Abstract: A semiconductor device package includes a substrate and an antenna module. The substrate has a first surface and a second surface opposite to the first surface. The antenna module is disposed on the first surface of the substrate with a gap. The antenna module has a support and an antenna layer. The support has a first surface facing away from the substrate and a second surface facing the substrate. The antenna layer is disposed on the first surface of the support. The antenna layer has a first antenna pattern and a first dielectric layer.

Abstract: The present disclosure provides an electronic device. The electronic device includes a circuit structure, an interconnection structure disposed over the circuit structure, and an antenna element disposed over the interconnection structure. The antenna element defines a first recess having a sidewall, and the sidewall of the first recess of the antenna element is configured to feed a signal to the antenna element and is electrically connected to the interconnection structure.

Abstract: The present disclosure provides an electronic device, which includes an encapsulant, an electronic component, an antenna structure, and a first conductive element. The electronic component is disposed in the encapsulant. The antenna structure has an antenna pattern exposed to air and facing the encapsulant, and a first supporting element separating the antenna pattern from the encapsulant. At least a portion of the first conductive element is within the encapsulant, and electrically connects the antenna pattern to the electronic component by the first supporting element.

Abstract: Methods, devices and computer-readable media for processing a compressed video to perform an inference task are disclosed. Processing the compressed video may include selecting a subset of frame encodings of the compressed video, or zero or more modalities (RGB, motion vectors, residuals) of a frame encoding, for further processing to perform the inference task. Pre-existing motion vector and/or residual information in frame encodings of the compressed video are leveraged to adaptively and efficiently perform the inference task. In some embodiments, the inference task is an action recognition task, such as a human action recognition task.

Abstract: Systems, methods and computer-readable medium for predicting a depth for a video frame are disclosed. An example method may include steps of: receiving a plurality of training data, each comprising a set of consecutive video frames and a depth representation of a subsequent video frame to the consecutive video frames; receiving a pre-trained neural network model f? having a plurality of weights ?; while the pre-trained neural network model f? has not converged: computing a plurality of second weights ?i?, based on each set of consecutive video frames, and updating the plurality of weights ?, based on the plurality of training data and the plurality of second weights ?i?; receiving a plurality of new consecutive video frames with consecutive timestamps; and predicting a depth representation of video frame immediately subsequent to the new consecutive video frames based on the updated plurality of weights ?.

Abstract: Methods and modules for accelerating inference computations in transformer models using edge devices includes partitioning inputs for each layer and synchronizing between transformer layers. A method includes receiving a transformer input, partitioning the transformer input into two or more first-stage divisions, processing each first-stage division into a processed first-stage division, and combining the processed first-stage divisions into a first output. A module includes a computing device for partitioning a transformer input into two or more divisions, transmitting each of the divisions, and receiving processed divisions, as well as two or more transformer processing units, each for receiving a division from the computing device, processing the division into a processed division, and sending the processed division to the computing device.

Abstract: System, method and/or computer readable medium for audio visual sound source Separation that applies cross-modal meta consistency learning. Inputs include an audio spectrogram that represents first sounds second sounds, a first video of a first sound producing object, and a second video of a second sound producing object. Audio features and audio tokens are generated by applying audio encoders to the audio spectrogram. Visual tokens are generated by applying a visual encoder to the first video and the second video. Respective audio-visual features are obtained based on combining the audio token with the respective visual tokens. Based on the respective audio-visual features, first and second separated audio masks are generated by applying a decoder.

Abstract: This disclosure provides for methods and system for meta few-shot class incremental learning. According to an aspect a method is provided. The method includes obtaining at least one weight attention map of a first network and updating weights of a second network using the at least one weight attention map, where the second network is a modulatory network. The method further includes generating at least one feature attention map of the second network based on the at least one weight attention map of the first network and a set of input images of at least one class. The method further includes generating at least one feature map of the first network based on the set of input images of the at least one class, and updating the at least one feature map of the first network based on the feature attention map of the second network.

Abstract: A method has the steps of obtaining a set of training samples from one or more domains, using the set of training samples to query a plurality of artificial-intelligence (AI) models, combining the outputs of the queried AI models, and adapting a target AI model via knowledge distillation using the combined outputs.

Abstract: Methods and systems for determining a surface color of a target surface under an environment with an environmental light source. A plurality of images of the target surface are captured as the target surface is illuminated with a variable intensity, constant color light source and a constant intensity, constant color environmental light source, wherein the intensity of the light source on the target surface is varied by a known amount between the capturing of the images. A color feature tensor, independent of the environmental light source, is extracted from the image data, and used to infer a surface color of the target surface.

