Shenzhen Intellifusion Technologies Co., Ltd.

Tencent Technology (shenzhen) Company Limited

Wen Hao Jiang

Yan Zhang

Lin Ma

Heguo Wang

Jing Wen Wang

Lea Hwang Lee

Dan Zhang

Bai Rui Wang

Bracelet

The embodiments of the disclosure provide a video description information generation method, a video processing method, and video description information generation apparatus, and a video processing apparatus. The video description information generation method includes: obtaining a frame-level video feature sequence corresponding to a video; generating a global part-of-speech sequence feature of the video according to the video feature sequence, the global part-of-speech sequence feature being a feature of a sequence of a combination of parts of speech in the video; and generating natural language description information of the video according to the global part-of-speech sequence feature and the video feature sequence.

Method and apparatus for generating video description information, and method and apparatus for video processing

The present disclosure discloses a video description generation method and apparatus, a video playing method and apparatus, and a computer-readable storage medium. The method includes: extracting video features, and obtaining a video feature sequence corresponding to video encoding moments in a video stream; encoding the video feature sequence by using a forward recurrent neural network and a backward recurrent neural network, to obtain a forward hidden state sequence and a backward hidden state sequence corresponding to each video encoding moment; and positioning, according to the forward hidden state sequence and the backward hidden state sequence, an event corresponding to each video encoding moment and an interval corresponding to the event at the video encoding moment, thereby predicting a video content description of the event. On the basis of distinguishing overlapping events, the interval corresponding to the event is introduced to predict and generate a word corresponding to the event at the video encoding moment, and events that overlap at the video encoding moment correspond to different intervals, so that the video content descriptions of events at this video encoding moment have a high degree of distinction. By analogy, events in the given video stream can be described more distinctively.

Video description generation method and apparatus, video playing method and apparatus, and storage medium

An image processing method is configured to split a deconvolution kernel according to a preset splitting mode to obtain a sub-convolution kernel. And then, determining an original sub-matrix corresponding to the sub-convolution kernel, according to parameters of the sub-convolution kernel and an image feature matrix, and performing a convolution operation on the original sub-matrix corresponding to the sub-convolution kernel by using the sub-convolution kernel to obtain a deconvolution sub-matrix corresponding to each sub-convolution kernel; determining a target feature matrix according to the deconvolution sub-matrix corresponding to the sub-convolution kernel. When performing the deconvolution operation by the method, the image feature matrix doesn't need to perform tic-tac-toe filling to reduce a storage space occupied in the deconvolution operation process; in addition, since zero filled in the tic-tac-toe isn't participated in the deconvolution operation, calculation amount can be greatly reduced, and calculation efficiency of the deconvolution operation can be improved.

Image processing method, image processing device, electronic equipment and computer readable storage medium

The present disclosure is applied for artificial intelligence (AI) technology field and provided a method for gradient updating of an image processing model and a related apparatus thereof. The method includes: determining a convolution kernel and convoluted data corresponding to each convolution layer by invoking a direct memory access (DMA) controlling module, according to convolution parameters of each convolution layer in the image processing model, and storing the convolution kernel and the convoluted data into a first cache space and a second cache space, respectively, the convolution kernel including a convolution kernel for an original image feature gradient and a convolution kernel for an original weight gradient; and performing an inverted convolution calculation based on the convolution kernel in the first cache space and the convoluted data in the second cache space to update the original image feature gradient and the original weight gradient of each convolution layer.

Method, apparatus and system for gradient updating of image processing model

An integrated circuit includes a data storage circuit, a weight storage circuit, and an operation circuit. The data storage circuit stores, according to a preset control instruction, gray-scale value data of an image in a first preset time period; the weight storage circuit stores a data weight corresponding to the gray-scale value data in the first preset time period; the operation circuit carries out an operation on the gray-scale value data and the data weight in the first preset time period and outputs first data; the data storage circuit further stores the first data according to the preset control instruction in a second preset time period; the weight storage circuit further stores the data weight corresponding to the first data in the second preset time period; the operation circuit carries out an operation on the first data and the data weight in the second time period and outputs second data.

Growing community of inventors

Shenzhen, China

Wen Hao Jiang