activity
20192022
most citedReference-Based Video Colorization with Spatiotemporal Correspondence

7 citations · 10 across the 3 of their papers we have counts for

collaborators

7 papers

cs.CV2022

Thinking the Fusion Strategy of Multi-reference Face Reenactment

Takuya Yashima, Takuya Narihira, Tamaki Kojima

In recent advances of deep generative models, face reenactment -manipulating and controlling human face, including their head movement-has drawn much attention for its wide range o…

cs.LG2021

Data Cleansing for Deep Neural Networks with Storage-efficient Approximation of Influence Functions

Kenji Suzuki, Yoshiyuki Kobayashi, Takuya Narihira

Identifying the influence of training data for data cleansing can improve the accuracy of deep learning. An approach with stochastic gradient descent (SGD) called SGD-influence to…

cs.CV2021

Perspectives and Prospects on Transformer Architecture for Cross-Modal Tasks with Language and Vision

Andrew Shin, Masato Ishii, Takuya Narihira

Transformer architectures have brought about fundamental changes to computational linguistic field, which had been dominated by recurrent neural networks for many years. Its succes…

cs.LG2021

Neural Network Libraries: A Deep Learning Framework Designed from Engineers' Perspectives

Takuya Narihira, Javier Alonsogarcia, Fabien Cardinaux +14

While there exist a plethora of deep learning tools and frameworks, the fast-growing complexity of the field brings new demands and challenges, such as more flexible network design…

cs.CV20207 cited

Reference-Based Video Colorization with Spatiotemporal Correspondence

Naofumi Akimoto, Akio Hayakawa, Andrew Shin +1

We propose a novel reference-based video colorization framework with spatiotemporal correspondence. Reference-based methods colorize grayscale frames referencing a user input color…

cs.LG20203 cited

Out-of-core Training for Extremely Large-Scale Neural Networks With Adaptive Window-Based Scheduling

Akio Hayakawa, Takuya Narihira

While large neural networks demonstrate higher performance in various tasks, training large networks is difficult due to limitations on GPU memory size. We propose a novel out-of-c…