73 citations · 212 across the 46 of their papers we have counts for
50 papers
Any-scale Object Detection using Arbitrary-scaled Images
Kazutoshi Akita, Norimichi Ukita
This paper proposes any-scale object detection using arbitrary-scale super-resolution for continuously rescaling object images, while general multi-scale object detection uses disc…
Energy-Regularized Imitation Learning for Force- and Work-Aware Robotic Manipulation
Toshiki Otani, Hiromu Taketsugu, Norimichi Ukita
This paper studies energy-aware manipulation as a physically grounded learning problem. We define a joint-space mechanical-work proxy from joint torque and angular displacement, an…
PRISM: Predictive Representation of Interaction Style and Motion for Social Robot Navigation
Bo-Han Chen, Hiromu Taketsugu, Norimichi Ukita
Humans often observe others before interacting and adjust their behavior accordingly. Robot navigation in crowds, however, often represents pedestrians mainly by observed geometric…
A Plug-and-Play 2D Motion Interface for Real-World Motion Language Models
Kaname Yokoyama, Norimichi Ukita
Motion Language Models (MoLMs) typically understand human motions by tokenizing 3D motion and processing the resulting tokens using a language model. However, obtaining accurate 3D…
SAMIDARE: Advanced Tracking-by-Segmentation for Dense Scenarios
Shozaburo Hirano, Norimichi Ukita
Automated sports analysis demands robust multi-object tracking (MOT), yet segmentation-based methods often struggle with mask errors and ID switches in dense scenes. We propose SAM…
Group-DINOmics: Incorporating People Dynamics into DINO for Self-supervised Group Activity Feature Learning
Ryuki Tezuka, Chihiro Nakatani, Norimichi Ukita
This paper proposes Group Activity Feature (GAF) learning without group activity annotations. Unlike prior work, which uses low-level static local features to learn GAFs, we propos…
End-to-End Shared Attention Estimation via Group Detection with Feedback Refinement
Chihiro Nakatani, Norimichi Ukita, Jean-Marc Odobez
This paper proposes an end-to-end shared attention estimation method via group detection. Most previous methods estimate shared attention (SA) without detecting the actual group of…
Multi-Person Pose Estimation Evaluation Using Optimal Transportation and Improved Pose Matching
Takato Moriki, Hiromu Taketsugu, Norimichi Ukita
In Multi-Person Pose Estimation, many metrics place importance on ranking of pose detection confidence scores. Current metrics tend to disregard false-positive poses with low confi…
Human-in-the-loop Adaptation in Group Activity Feature Learning for Team Sports Video Retrieval
Chihiro Nakatani, Hiroaki Kawashima, Norimichi Ukita
This paper proposes human-in-the-loop adaptation for Group Activity Feature Learning (GAFL) without group activity annotations. This human-in-the-loop adaptation is employed in a g…
MMCM: Multimodality-aware Metric using Clustering-based Modes for Probabilistic Human Motion Prediction
Kyotaro Tokoro, Hiromu Taketsugu, Norimichi Ukita
This paper proposes a novel metric for Human Motion Prediction (HMP). Since a single past sequence can lead to multiple possible futures, a probabilistic HMP method predicts such m…
Efficient Cost-and-Quality Controllable Arbitrary-scale Super-resolution with Fourier Constraints
Kazutoshi Akita, Norimichi Ukita
Cost-and-Quality (CQ) controllability in arbitrary-scale super-resolution is crucial. Existing methods predict Fourier components one by one using a recurrent neural network. Howev…
Dynamic Group Detection using VLM-augmented Temporal Groupness Graph
Kaname Yokoyama, Chihiro Nakatani, Norimichi Ukita
This paper proposes dynamic human group detection in videos. For detecting complex groups, not only the local appearance features of in-group members but also the global context of…
Efficient Burst Super-Resolution with One-step Diffusion
Kento Kawai, Takeru Oba, Kyotaro Tokoro +2
While burst Low-Resolution (LR) images are useful for improving their Super Resolution (SR) image compared to a single LR image, prior burst SR methods are trained in a determinist…
MVA 2025 Small Multi-Object Tracking for Spotting Birds Challenge: Dataset, Methods, and Results
Yuki Kondo, Norimichi Ukita, Riku Kanayama +21
Small Multi-Object Tracking (SMOT) is particularly challenging when targets occupy only a few dozen pixels, rendering detection and appearance-based association unreliable. Buildin…
Selective Social-Interaction via Individual Importance for Fast Human Trajectory Prediction
Yota Urano, Hiromu Taketsugu, Norimichi Ukita
This paper presents an architecture for selecting important neighboring people to predict the primary person's trajectory. To achieve effective neighboring people selection, we pro…
Human Motion Prediction via Test-domain-aware Adaptation with Easily-available Human Motions Estimated from Videos
Katsuki Shimbo, Hiromu Taketsugu, Norimichi Ukita
In 3D Human Motion Prediction (HMP), conventional methods train HMP models with expensive motion capture data. However, the data collection cost of such motion capture data limits…
CacheFlow: Fast Human Motion Prediction by Cached Normalizing Flow
Takahiro Maeda, Jinkun Cao, Norimichi Ukita +1
Many density estimation techniques for 3D human motion prediction require a significant amount of inference time, often exceeding the duration of the predicted time horizon. To add…
Robot Motion Planning using One-Step Diffusion with Noise-Optimized Approximate Motions
Tomoharu Aizu, Takeru Oba, Yuki Kondo +1
This paper proposes an image-based robot motion planning method using a one-step diffusion model. While the diffusion model allows for high-quality motion generation, its computati…
Physical Plausibility-aware Trajectory Prediction via Locomotion Embodiment
Hiromu Taketsugu, Takeru Oba, Takahiro Maeda +2
Humans can predict future human trajectories even from momentary observations by using human pose-related cues. However, previous Human Trajectory Prediction (HTP) methods leverage…
Test-time Cost-and-Quality Controllable Arbitrary-Scale Super-Resolution with Variable Fourier Components
Kazutoshi Akita, Norimichi Ukita
Super-resolution (SR) with arbitrary scale factor and cost-and-quality controllability at test time is essential for various applications. While several arbitrary-scale SR methods…
Size-Variable Virtual Try-On with Physical Clothes Size
Yohei Yamashita, Chihiro Nakatani, Norimichi Ukita
This paper addresses a new virtual try-on problem of fitting any size of clothes to a reference person in the image domain. While previous image-based virtual try-on methods can pr…
Burst Super-Resolution with Diffusion Models for Improving Perceptual Quality
Kyotaro Tokoro, Kazutoshi Akita, Norimichi Ukita
While burst LR images are useful for improving the SR image quality compared with a single LR image, prior SR networks accepting the burst LR images are trained in a deterministic…
Inpainting-Driven Mask Optimization for Object Removal
Kodai Shimosato, Norimichi Ukita
This paper proposes a mask optimization method for improving the quality of object removal using image inpainting. While many inpainting methods are trained with a set of random ma…
Time-series Initialization and Conditioning for Video-agnostic Stabilization of Video Super-Resolution using Recurrent Networks
Hiroshi Mori, Norimichi Ukita
A Recurrent Neural Network (RNN) for Video Super Resolution (VSR) is generally trained with randomly clipped and cropped short videos extracted from original training videos due to…