Results 111 to 120 of about 76,480 (326)

Chemically Doped Conductive Polymers for Wearable Health Monitoring

Advanced Materials Technologies, EarlyView.
Among conductive polymers, poly(3,4‐ethylenedioxythiophene):poly(styrenesulfonate) (PEDOT:PSS), polyaniline (PANI), and polypyrrole (PPy) are the most studied and applied. Chemical doping significantly boosts intrinsic conductivity and mechanical robustness.
Mengdi Zuo, Jian Song, Hong Hu, Le Zheng, Lei Zhang, Charles H. Lawrie   +5 more
wiley   +1 more source

WSPolyp-SAM: Weakly Supervised and Self-Guided Fine-Tuning of SAM for Colonoscopy Polyp Segmentation

Applied Sciences
Ensuring precise segmentation of colorectal polyps holds critical importance in the early diagnosis and treatment of colorectal cancer. Nevertheless, existing deep learning-based segmentation methods are fully supervised, requiring extensive, precise ...
Tingting Cai, Hongping Yan, Kun Ding, Yan Zhang, Yueyue Zhou   +4 more
doaj   +1 more source

Learning Neural Sequence-to-Sequence Models from Weak Feedback with Bipolar Ramp Loss

Transactions of the Association for Computational Linguistics, 2019
In many machine learning scenarios, supervision by gold labels is not available and conse quently neural models cannot be trained directly by maximum likelihood estimation.
Jehl, Laura, Lawrence, Carolin, Riezler, Stefan   +2 more
doaj   +1 more source

Microfluidic Hydroporation Platform for Effective Allogeneic CAR‐T Cell Production and Subsequent Functional Cytotoxicity Analysis

Advanced Materials Technologies, EarlyView.
The hydroporator platform employs controlled hydrodynamic deformation for efficient mRNA and CRISPR/Cas9 delivery into primary human T cells, enabling allogeneic CAR‐T cell manufacturing. It preserves cell functionality and drives potent gene editing, CAR expression, and tumor cytotoxicity, while feature‐based analysis links these functional outcomes ...
Soohyun Jeon, Sein Kim, Hyun‐Young Kim, Duck Cho, Sungsu Park, Seohyun Kim, Aram J. Chung   +6 more
wiley   +1 more source

Weakly-Supervised Contrastive Learning for Unsupervised Object Discovery

IEEE Transactions on Image Processing
Unsupervised object discovery (UOD) refers to the task of discriminating the whole region of objects from the background within a scene without relying on labeled datasets, which benefits the task of bounding-box-level localization and pixel-level segmentation. This task is promising due to its ability to discover objects in a generic manner.
Yunqiu Lv, Jing Zhang, Nick Barnes, Yuchao Dai   +3 more
openaire   +3 more sources

Ice hockey player identification via transformers and weakly supervised learning [PDF]

, 2021
Kanav Vats, William McNally, Pascale Walters, David A. Clausi, John Zelek   +4 more
openalex   +1 more source

High‐Throughput Screening of REBCO Superconducting Thin Films Fabricated Via Combinatorial Inkjet Printing and TLAG Process

Advanced Materials Technologies, EarlyView.
A methodological framework is presented for combinatorial REBCO thin films fabricated by drop‐on‐demand inkjet printing with controlled Rare Earth composition gradients. Automated, synchrotron‐based, and local characterization techniques produce comprehensive property maps that correlate composition and TLAG process parameters with superconducting ...
Emma Ghiara, Zeyu Wu, Mahel Voulhoux, Ona Mola Bertran, Vittorio Bertini, Carla Torres, Aiswarya Kethamkuzhi, Guilherme Theophilo Telles, Victor Fuentes, Elzbieta Pach, Cornelia Pop, Eduardo Solano, Kapil Gupta, Takanobu Kiss, Xavier Obradors, Teresa Puig   +15 more
wiley   +1 more source

Weakly supervised instance action recognition

Computational Visual Media
We study the novel problem of weakly supervised instance action recognition (WSiAR) in multi-person (crowd) scenes. We specifically aim to recognize the action of each subject in the crowd, for which we propose the use of a weakly supervised method ...
Haomin Yan, Ruize Han, Wei Feng, Jiewen Zhao, Song Wang   +4 more
doaj   +1 more source

In Situ Copper Electroplating Turns Material Extrusion 3D Printers Into Metal–Polymer Hybrid Fabricators

Advanced Materials Technologies, EarlyView.
An in situ electroplating approach for MEX 3D printing is proposed, enabling copper deposition during the fabrication of conductive polymers. The method combines a printer‐integrated plating head, ML‐based g‐code control, and stop‐and‐go printing, achieving near‐bulk copper conductivity and enabling fully embedded, assembly‐free electronic components ...
Gianluca Percoco, Nicola Larovere, Antonio Zagaria, Antonio Pavone, Rosanna Rifino, Gianni Stano   +5 more
wiley   +1 more source

Infrared Ship Segmentation Based on Weakly-Supervised and Semi-Supervised Learning

IEEE Access
Existing fully-supervised semantic segmentation methods have achieved good performance. However, they all rely on high-quality pixel-level labels. To minimize the annotation costs, weakly-supervised methods or semi-supervised methods are proposed.
Isa Ali Ibrahim, Abdallah Namoun, Sami Ullah, Hisham Alasmary, Muhammad Waqas, Iftekhar Ahmad   +5 more
doaj   +1 more source