway and an operation status of the edge devices to the edge gateway management server, the edge gateway management server generates suggestion information to be delivered to a user of the edge gateway based on the operation status of the edge gateway and the operation status of the edge devices, and the suggestion information includes any one of an edge device use suggestion, an edge device sharing suggestion, and an edge gateway service resource sharing suggestion.

Abstract: An apparatus and method for quantizing a transformer-based target tracking model are provided. The method includes obtaining a transformer-based target tracking model including a template branch, a search branch, a stitching module, and a first transformer module, generating an optimized target tracking model by removing the stitching module from the transformer-based target tracking model and dividing the first transformer module into a second transformer module and a third transformer module, and generating a quantization model corresponding to the optimized target tracking model by quantizing the divided second transformer module independently of quantizing the divided third transformer module.

Abstract: A processor-implemented method with video processing includes: determining a first image feature of a first image of video data and a second image feature of a second image that is previous to the first image; determining a time-domain information fusion processing result by performing time-domain information fusion processing on the first image feature and the second image feature; and determining a panoptic segmentation result of the first image based on the time-domain information fusion processing result.

Abstract: Disclosed is an adaptive deep learning inference system that adapts to changing network latency and executes deep learning model inference to ensure end-to-end data processing service latency when providing a deep learning inference service in a mobile edge computing (MEC) environment. An apparatus and method for providing a deep learning inference service performed in an MEC environment including a terminal device, a wireless access network, and an edge computing server are provided. The apparatus and method provide deep learning inference data having deterministic latency, which is fixed service latency, by adjusting service latency required to provide a deep learning inference result according to a change in latency of the wireless access network when at least one terminal device senses data and requests a deep learning inference service.

Abstract: A method and apparatus with image correction is provided. A processor-implemented method includes generating, using a neural network model provided an input image, an illumination map including illumination values dependent on respective color casts by one or more illuminants individually affecting each pixel of the input image, and generating a white-adjusted image by removing at least a portion of the color casts from the input image using the generated illumination map.

Abstract: A device and method with object recognition is included. In one general aspect, an electronic device includes a camera sensor configured to capture a first image of a scene, the camera sensor is configured to perform at least one type of physical camera motion relative to the electronic device, the at least one type of physical camera motion includes rolling, panning, tilting, or zooming the camera sensor relative to the electronic device, and a processor configured to control the camera sensor to perform a physical motion of the physical camera motion type based on detecting an object in the first image, acquire a second image captured using the camera sensor as adjusted based on the performed physical motion, and recognize the object in the second image.

Abstract: A method and apparatus for detecting a liveness based on a phase difference are provided. The method includes generating a first phase image based on first visual information of a first phase, generating a second phase image based on second visual information of a second phase, generating a minimum map based on a disparity between the first phase image and the second phase image, and detecting a liveness based on the minimum map.

Abstract: Disclosed is a method and apparatus for adaptive tracking of a target object. The method includes method of tracking an object, the method including estimating a dynamic characteristic of an object in an input image based on frames of the input image, determining a size of a crop region for a current frame of the input image based on the dynamic characteristic of the object, generating a cropped image by cropping the current frame based on the size of the crop region, and generating a result of tracking the object for the current frame using the cropped image.

Abstract: A method and apparatus for detecting a liveness based on a phase difference are provided. The method includes generating a first phase image based on first visual information of a first phase, generating a second phase image based on second visual information of a second phase, generating a minimum map based on a disparity between the first phase image and the second phase image, and detecting a liveness based on the minimum map.

Abstract: A processor-implemented method with visual code processing includes generating a first image by capturing a first visual code, using an always on (AO) sensor module of an electronic device, detecting a first code image included in the first image and corresponding to the first visual code, using the AO sensor module, performing a first type decoding on the first code image, using the AO sensor module, waking up an application processor (AP) of the electronic device from a low-power state, based on a first decoding result of the first type decoding, and executing a first application of the electronic device corresponding to the first visual code, using the AP.

Abstract: An object classification method and apparatus are disclosed. The object classification method includes receiving an input image, storing first feature data extracted by a first feature extraction layer of a neural network configured to extract features of the input image, receiving second feature data from a second feature extraction layer which is an upper layer of the first feature extraction layer, generating merged feature data by merging the first feature data and the second feature data, and classifying an object in the input image based on the merged feature data.

Abstract: An image sensor includes: a motion detection circuit configured to detect a motion in image frames; and a micro control unit (MCU) configured to adjust at least a portion of a target frame among the image frames based on whether the motion is detected, and detect whether a target object is present based on the adjusted portion of the target frame.

Abstract: A processor-implemented method including generating a depth-aware feature of an image dependent on image features extracted from image data of the image and generating image data, representing information corresponding to one or more segmentations of the image, based on the depth-aware feature and a depth-aware representation, the depth-aware representation being depth-related information and visual-related information for the image.

Abstract: An apparatus and method for training a neural network model for classification without a teacher model are disclosed. The includes: selecting classes from a database comprising a set of classes; generating a mean feature group comprising mean features extracted from the selected classes; receiving a batch comprising input data and extracting, by the neural network model, a feature from the input data, wherein the neural network model is to be trained according to a mean feature set; determining a first similarity between the extracted feature and a mean feature corresponding to the input data; determining a second similarity comprising a self-similarity of the mean feature; and updating a parameter of the neural network model based on the first similarity and the second similarity.

Abstract: A processor-implemented method with target object tracking includes: setting a search area for a target object included in an input image based on a position of a first target box in a template image; selecting a network path from a plurality of network paths of a neural network model according to a resizing ratio of a size of another image that is input to the neural network model to a size of the search area; and tracking the target object by estimating a position of a second target box corresponding to the target object in the input image according to the selected network path.

Abstract: An apparatus with image segmentation includes: one or more processors configured to: obtain a second image based on a first segmentation label corresponding to a first image; generate a composite image by composing an image of an object corresponding to an object class of the first image among objects comprised by the second image with the first image; and train an image segmentation model based on the composite image, the first image, and the second image.

Abstract: A processor-implemented method with pose estimation includes: receiving an image, instance queries for object identification, and joint queries for joint identification; generating first heat maps associated with objects and second heat maps associated with joints in parallel based on the image, the instance queries, and the joint queries; and estimating respective joint information of a plurality of objects included in the image by combining the first heat maps and the second heat maps.

Abstract: A method, apparatus, and system with tracking are disclosed. The apparatus is configured to acquire a feature map of a template image, a color histogram of a foreground of the template image that has an object, and a color histogram of a background of the template image other than the foreground, acquire a feature score map, and a bounding box map corresponding to the feature score map, based on the feature map of the template image and a feature map of a search image, acquire a color score map based on the color histogram of the foreground, the color histogram of the background, and a color value of the search image, acquire a final score map, and a bounding box map corresponding to the final score map, based on the feature score map, the color score map, and the bounding box map, and output the corresponding bounding box.

Abstract: An image sensor includes: a motion detection circuit configured to detect a motion in image frames; and a micro control unit (MCU) configured to adjust at least a portion of a target frame among the image frames based on whether the motion is detected, and detect whether a target object is present based on the adjusted portion of the target frame.

Abstract: A processor-implemented method includes: obtaining a video feature of a video comprising a plurality of video frames; determining a target object representation of the video based on the video feature using a neural network; and generating a panorama segmentation result of the video based on the target object representation.