Abstract: In particular embodiments, a computing system may access a plurality of images for pre-training a first machine-learning model that includes an encoder and a decoder. Using each image, the system may pre-train the model by dividing the image into a set a patches, selecting a first subset of the patches to be visible and a second subset of the patches to be masked during the pre-training, processing, using the encoder, the first subset of patches to generate corresponding first latent representations, processing, using the decoder, the first latent representations corresponding to the first subset of patches and mask tokens corresponding to the second subset of patches to generate reconstructed patches corresponding to the second subset of patches, the reconstructed patches and the first subset of patches being used to generate a reconstructed image, and updating the model based on comparisons between the image and the reconstructed image.

Abstract: An image processing method, device, storage medium and camera are provided. The method, applied to the camera, comprises: capturing a target image; acquiring a target feature map of the target image through a preset target convolution layer, wherein the target convolution layer includes at least one of a plurality of convolution layers of a convolutional neural network (CNN); and outputting the target feature map. That is to say, after the target image is captured by the camera, the target feature map may be acquired by processing the target image through the target convolution layer pre-integrated in the camera. In this way, the camera transmits the target feature map only to reduce the transmitted data volume, thereby being capable of shortening transmission delay and saving bandwidth required by image transmission.

Abstract: A method for tracking target object, storage medium and electronic device, which relate to the field of an image processing technology. The method includes: receiving at least one target image captured by a single photon avalanche diode (SPAD) camera before present moment; for each target image, inputting the target image and a preset template image into a pre-trained siamese network to acquire a position of a target object in the target image output by the siamese network, wherein the template image includes the target object; and determining a position of the target object in an image to be predicted based on the position of the target object in each target image, wherein the image to be predicted is an image captured by the SPAD camera at the present moment.

Abstract: An image processing method, device, storage medium and camera are provided. The method, applied to the camera, comprises: capturing a target image; acquiring a target feature map of the target image through a preset target convolution layer, wherein the target convolution layer includes at least one of a plurality of convolution layers of a convolutional neural network (CNN); and outputting the target feature map. That is to say, after the target image is captured by the camera, the target feature map may be acquired by processing the target image through the target convolution layer pre-integrated in the camera. In this way, the camera transmits the target feature map only to reduce the transmitted data volume, thereby being capable of shortening transmission delay and saving bandwidth required by image transmission.

Abstract: A method for tracking target object, storage medium and electronic device, which relate to the field of an image processing technology. The method includes: receiving at least one target image captured by a single photon avalanche diode (SPAD) camera before present moment; for each target image, inputting the target image and a preset template image into a pre-trained siamese network to acquire a position of a target object in the target image output by the siamese network, wherein the template image includes the target object; and determining a position of the target object in an image to be predicted based on the position of the target object in each target image, wherein the image to be predicted is an image captured by the SPAD camera at the present moment.

Abstract: In implementations of the subject matter described herein, an action detection scheme using a recurrent neural network (RNN) is proposed. Representation information of an incoming frame of a video and a predefined action label for the frame are obtained to train a learning network including RNN elements and a classification element. The representation information represents an observed entity in the frame. Specifically, parameters for the RNN elements are determined based on the representation information and the predefined action label. With the determined parameters, the RNN elements are caused to extract features for the frame based on the representation information and features for a preceding frame. Parameters for the classification element are determined based on the extracted features and the predefined action label. The classification element with the determined parameters generates a probability of the frame being associated with the predefined action label.

Abstract: In implementations of the subject matter described herein, an action detection scheme using a recurrent neural network (RNN) is proposed. Representation information of an incoming frame of a video and a predefined action label for the frame are obtained to train a learning network including RNN elements and a classification element. The representation information represents an observed entity in the frame. Specifically, parameters for the RNN elements are determined based on the representation information and the predefined action label. With the determined parameters, the RNN elements are caused to extract features for the frame based on the representation information and features for a preceding frame. Parameters for the classification element are determined based on the extracted features and the predefined action label. The classification element with the determined parameters generates a probability of the frame being associated with the predefined action label.