Search Results for author: Keiji Yanai

Found 9 papers, 5 papers with code

Focusing on what to decode and what to train: Efficient Training with HOI Split Decoders and Specific Target Guided DeNoising

1 code implementation5 Jul 2023 Junwen Chen, Yingcheng Wang, Keiji Yanai

However, the current methods redirect the detection target of the object decoder, and the box target is not explicitly separated from the query embeddings, which leads to long and hard training.

Denoising Human-Object Interaction Detection +3

Transformer-based Cross-Modal Recipe Embeddings with Large Batch Training

no code implementations10 May 2022 Jing Yang, Junwen Chen, Keiji Yanai

In this paper, we present a cross-modal recipe retrieval framework, Transformer-based Network for Large Batch Training (TNLBT), which is inspired by ACME~(Adversarial Cross-Modal Embedding) and H-T~(Hierarchical Transformer).

Contrastive Learning Image Generation +2

QAHOI: Query-Based Anchors for Human-Object Interaction Detection

1 code implementation16 Dec 2021 Junwen Chen, Keiji Yanai

Human-object interaction (HOI) detection as a downstream of object detection tasks requires localizing pairs of humans and objects and extracting the semantic relationships between humans and objects from an image.

Human-Object Interaction Detection Object +2

IPN Hand: A Video Dataset and Benchmark for Real-Time Continuous Hand Gesture Recognition

1 code implementation20 Apr 2020 Gibran Benitez-Garcia, Jesus Olivares-Mercado, Gabriel Sanchez-Perez, Keiji Yanai

The experimental results show that the state-of-the-art ResNext-101 model decreases about 30% accuracy when using our real-world dataset, demonstrating that the IPN Hand dataset can be used as a benchmark, and may help the community to step forward in the continuous HGR.

Hand Gesture Recognition Hand-Gesture Recognition +2

Iconify: Converting Photographs into Icons

no code implementations7 Apr 2020 Takuro Karamatsu, Gibran Benitez-Garcia, Keiji Yanai, Seiichi Uchida

In this paper, we tackle a challenging domain conversion task between photo and icon images.

Self-Supervised Difference Detection for Weakly-Supervised Semantic Segmentation

1 code implementation ICCV 2019 Wataru Shimoda, Keiji Yanai

In this paper, to make the most of such mapping functions, we assume that the results of the mapping function include noise, and we improve the accuracy by removing noise.

Segmentation Weakly supervised segmentation +2

Scene Text Eraser

no code implementations8 May 2017 Toshiki Nakamura, Anna Zhu, Keiji Yanai, Seiichi Uchida

That proves the effectiveness of proposed method for erasing the text in natural scene images.

Scene Text Detection Text Detection

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