activity
20162024
most citedOptimization on Submanifolds of Convolution Kernels in CNNs

39 citations · 47 across the 9 of their papers we have counts for

collaborators

11 papers

math.NA2024

A Simple Channel Compression Method for Brain Signal Decoding on Classification Task

Changqing Ji, Keisuke Kawasaki, Isao Hasegawa +1

In the application of brain-computer interface (BCI), while pursuing accurate decoding of brain signals, we also need consider the computational efficiency of BCI devices. ECoG sig…

cs.CV2024

Rethinking Annotation for Object Detection: Is Annotating Small-size Instances Worth Its Cost?

Yusuke Hosoya, Masanori Suganuma, Takayuki Okatani

Detecting objects occupying only small areas in an image is difficult, even for humans. Therefore, annotating small-size object instances is hard and thus costly. This study questi…

cs.CV20241 cited

Temporal Insight Enhancement: Mitigating Temporal Hallucination in Multimodal Large Language Models

Li Sun, Liuan Wang, Jun Sun +1

Recent advancements in Multimodal Large Language Models (MLLMs) have significantly enhanced the comprehension of multimedia content, bringing together diverse modalities such as te…

cs.CV20231 cited

Bridge Damage Cause Estimation Using Multiple Images Based on Visual Question Answering

Tatsuro Yamane, Pang-jo Chun, Ji Dang +1

In this paper, a bridge member damage cause estimation framework is proposed by calculating the image position using Structure from Motion (SfM) and acquiring its information via V…

cs.CV2022

GRIT: Faster and Better Image captioning Transformer Using Dual Visual Features

Van-Quang Nguyen, Masanori Suganuma, Takayuki Okatani

Current state-of-the-art methods for image captioning employ region-based features, as they provide object-level information that is essential to describe the content of images; th…

cs.CV20221 cited

Single-image Defocus Deblurring by Integration of Defocus Map Prediction Tracing the Inverse Problem Computation

Qian Ye, Masanori Suganuma, Takayuki Okatani

In this paper, we consider the problem in defocus image deblurring. Previous classical methods follow two-steps approaches, i.e., first defocus map estimation and then the non-blin…