Abstract: At least some embodiments of the present disclosure relate to a semiconductor device package. The semiconductor device package comprises a substrate, an antenna, and an active component. The antenna is disposed at least partially within the substrate. The active component is disposed on the substrate and electrically connected to the antenna. A location of the antenna is configured to be adjustable with respect to a location of the active component.

Abstract: A method, device and computer-readable medium for generating a super-resolution version of a compressed video stream. By leveraging the motion information and residual information in compressed video streams, described examples are able to skip the time-consuming motion-estimation step for most frames and make the most use of the SR results of key frames. A key frame SR module generates SR versions of I-frames and other key frames of a compressed video stream using techniques similar to existing multi-frame approaches to VSR. A non-key frame SR module generates SR version of the non-key inter frames between these key frames by making use of motion information and residual information used to encode the inter frames in the compressed video stream.

Abstract: A semiconductor device package includes a carrier, an electronic component and a connector. The electronic component is disposed on the carrier. The connector is disposed on the carrier and electrically connected to the electronic component. A S 11 parameter of the connector is less than ?20 dB.

Abstract: A semiconductor device package includes a substrate, a reflector, a radiator and a first director. The reflector is disposed on a surface of the substrate. The radiator is disposed over the reflector. The first director is disposed over the radiator. The reflector, the radiator and the first director have different elevations with respect to the surface of the substrate. The radiator and the first director define an antenna.

Abstract: Methods and systems for image deblurring are described. The weights of a deblurring network are first trained by meta-training the deblurring network on both a primary deblurring task and an auxiliary reconstruction task. Application-time training of the deblurring network is then performed, using an application-time blurry input image, to obtain values of application-time trained weights. Application-time training includes performing the auxiliary reconstruction task on the application-time blurry input image, and updating the weights of the deblurring network based on an auxiliary loss computed from the auxiliary reconstruction task. A deblurred output image is generated from the application-time blurry input image, using the application-time trained weights in the deblurring network.

Abstract: Devices and methods for extracting motion vector data during decoding compressed of video data are described. At a video decoder, an encoded video data for a frame of video from an input buffer is obtained. The encoded video data is decoded to obtain decoded image data for a decoded frame, where the decoding includes extracting corresponding motion vector data for the decoded frame. The decoded image data is stored in a temporary storage indexed with a given index, and the corresponding motion vector data is stored in a same or different temporary storage indexed with the given index. An output buffer indexed with the given index is filled with the decoded image data and the corresponding motion vector data stored in the respective temporary storage indexed with the given index.

Abstract: A semiconductor device package includes a substrate and an antenna module. The substrate has a first surface and a second surface opposite to the first surface. The antenna module is disposed on the first surface of the substrate with a gap. The antenna module has a support and an antenna layer. The support has a first surface facing away from the substrate and a second surface facing the substrate. The antenna layer is disposed on the first surface of the support. The antenna layer has a first antenna pattern and a first dielectric layer.

Abstract: The present disclosure provides a semiconductor structure including a first substrate having a first surface, a first semiconductor device package disposed on the first surface of the first substrate, and a second semiconductor device package disposed on the first surface of the first substrate. The first semiconductor device package and the second semiconductor device package have a first signal transmission path through the first substrate and a second signal transmission path insulated from the first substrate. The present disclosure also provides an electronic device.

Abstract: Methods, devices and computer-readable media for processing a compressed video to perform an inference task are disclosed. Processing the compressed video may include selecting a subset of frame encodings of the compressed video, or zero or more modalities (RGB, motion vectors, residuals) of a frame encoding, for further processing to perform the inference task. Pre-existing motion vector and/or residual information in frame encodings of the compressed video are leveraged to adaptively and efficiently perform the inference task. In some embodiments, the inference task is an action recognition task, such as a human action recognition task.

Abstract: Devices and methods for extracting motion vector data during decoding compressed of video data are described. At a video decoder, an encoded video data for a frame of video from an input buffer is obtained. The encoded video data is decoded to obtain decoded image data for a decoded frame, where the decoding includes extracting corresponding motion vector data for the decoded frame. The decoded image data is stored in a temporary storage indexed with a given index, and the corresponding motion vector data is stored in a same or different temporary storage indexed with the given index. An output buffer indexed with the given index is filled with the decoded image data and the corresponding motion vector data stored in the respective temporary storage indexed with the given index.