Zobrazeno 1 - 10
of 604
pro vyhledávání: '"Baocai Yin"'
Publikováno v:
IET Computer Vision, Vol 18, Iss 5, Pp 652-665 (2024)
Abstract Image‐text retrieval is a fundamental yet challenging task, which aims to bridge a semantic gap between heterogeneous data to achieve precise measurements of semantic similarity. The technique of fine‐grained alignment between cross‐mo
Externí odkaz:
https://doaj.org/article/2e15baefa54a4204b01a0ea3f1e02b75
Publikováno v:
Journal of Big Data, Vol 11, Iss 1, Pp 1-22 (2024)
Abstract Short-term traffic flow forecasting is a hot issue in the field of intelligent transportation. The research field of traffic forecasting has evolved greatly in past decades. With the rapid development of deep learning and neural networks, a
Externí odkaz:
https://doaj.org/article/a1031da53523489e8e4cc314289273d4
Publikováno v:
IET Computer Vision, Vol 18, Iss 3, Pp 355-369 (2024)
Abstract In industrial manufacturing, how to accurately classify defective products and locate the location of defects has always been a concern. Previous studies mainly measured similarity based on extracting single‐scale features of samples. Howe
Externí odkaz:
https://doaj.org/article/5908fda693ca4f27a2c4206b074ff418
Publikováno v:
IET Image Processing, Vol 18, Iss 4, Pp 1083-1095 (2024)
Abstract Referring image segmentation identifies the object masks from images with the guidance of input natural language expressions. Nowadays, many remarkable cross‐modal decoder are devoted to this task. But there are mainly two key challenges i
Externí odkaz:
https://doaj.org/article/bec0e0d2b6e84f028d75c92b25cffc32
Publikováno v:
IET Computer Vision, Vol 18, Iss 1, Pp 33-45 (2024)
Abstract Due to the huge cost of manual annotations, the labelled data may not be sufficient to train a dynamic facial expression (DFR) recogniser with good performance. To address this, the authors propose a multi‐modal pre‐training method with
Externí odkaz:
https://doaj.org/article/a5f5658a785145d7a69d2fad4846f6c9
Autor:
Kan Guo, Daxin Tian, Yongli Hu, Yanfeng Sun, Zhen (Sean) Qian, Jianshan Zhou, Junbin Gao, Baocai Yin
Publikováno v:
IET Intelligent Transport Systems, Vol 18, Iss 2, Pp 290-301 (2024)
Abstract Contrastive learning is an increasingly important research direction and has attracted considerable attention in the field of computer vision. It can greatly improve the representativeness of image features through data augmentation, unsuper
Externí odkaz:
https://doaj.org/article/a7efa7c2cf4445559231aac667a9fc5f
Publikováno v:
Sensors, Vol 24, Iss 16, p 5439 (2024)
The surge in image data has significantly increased the pressure on storage and transmission, posing new challenges for image compression technology. The structural texture of an image implies its statistical characteristics, which is effective for i
Externí odkaz:
https://doaj.org/article/033eff522ed44357934a56ba33645e63
Publikováno v:
IET Intelligent Transport Systems, Vol 17, Iss 10, Pp 2020-2033 (2023)
Abstract Real‐time passenger‐flow anomaly detection at all metro stations is a very critical task for advanced Internet management. Robust principal component analysis (RPCA) based method has often been employed for anomaly detection task of mult
Externí odkaz:
https://doaj.org/article/3ec188fc268342f0b970f136231f15eb
Publikováno v:
IET Intelligent Transport Systems, Vol 17, Iss 9, Pp 1835-1845 (2023)
Abstract Traffic prediction is an important part of intelligent transportation system. Recently, graph convolution network (GCN) is introduced for traffic flow forecasting and achieves good performance due to its superiority of representing the graph
Externí odkaz:
https://doaj.org/article/37c4dfd183ef45eda034286fde46325f
Publikováno v:
IET Computer Vision, Vol 17, Iss 6, Pp 638-651 (2023)
Abstract Visual Question Answering (VQA) aims to appropriately answer a text question by understanding the image content. Attention‐based VQA models mine the implicit relationships between objects according to the feature similarity, which neglects
Externí odkaz:
https://doaj.org/article/6e1188e14d3d45ccbc23509d6db0f970