Search Results for author: Norimichi Ukita

Found 24 papers, 13 papers with code

Fast Inference and Update of Probabilistic Density Estimation on Trajectory Prediction

1 code implementation ICCV 2023 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.

Autonomous Vehicles Density Estimation +1

Interaction-aware Joint Attention Estimation Using People Attributes

1 code implementation ICCV 2023 Chihiro Nakatani, Hiroaki Kawashima, Norimichi Ukita

We introduce a specialized MLP head with positional embedding to the Transformer so that it predicts pixelwise confidence of joint attention for generating the confidence heatmap.

MVA2023 Small Object Detection Challenge for Spotting Birds: Dataset, Methods, and Results

1 code implementation18 Jul 2023 Yuki Kondo, Norimichi Ukita, Takayuki Yamaguchi, Hao-Yu Hou, Mu-Yi Shen, Chia-Chi Hsu, En-Ming Huang, Yu-Chen Huang, Yu-Cheng Xia, Chien-Yao Wang, Chun-Yi Lee, Da Huo, Marc A. Kastner, TingWei Liu, Yasutomo Kawanishi, Takatsugu Hirayama, Takahiro Komamizu, Ichiro Ide, Yosuke Shinya, Xinyao Liu, Guang Liang, Syusuke Yasui

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 challenging task due to the noisy, blurred, and less-informative image appearances of small objects.

Ranked #2 on Small Object Detection on SOD4SB Public Test (using extra training data)

Object object-detection +1

R2-Diff: Denoising by diffusion as a refinement of retrieved motion for image-based motion prediction

no code implementations15 Jun 2023 Takeru Oba, Norimichi Ukita

In R2-Diff, a motion retrieved from a dataset based on image similarity is fed into a diffusion model instead of random noise.

Denoising motion prediction +2

KS-DETR: Knowledge Sharing in Attention Learning for Detection Transformer

1 code implementation22 Feb 2023 Kaikai Zhao, Norimichi Ukita

We propose a triple-attention module in which the first attention is a plain scaled dot-product attention, the second/third attention generates high-quality weights/values (with the assistance of GT Fg-Bg Mask) and shares the values/weights with the first attention to improve the quality of values/weights.

Knowledge Distillation Transfer Learning

Kernelized Back-Projection Networks for Blind Super Resolution

no code implementations16 Feb 2023 Tomoki Yoshida, Yuki Kondo, Takahiro Maeda, Kazutoshi Akita, Norimichi Ukita

In our second model, the Kernelized BackProjection Network (KBPN), a raw kernel is estimated and directly employed for modeling the image degradation.

Blind Super-Resolution Super-Resolution

Data-Driven Stochastic Motion Evaluation and Optimization with Image by Spatially-Aligned Temporal Encoding

no code implementations10 Feb 2023 Takeru Oba, Norimichi Ukita

While our method evaluates the task achievability by the Energy-Based Model (EBM), previous EBMs are not designed for evaluating the consistency between different domains (i. e., image and motion in our method).

motion prediction

Image Super-Resolution using Explicit Perceptual Loss

no code implementations1 Sep 2020 Tomoki Yoshida, Kazutoshi Akita, Muhammad Haris, Norimichi Ukita

The previous approaches use several loss functions which is hard to interpret and has the implicit relationships to improve the perceptual score.

Image Super-Resolution

Space-Time-Aware Multi-Resolution Video Enhancement

1 code implementation CVPR 2020 Muhammad Haris, Greg Shakhnarovich, Norimichi Ukita

We consider the problem of space-time super-resolution (ST-SR): increasing spatial resolution of video frames and simultaneously interpolating frames to increase the frame rate.

Video Enhancement Video Super-Resolution

Semi- and Weakly-supervised Human Pose Estimation

no code implementations4 Jun 2019 Norimichi Ukita, Yusuke Uematsu

While the first and second learning schemes select only poses that are similar to those in the supervised training data, the third scheme selects more true-positive poses that are significantly different from any supervised poses.

Clustering Pose Estimation +1

Deep Back-Projection Networks for Single Image Super-resolution

7 code implementations4 Apr 2019 Muhammad Haris, Greg Shakhnarovich, Norimichi Ukita

Previous feed-forward architectures of recently proposed deep super-resolution networks learn the features of low-resolution inputs and the non-linear mapping from those to a high-resolution output.

Image Super-Resolution

Human Pose Estimation using Motion Priors and Ensemble Models

no code implementations26 Jan 2019 Norimichi Ukita

Human pose estimation in images and videos is one of key technologies for realizing a variety of human activity recognition tasks (e. g., human-computer interaction, gesture recognition, surveillance, and video summarization).

2D Human Pose Estimation 3D Human Pose Tracking +4

Task-Driven Super Resolution: Object Detection in Low-resolution Images

no code implementations30 Mar 2018 Muhammad Haris, Greg Shakhnarovich, Norimichi Ukita

We consider how image super resolution (SR) can contribute to an object detection task in low-resolution images.

Image Super-Resolution Object +2

Deep Back-Projection Networks For Super-Resolution

17 code implementations CVPR 2018 Muhammad Haris, Greg Shakhnarovich, Norimichi Ukita

The feed-forward architectures of recently proposed deep super-resolution networks learn representations of low-resolution inputs, and the non-linear mapping from those to high-resolution output.

Image Super-Resolution Video Super-Resolution

Cannot find the paper you are looking for? You can Submit a new open access paper.