Results 81 to 90 of about 3,651 (256)

Stack-Captioning: Coarse-to-Fine Learning for Image Captioning

Proceedings of the AAAI Conference on Artificial Intelligence, 2018
The existing image captioning approaches typically train a one-stage sentence decoder, which is difficult to generate rich fine-grained descriptions. On the other hand, multi-stage image caption model is hard to train due to the vanishing gradient problem.
Jiuxiang Gu, Jianfei Cai 0001, Gang Wang 0012, Tsuhan Chen   +3 more
openaire   +4 more sources

AI Designed Conformation Locking Peptides Target STING to Restore Diabetic Wound Healing

Advanced Science, EarlyView.
A generative AI pipeline identifies SCP‐1, a conformation‐locking peptide that stabilizes inactive STING. Incorporated into a dual‐responsive hydrogel for localized, MMP‐9‐triggered release, SCP‐1 suppresses inflammation, promotes reparative macrophage polarization, and accelerates diabetic wound healing.
Xinyu Li, Haojie Fu, Zhe Wang, Xuanzhou Chen, Ruhong Zhang, Xudong Wang, Louis D. Zhang, Xiang Li, Datao Li   +8 more
wiley   +1 more source

Multi‐task learning for captioning images with novel words

IET Computer Vision, 2019
Recent captioning models are limited in their ability to describe concepts unseen in paired image–sentence pairs. This study presents a framework of multi‐task learning for describing novel words not present in existing image‐captioning datasets.
He Zheng, Jiahong Wu, Rui Liang, Ye Li, Xuzhi Li   +4 more
doaj   +1 more source

Heat‐Suppressing Projection Two‐Photon Lithography Enables High‐Throughput Sub‐Micrometer Manufacturing of Biopolymer Hydrogels for Tissue Engineering

Advanced Science, EarlyView.
The iLEAP technique integrates high‐throughput two‐photon lithography with extrusion printing, bridging sub‐micrometer precision and macroscopic scaffold fabrication. By employing a low‐exothermic photoinitiator, it mitigates thermal damage to biopolymers and preserves bioactivity.
Qifeng Guan, Yanzhe Fu, Xiangyu Xu, Naitao Li, Sen Hou, Kai Wang, Yufan Wang, Jiakun Li, Ping Li, Jiebo Li, Lizhen Wang, Yubo Fan   +11 more
wiley   +1 more source

Image Captioning Method Based on Transformer Visual Features Fusion [PDF]

Jisuanji gongcheng
Existing image captioning methods only use regional visual features to generate description statements and ignore the importance of grid visual features. Moreover, as these methods are two-stage approaches, image captioning quality is affected.
Xuebing BAI, Jin CHE, Jinman WU, Yumin CHEN
doaj   +1 more source

POLLEN 73E Caption

, 2019
Pollen from Brazilian Savannah (Cerrado), Mato Grosso do Sul state. The images were used for training and test software based on computer vision and machine learning.
openaire   +1 more source

Sonoselective Transfection of Glioma Endothelium

Advanced Science, EarlyView.
Delivering non‐viral, gene‐bearing nanoparticles with thiol‐decorated surfaces to gliomas with focused ultrasound yields transfection tropism for endothelial cells. From this platform, “sonoselective” transfection of glioma endothelium is achieved via incorporation of an endothelial cell‐specific promoter.
Anna C. Debski, Catherine M. Gorick, Victoria R. Breza, Jackson Tirrell, Krishan Perumal, Katherine M. Nowak, Ji Song, Natasha D. Sheybani, Richard J. Price   +8 more
wiley   +1 more source

Heat‐to‐Electricity Conversion Using Barium Strontium Titanate Multilayer Capacitors

Advanced Science, EarlyView.
Lead‐free barium strontium titanate multilayer capacitors convert waste heat into electricity via the Olsen electro‐thermodynamic cycle. These capacitors achieve an energy density of 3.7 J cm−3, comparable to the performance of lead‐based ceramics. Their high dielectric strength and broad operating temperature window below 100°C make them practical for
Fan Ni, Junning Li, Uros Prah, Youri Nouchokgwe, Yves Fleming, Ashwath Aravindhan, Moiz Khalil, Torsten Granzow, Sakyo Hirose, Veronika Kovacova, Emmanuel Defay   +10 more
wiley   +1 more source

NLP-Based Fusion Approach to Robust Image Captioning

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Robustness in remote sensing image captioning is crucial for real-world applications. However, most of the research focuses on improving the performance of single captioning algorithms, either by introducing novel feature processing units or metatasks ...
Riccardo Ricci, Farid Melgani, Jose Marcato Junior, Wesley Nunes Goncalves   +3 more
doaj   +1 more source

Caption this ???!?!?!

Dieser Beitrag ist ein kreativer Kommentar, eine praktisch-rezeptive Antwort auf den Film Everything but the World (DIS 2021). Stills und Zitate bilden das Ausgangsmaterial für ein Mit-, Nach- und Weiterdenken seiner zentralen Motive und Fragestellungen.
Lomparski, Anja, Wodicka, Jana
openaire   +2 more sources