1 citations · 2 across the 4 of their papers we have counts for
4 papers
PCT: Perspective Cue Training Framework for Multi-Camera BEV Segmentation
Haruya Ishikawa, Takumi Iida, Yoshinori Konishi +1
Generating annotations for bird's-eye-view (BEV) segmentation presents significant challenges due to the scenes' complexity and the high manual annotation cost. In this work, we ad…
Lite-HRNet Plus: Fast and Accurate Facial Landmark Detection
Sota Kato, Kazuhiro Hotta, Yuhki Hatakeyama +1
Facial landmark detection is an essential technology for driver status tracking and has been in demand for real-time estimations. As a landmark coordinate prediction, heatmap-based…
Geometry-Aware Unsupervised Domain Adaptation for Stereo Matching
Hiroki Sakuma, Yoshinori Konishi
Recently proposed DNN-based stereo matching methods that learn priors directly from data are known to suffer a drastic drop in accuracy in new environments. Although supervised app…
Visualizing Color-wise Saliency of Black-Box Image Classification Models
Yuhki Hatakeyama, Hiroki Sakuma, Yoshinori Konishi +1
Image classification based on machine learning is being commonly used. However, a classification result given by an advanced method, including deep learning, is often hard to inter…