activity
20172022
most citedUnsupervised Learning of Image Segmentation Based on Differentiable Feature Clustering

253 citations · 300 across the 15 of their papers we have counts for

collaborators
Showing cs.CVShow all

17 papers · 1 filter

cs.CV20212 cited

Multi-Modal Pedestrian Detection with Large Misalignment Based on Modal-Wise Regression and Multi-Modal IoU

Napat Wanchaitanawong, Masayuki Tanaka, Takashi Shibata +1

The combined use of multiple modalities enables accurate pedestrian detection under poor lighting conditions by using the high visibility areas from these modalities together. The…

cs.CV2021

Geometric Data Augmentation Based on Feature Map Ensemble

Takashi Shibata, Masayuki Tanaka, Masatoshi Okutomi

Deep convolutional networks have become the mainstream in computer vision applications. Although CNNs have been successful in many computer vision tasks, it is not free from drawba…

cs.CV2020

Deep Snapshot HDR Imaging Using Multi-Exposure Color Filter Array

Takeru Suda, Masayuki Tanaka, Yusuke Monno +1

In this paper, we propose a deep snapshot high dynamic range (HDR) imaging framework that can effectively reconstruct an HDR image from the RAW data captured using a multi-exposure…

cs.CV2020

Adaptive Future Frame Prediction with Ensemble Network

Wonjik Kim, Masayuki Tanaka, Masatoshi Okutomi +1

Future frame prediction in videos is a challenging problem because videos include complicated movements and large appearance changes. Learning-based future frame prediction approac…

cs.CV2020

Human Segmentation with Dynamic LiDAR Data

Tao Zhong, Wonjik Kim, Masayuki Tanaka +1

Consecutive LiDAR scans compose dynamic 3D sequences, which contain more abundant information than a single frame. Similar to the development history of image and video perception,…

cs.CV2020253 cited

Unsupervised Learning of Image Segmentation Based on Differentiable Feature Clustering

Wonjik Kim, Asako Kanezaki, Masayuki Tanaka

The usage of convolutional neural networks (CNNs) for unsupervised image segmentation was investigated in this study. In the proposed approach, label prediction and network paramet…