Zobrazeno 1 - 10
of 113
pro vyhledávání: '"Qimin Cheng"'
Publikováno v:
International Journal of Digital Earth, Vol 16, Iss 2, Pp 4848-4866 (2023)
ABSTRACTRemote Sensing Image Captioning (RSIC) plays a crucial role in advancing semantic understanding and has increasingly become a focal point of research. Nevertheless, existing RSIC methods grapple with challenges due to the intricate multi-scal
Externí odkaz:
https://doaj.org/article/d144ee6e2d634972896f943d9224b377
Publikováno v:
Remote Sensing, Vol 16, Iss 16, p 2961 (2024)
Pioneering remote sensing image captioning (RSIC) works use autoregressive decoding for fluent and coherent sentences but suffer from high latency and high computation costs. In contrast, non-autoregressive approaches improve inference speed by predi
Externí odkaz:
https://doaj.org/article/531bc0f3d10c4be5ac90c21d794010dd
Publikováno v:
Remote Sensing, Vol 16, Iss 15, p 2751 (2024)
Despite impressive progress, obtaining appropriate data for instance-level lane segmentation remains a significant challenge. This limitation hinders the refinement of granular lane-related applications such as lane line crossing surveillance, paveme
Externí odkaz:
https://doaj.org/article/76e4da90555f4aaabf46866a5ba67bff
Publikováno v:
Sensors, Vol 24, Iss 5, p 1386 (2024)
Risky driving is a major factor in traffic incidents, necessitating constant monitoring and prevention through Intelligent Transportation Systems (ITS). Despite recent progress, a lack of suitable data for detecting risky driving in traffic surveilla
Externí odkaz:
https://doaj.org/article/457683d90284426f928a529d92165939
Publikováno v:
Remote Sensing, Vol 16, Iss 1, p 90 (2023)
The effectiveness of hashing methods in big data retrieval has been proved due to their merit in computational and storage efficiency. Recently, encouraged by the strong discriminant capability of deep learning in image representation, various deep h
Externí odkaz:
https://doaj.org/article/640740daa26040bcb952308412a16fae
Publikováno v:
Foods, Vol 12, Iss 23, p 4293 (2023)
A reasonable and balanced diet is essential for maintaining good health. With advancements in deep learning, an automated nutrition estimation method based on food images offers a promising solution for monitoring daily nutritional intake and promoti
Externí odkaz:
https://doaj.org/article/d81b01de92d24560a26c5f40ff6a1ce8
Publikováno v:
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol 14, Pp 2711-2723 (2021)
Conventional deep-learning-based retrieval models are generally trained under the framework of scene classification with cross-entropy loss, this way focuses only on the output probability corresponding to the label of input samples, while ignoring t
Externí odkaz:
https://doaj.org/article/bbdf70622b0249e8a392a19122d2d4e1
Publikováno v:
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol 14, Pp 4284-4297 (2021)
Because of the rapid growth of multimodal data from the internet and social media, a cross-modal retrieval has become an important and valuable task in recent years.The purpose of the cross-modal retrieval is to obtain the result data in one modality
Externí odkaz:
https://doaj.org/article/439190b951094509ba2b51337c13bc67
Publikováno v:
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol 13, Pp 318-328 (2020)
Conventional remote sensing image retrieval (RSIR) system usually performs single-label retrieval where each image is annotated by a single label representing the most significant semantic content of the image. In this scenario, however, the scene co
Externí odkaz:
https://doaj.org/article/f7a2534c069b40b29454ff6808a2a053
Publikováno v:
Complexity, Vol 2021 (2021)
Externí odkaz:
https://doaj.org/article/611cb1c05b8e4409aacbcc40f69a3328