activity
20152022
most citedRevisiting Fine-tuning for Few-shot Learning

30 citations · 193 across the 34 of their papers we have counts for

collaborators
Showing cs.CVShow all

43 papers · 1 filter

cs.CV2022

Learning by Asking Questions for Knowledge-based Novel Object Recognition

Kohei Uehara, Tatsuya Harada

In real-world object recognition, there are numerous object classes to be recognized. Conventional image recognition based on supervised learning can only recognize object classes…

cs.CV202215 cited

Multitask AET with Orthogonal Tangent Regularity for Dark Object Detection

Ziteng Cui, Guo-Jun Qi, Lin Gu +3

Dark environment becomes a challenge for computer vision algorithms owing to insufficient photons and undesirable noise. To enhance object detection in a dark environment, we propo…

cs.CV20213 cited

Unsupervised Pose-Aware Part Decomposition for 3D Articulated Objects

Yuki Kawana, Yusuke Mukuta, Tatsuya Harada

Articulated objects exist widely in the real world. However, previous 3D generative methods for unsupervised part decomposition are unsuitable for such objects, because they assume…

cs.CV20212 cited

Video Moment Retrieval with Text Query Considering Many-to-Many Correspondence Using Potentially Relevant Pair

Sho Maeoki, Yusuke Mukuta, Tatsuya Harada

In this paper we undertake the task of text-based video moment retrieval from a corpus of videos. To train the model, text-moment paired datasets were used to learn the correct cor…

cs.CV2021

Efficient training for future video generation based on hierarchical disentangled representation of latent variables

Naoya Fushishita, Antonio Tejero-de-Pablos, Yusuke Mukuta +1

Generating videos predicting the future of a given sequence has been an area of active research in recent years. However, an essential problem remains unsolved: most of the methods…

cs.CV2021

Neural Articulated Radiance Field

Atsuhiro Noguchi, Xiao Sun, Stephen Lin +1

We present Neural Articulated Radiance Field (NARF), a novel deformable 3D representation for articulated objects learned from images. While recent advances in 3D implicit represen…