73 citations · 212 across the 46 of their papers we have counts for
10 papers · 1 filter
Active Transfer Learning for Efficient Video-Specific Human Pose Estimation
Hiromu Taketsugu, Norimichi Ukita
Human Pose (HP) estimation is actively researched because of its wide range of applications. However, even estimators pre-trained on large datasets may not perform satisfactorily d…
Multimodal Active Measurement for Human Mesh Recovery in Close Proximity
Takahiro Maeda, Keisuke Takeshita, Norimichi Ukita +1
For physical human-robot interactions (pHRI), a robot needs to estimate the accurate body pose of a target person. However, in these pHRI scenarios, the robot cannot fully observe…
Fast Inference and Update of Probabilistic Density Estimation on Trajectory Prediction
Takahiro Maeda, Norimichi Ukita
Safety-critical applications such as autonomous vehicles and social robots require fast computation and accurate probability density estimation on trajectory prediction. To address…
Interaction-aware Joint Attention Estimation Using People Attributes
Chihiro Nakatani, Hiroaki Kawashima, Norimichi Ukita
This paper proposes joint attention estimation in a single image. Different from related work in which only the gaze-related attributes of people are independently employed, (I) th…
MVA2023 Small Object Detection Challenge for Spotting Birds: Dataset, Methods, and Results
Yuki Kondo, Norimichi Ukita, Takayuki Yamaguchi +19
Small Object Detection (SOD) is an important machine vision topic because (i) a variety of real-world applications require object detection for distant objects and (ii) SOD is a ch…
R2-Diff: Denoising by diffusion as a refinement of retrieved motion for image-based motion prediction
Takeru Oba, Norimichi Ukita
Image-based motion prediction is one of the essential techniques for robot manipulation. Among the various prediction models, we focus on diffusion models because they have achieve…
KS-DETR: Knowledge Sharing in Attention Learning for Detection Transformer
Kaikai Zhao, Norimichi Ukita
Scaled dot-product attention applies a softmax function on the scaled dot-product of queries and keys to calculate weights and then multiplies the weights and values. In this work,…
Data-Driven Stochastic Motion Evaluation and Optimization with Image by Spatially-Aligned Temporal Encoding
Takeru Oba, Norimichi Ukita
This paper proposes a probabilistic motion prediction method for long motions. The motion is predicted so that it accomplishes a task from the initial state observed in the given i…
Joint Learning of Blind Super-Resolution and Crack Segmentation for Realistic Degraded Images
Yuki Kondo, Norimichi Ukita
This paper proposes crack segmentation augmented by super resolution (SR) with deep neural networks. In the proposed method, a SR network is jointly trained with a binary segmentat…
Kernelized Back-Projection Networks for Blind Super Resolution
Tomoki Yoshida, Yuki Kondo, Takahiro Maeda +2
Since non-blind Super Resolution (SR) fails to super-resolve Low-Resolution (LR) images degraded by arbitrary degradations, SR with the degradation model is required. However, this…