8 citations · 13 across the 5 of their papers we have counts for
5 papers
Adversarial Pseudo-replay for Exemplar-free Class-incremental Learning
Hiroto Honda
Exemplar-free class-incremental learning (EFCIL) aims to retain old knowledge acquired in the previous task while learning new classes, without storing the previous images due to s…
CLRerNet: Improving Confidence of Lane Detection with LaneIoU
Hiroto Honda, Yusuke Uchida
Lane marker detection is a crucial component of the autonomous driving and driver assistance systems. Modern deep lane detection methods with row-based lane representation exhibit…
End-to-End Monocular Vanishing Point Detection Exploiting Lane Annotations
Hiroto Honda, Motoki Kimura, Takumi Karasawa +1
Vanishing points (VPs) play a vital role in various computer vision tasks, especially for recognizing the 3D scenes from an image. In the real-world scenario of automobile applicat…
Leveraging Temporal Joint Depths for Improving 3D Human Pose Estimation in Video
Naoki Kato, Hiroto Honda, Yusuke Uchida
The effectiveness of the approaches to predict 3D poses from 2D poses estimated in each frame of a video has been demonstrated for 3D human pose estimation. However, 2D poses witho…
Full-body High-resolution Anime Generation with Progressive Structure-conditional Generative Adversarial Networks
Koichi Hamada, Kentaro Tachibana, Tianqi Li +2
We propose Progressive Structure-conditional Generative Adversarial Networks (PSGAN), a new framework that can generate full-body and high-resolution character images based on stru…