Abstract: The present application discloses a method and an apparatus for training a backbone network, an image processing method and apparatus, and a device. A weight selection cycle is set, where the weight selection cycle may include at least one backbone network training cycle. The backbone network is trained with sample data in the current weight selection cycle, and a cumulative weight adjustment amount for each weight in the backbone network in the current weight selection cycle is recorded. A target weight for which the cumulative weight adjustment amount meets a preset condition is selected from the backbone network based on the cumulative weight adjustment amount for each weight, and only the target weight in the backbone network is adjusted in a next weight selection cycle, to complete training of the backbone network in the next weight selection cycle based on the adjusted target weight.

Abstract: The present disclosure describes techniques of improving video matting. The techniques comprise extracting features from each frame of a video by an encoder of a model, wherein the video comprises a plurality of frames; incorporating, by a decoder of the model, into any particular frame temporal information extracted from one or more frames previous to the particular frame, wherein the particular frame and the one or more previous frames are among the plurality of frames of the video, and the decoder is a recurrent decoder; and generating a representation of a foreground object included in the particular frame by the model, wherein the model is trained using segmentation dataset and matting dataset.

Abstract: Described are examples for detecting objects in an image on a device including setting, based on a condition, a number of sparse proposals to use in performing object detection in the image, performing object detection in the image based on providing the sparse proposals as input to an object detection process to infer object location and classification of one or more objects in the image, and indicating, to an application and based on an output of the object detection process, the object location and classification of the one or more objects.

Abstract: A modulated segmentation system can use a modulator network to emphasize spatial prior data of an object to track the object across multiple images. The modulated segmentation system can use a segmentation network that receives spatial prior data as intermediate data that improves segmentation accuracy. The segmentation network can further receive visual guide information from a visual guide network to increase tracking accuracy via segmentation.

Abstract: A system and a method are provided that include a processor executing a caption generation program to receive an input video, sample video frames from the input video, extract video frames from the input video, extract video embeddings and audio embeddings from the video frames, including local video tokens and local audio tokens, respectively, input the local video tokens and the local audio tokens into at least a transformer layer of a cross-modal encoder to generate multi-modal embeddings, and generate video captions based on the multi-modal embeddings using a caption decoder.

Abstract: A machine learning system can generate an image mask (e.g., a pixel mask) comprising pixel assignments for pixels. The pixels can be assigned to classes, including, for example, face, clothes, body skin, or hair. The machine learning system can be implemented using a convolutional neural network that is configured to execute efficiently on computing devices having limited resources, such as mobile phones. The pixel mask can be used to more accurately display video effects interacting with a user or subject depicted in the image.

Abstract: A unified place recognition framework handles both retrieval and re-ranking with a unified transformer model. The re-ranking modules utilizes feature correlation, attention value, and x/y coordinates into account, and learns to determine whether an image pair is from a same location.

Abstract: A machine learning system can generate an image mask (e.g., a pixel mask) comprising pixel assignments for pixels. The pixels can be assigned to classes, including, for example, face, clothes, body skin, or hair. The machine learning system can be implemented using a convolutional neural network that is configured to execute efficiently on computing devices having limited resources, such as mobile phones. The pixel mask can be used to more accurately display video effects interacting with a user or subject depicted in the image.

Abstract: A mobile device can generate real-time complex visual image effects using asynchronous processing pipeline. A first pipeline applies a complex image process, such as a neural network, to keyframes of a live image sequence. A second pipeline generates flow maps that describe feature transformations in the image sequence. The flow maps can be used to process non-keyframes on the fly. The processed keyframes and non-keyframes can be used to display a complex visual effect on the mobile device in real-time or near real-time.

Abstract: Object detection using a transformer-based object detection model includes randomly initializing basic queries for the model, modulating the basic queries based on semantics of input images, and training the model basic on features extracted from input images and the modulated queries.

Abstract: A mobile device can generate real-time complex visual image effects using asynchronous processing pipeline. A first pipeline applies a complex image process, such as a neural network, to keyframes of a live image sequence. A second pipeline generates flow maps that describe feature transformations in the image sequence. The flow maps can be used to process non-keyframes on the fly. The processed keyframes and non-keyframes can be used to display a complex visual effect on the mobile device in real-time or near real-time.

Abstract: Systems and methods for obtaining attention features are described. Some examples may include: receiving, at a projector of a transformer, a plurality of tokens associated with image features of a first dimensional space; generating, at the projector of the transformer, projected features by concatenating the plurality of tokens with a positional map, the projected features having a second dimensional space that is less than the first dimensional space; receiving, at an encoder of the transformer, the projected features and generating encoded representations of the projected features using self-attention; decoding, at a decoder of the transformer, the encoded representations and obtaining a decoded output; and projecting the decoded output to the first dimensional space and adding the image features of the first dimensional space to obtain attention features associated with the image features.

Abstract: A modulated segmentation system can use a modulator network to emphasize spatial prior data of an object to track the object across multiple images. The modulated segmentation system can use a segmentation network that receives spatial prior data as intermediate data that improves segmentation accuracy. The segmentation network can further receive visual guide information from a visual guide network to increase tracking accuracy via segmentation.

Abstract: A modulated segmentation system can use a modulator network to emphasize spatial prior data of an object to track the object across multiple images. The modulated segmentation system can use a segmentation network that receives spatial prior data as intermediate data that improves segmentation accuracy. The segmentation network can further receive visual guide information from a visual guide network to increase tracking accuracy via segmentation.

Abstract: Systems and methods for performing neural architecture search are provided. In one aspect, the system includes a processor configured to select a plurality of candidate neural networks within a search space, evaluate a performance of each of the plurality of candidate neural networks by: training each candidate neural network on a training dataset to perform the predetermined task and determining a ranking metric for each candidate neural network based on an objective function. The ranking metric includes a weight-related metric that is determined based on weights of a prediction layer of each respective candidate neural network before and after the respective candidate neural network is trained. The processor is configured to rank the plurality of candidate neural networks based on the determined ranking metrics.

Abstract: A machine learning system can generate an image mask (e.g., a pixel mask) comprising pixel assignments for pixels. The pixels can be assigned to classes, including, for example, face, clothes, body skin, or hair. The machine learning system can be implemented using a convolutional neural network that is configured to execute efficiently on computing devices having limited resources, such as mobile phones. The pixel mask can be used to more accurately display video effects interacting with a user or subject depicted in the image.

Abstract: Segmentation of an image into individual body parts is performed based on a trained model. The model is trained with a plurality of training images, each training image representing a corresponding training figure. The model is also trained with a corresponding plurality of segmentations of the training figures. Each segmentation is generated by positioning body parts between defined positions of joints of the represented figure. The body parts are represented by body part templates obtained from a template library, with the templates defining characteristics of body parts represented by the templates.

Abstract: A mobile device can generate real-time complex visual image effects using asynchronous processing pipeline. A first pipeline applies a complex image process, such as a neural network, to keyframes of a live image sequence. A second pipeline generates flow maps that describe feature transformations in the image sequence. The flow maps can be used to process non-keyframes on the fly. The processed keyframes and non-keyframes can be used to display a complex visual effect on the mobile device in real-time or near real-time.

Abstract: A machine learning system can generate an image mask (e.g., a pixel mask) comprising pixel assignments for pixels. The pixels can he assigned to classes, including, for example, face, clothes, body skin, or hair. The machine learning system can be implemented. using a convolutional neural network that is configured to execute efficiently on computing devices having limited resources, such as mobile phones. The pixel mask can be used to more accurately display video effects interacting with a user or subject depicted in the image.