Zobrazeno 1 - 10
of 386
pro vyhledávání: '"WEI Lina"'
Publikováno v:
Shipin Kexue, Vol 44, Iss 17, Pp 51-59 (2023)
In order to improve the drying rate and rehydration of tilapia meat, the freeze-drying characteristics and quality changes of blanched or steamed fish meat were analyzed. The effect of heat pretreatment on the quality of freeze-dried fish meat was el
Externí odkaz:
https://doaj.org/article/47fd14d14af4417aa0ae4f79d77353be
Publikováno v:
Acta Biochimica et Biophysica Sinica, Vol 54, Pp 904-916 (2022)
The incidence of endometrial cancer (EC) increases annually and tends to occur in younger women. A particularly important relationship exists between EC and metabolic disorders. As one of the most important components of lipid metabolism, phospholipi
Externí odkaz:
https://doaj.org/article/389442ee7e6540c08b22eb0c509213a1
Existing Masked Image Modeling (MIM) depends on a spatial patch-based masking-reconstruction strategy to perceive objects'features from unlabeled images, which may face two limitations when applied to chest CT: 1) inefficient feature learning due to
Externí odkaz:
http://arxiv.org/abs/2407.08961
Autor:
Ji, Wei, Liu, Xiangyan, Sun, Yingfei, Deng, Jiajun, Qin, You, Nuwanna, Ammar, Qiu, Mengyao, Wei, Lina, Zimmermann, Roger
Detecting visual content on language expression has become an emerging topic in the community. However, in the video domain, the existing setting, i.e., spatial-temporal video grounding (STVG), is formulated to only detect one pre-existing object in
Externí odkaz:
http://arxiv.org/abs/2407.05610
Adversarial training (AT) is currently one of the most effective ways to obtain the robustness of deep neural networks against adversarial attacks. However, most AT methods suffer from robust overfitting, i.e., a significant generalization gap in adv
Externí odkaz:
http://arxiv.org/abs/2403.09101
One of the fundamental challenges in microscopy (MS) image analysis is instance segmentation (IS), particularly when segmenting cluster regions where multiple objects of varying sizes and shapes may be connected or even overlapped in arbitrary orient
Externí odkaz:
http://arxiv.org/abs/2401.09895
Panoptic Scene Graph Generation (PSG) parses objects and predicts their relationships (predicate) to connect human language and visual scenes. However, different language preferences of annotators and semantic overlaps between predicates lead to bias
Externí odkaz:
http://arxiv.org/abs/2307.15567
Publikováno v:
In Carbohydrate Polymers 1 November 2024 343
Publikováno v:
In Algal Research October 2024 83
Autor:
Ma, Xueni, Li, Muyang, Wang, Xiaochun, Xu, Huimei, Jiang, Luxia, Wu, Fanqi, Wei, Lina, Qi, Guoqing, Zhang, Dekui
Publikováno v:
In International Immunopharmacology 10 September 2024 138