activity
20192022
most citedIterNet: Retinal Image Segmentation Utilizing Structural Redundancy in Vessel Networks

22 citations · 56 across the 10 of their papers we have counts for

collaborators

12 papers

cs.CV20221 cited

Contrastive Losses Are Natural Criteria for Unsupervised Video Summarization

Zongshang Pang, Yuta Nakashima, Mayu Otani +1

Video summarization aims to select the most informative subset of frames in a video to facilitate efficient video browsing. Unsupervised methods usually rely on heuristic training…

cs.CV2022

A General Scattering Phase Function for Inverse Rendering

Thanh-Trung Ngo, Hajime Nagahara

We tackle the problem of modeling light scattering in homogeneous translucent material and estimating its scattering parameters. A scattering phase function is one of such paramete…

cs.CV20214 cited

Built Year Prediction from Buddha Face with Heterogeneous Labels

Yiming Qian, Cheikh Brahim El Vaigh, Yuta Nakashima +3

Buddha statues are a part of human culture, especially of the Asia area, and they have been alongside human civilisation for more than 2,000 years. As history goes by, due to wars,…

cs.LG20214 cited

GCNBoost: Artwork Classification by Label Propagation through a Knowledge Graph

Cheikh Brahim El Vaigh, Noa Garcia, Benjamin Renoust +3

The rise of digitization of cultural documents offers large-scale contents, opening the road for development of AI systems in order to preserve, search, and deliver cultural herita…

cs.CV20201 cited

Match Them Up: Visually Explainable Few-shot Image Classification

Bowen Wang, Liangzhi Li, Manisha Verma +3

Few-shot learning (FSL) approaches are usually based on an assumption that the pre-trained knowledge can be obtained from base (seen) categories and can be well transferred to nove…

cs.CV2020

Noisy-LSTM: Improving Temporal Awareness for Video Semantic Segmentation

Bowen Wang, Liangzhi Li, Yuta Nakashima +3

Semantic video segmentation is a key challenge for various applications. This paper presents a new model named Noisy-LSTM, which is trainable in an end-to-end manner, with convolut…