Beijing Baidu Netcom Science and Technology Co., Ltd.

Baidu USA LLC

Beijing Baidu Netcom Science Technology Co., Ltd

Baidu.com Times Technology (Beijing) Co. Ltd.

Wenhao Wu

Wei Li

Xinyan Xiao

Dongliang He

Baopu Li

Zhihong Pan

Jiachen Liu

Tianwei Lin

Yuxiang Zhao

Image super-resolution (SR) refers to the process of recovering high-resolution (HR) images from low-resolution (LR) inputs. Blind image SR is a more challenging task which involves unknown blurring kernels and characterizes the degradation process from HR to LR. In the present disclosure, embodiments of a variational autoencoder (VAE) are leveraged to train a kernel autoencoder for more accurate degradation representation and more efficient kernel estimation. In one or more embodiments, a kernel-agnostic loss is used to learn more robust kernel features in the latent space from LR inputs without using ground-truth kernel references. In addition, attention-based adaptive pooling is introduced to improve kernel estimation accuracy, and spatially non-uniform kernel features are passed into SR restoration resulting in additional kernel estimation error tolerance. Extensive experiments on synthetic and real-world images show that embodiments of the presented model outperform state-of-the-art methods significantly with the peak signal-to-noise ratio (PSNR) raised considerably.

Robust and efficient blind super-resolution using variational kernel autoencoder

The present disclosure provides a summary generation model training method and apparatus, a device and a storage medium, and relates to the field of computer technologies, and in particular, to the field of artificial intelligence such as natural language processing and deep learning. The summary generation model training method includes: acquiring a document representation corresponding to a document sample; constructing, based on the document representation, a summary representation corresponding to the document representation, the summary representation including a positive summary representation and a negative summary representation; and constructing a total contrastive loss function based on the document representation, the positive summary representation and the negative summary representation, and training a summary generation model based on the total contrastive loss function. The present disclosure may improve accuracy of the summary generation model.

Summary generation model training method and apparatus, device and storage medium

Provided are a video recognition method and apparatus, an electronic device, a medium and a computer program product. The video recognition method is described below. A to-be-recognized video is divided into at least two video segments; video frames are extracted from the at least two video segments, and feature recognition is performed on the video frames to obtain initial semantic feature blocks of the at least two video segments; each of the initial semantic feature blocks is fused, and a fused target semantic feature block is obtained; and a type of the to-be-recognized video is determined according to the fused target semantic feature block.

Video recognition method and apparatus, electronic device and storage medium

A method, an apparatus, an electronic device and a computer readable storage medium for classifying a video are provided. The method may include: acquiring a to-be-classified video and an image complexity of the to-be-classified video; extracting a feature map with a resolution corresponding to the image complexity from the to-be-classified video; and determining a target video class to which the to-be-classified video belongs based on the feature map.

Method, apparatus, electronic device and readable storage medium for classifying video

Growing community of inventors

Beijing, China

Wenhao Wu