* To appear in IEEE Transactions ON Neural Networks and Learning
Systems. We prove that dynamically adapting network architectures tailored
for each domain task along with weight finetuning benefits in both efficiency
and effectiveness, compared to the existing image recognition pipeline that
only tunes the weights regardless of the architecture Access Paper or Ask Questions
* To appear in IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE
INTELLIGENCE (T-PAMI) 2021. We propose a graph reasoning and transfer
learning framework, which incorporates human knowledge and label taxonomy
into the intermediate graph representation learning beyond local
convolutions. arXiv admin note: substantial text overlap with
arXiv:1904.04536 Access Paper or Ask Questions
* To appear in IEEE Transactions on Cybernetics 2021. We attempt to
resolve the challenging medical report composition task by i) enforcing the
semantic consistency of medical terms to be incorporated into the final
reports; and ii) encouraging the sentence generation for rare abnormal
descriptions Access Paper or Ask Questions
* To appear in TNNLS 2021. Considering that a desirable VQA model
should correctly perceive the image context, understand the question, and
incorporate its learned knowledge, our proposed dataset aims to cutoff the
shortcut learning exploited by the current deep embedding models and push the
research boundary of the knowledge-based visual question reasoning Access Paper or Ask Questions
* This work has been submitted to the IEEE for possible publication.
Copyright may be transferred without notice, after which this version may no
longer be accessible. This paper focuses on the sensor-to-vision heterogenous
action recognition problem. Codes is available in
https://github.com/YangLiu9208/SAKDN Access Paper or Ask Questions