Search Results for author: Wen-Chin Chen

Found 7 papers, 6 papers with code

Class-agnostic-Few-shot-Object-Counting

1 code implementation WACV 2021 Shuo-Diao Yang, Hung-Ting Su, Winston H. Hsu, Wen-Chin Chen

Instead of counting a pre-defined class, our model is able to count instances based on input reference images and reduces the huge cost of data collection, training and parameter tuning for each new object class.

Object Object Counting

Dual-Awareness Attention for Few-Shot Object Detection

1 code implementation24 Feb 2021 Tung-I Chen, Yueh-Cheng Liu, Hung-Ting Su, Yu-Cheng Chang, Yu-Hsiang Lin, Jia-Fong Yeh, Wen-Chin Chen, Winston H. Hsu

While recent progress has significantly boosted few-shot classification (FSC) performance, few-shot object detection (FSOD) remains challenging for modern learning systems.

Few-Shot Learning Few-Shot Object Detection +2

CrossDTR: Cross-view and Depth-guided Transformers for 3D Object Detection

1 code implementation27 Sep 2022 Ching-Yu Tseng, Yi-Rong Chen, Hsin-Ying Lee, Tsung-Han Wu, Wen-Chin Chen, Winston H. Hsu

To achieve accurate 3D object detection at a low cost for autonomous driving, many multi-camera methods have been proposed and solved the occlusion problem of monocular approaches.

3D Object Detection Autonomous Driving +5

OCID-Ref: A 3D Robotic Dataset with Embodied Language for Clutter Scene Grounding

1 code implementation NAACL 2021 Ke-Jyun Wang, Yun-Hsuan Liu, Hung-Ting Su, Jen-Wei Wang, Yu-Siang Wang, Winston H. Hsu, Wen-Chin Chen

To effectively apply robots in working environments and assist humans, it is essential to develop and evaluate how visual grounding (VG) can affect machine performance on occluded objects.

Referring Expression Referring Expression Segmentation +1

Coarse-to-Fine Point Cloud Registration with SE(3)-Equivariant Representations

1 code implementation5 Oct 2022 Cheng-Wei Lin, Tung-I Chen, Hsin-Ying Lee, Wen-Chin Chen, Winston H. Hsu

As global feature alignment requires the features to preserve the poses of input point clouds and local feature matching expects the features to be invariant to these poses, we propose an SE(3)-equivariant feature extractor to simultaneously generate two types of features.

Point Cloud Registration

MuRAL: Multi-Scale Region-based Active Learning for Object Detection

no code implementations29 Mar 2023 Yi-Syuan Liou, Tsung-Han Wu, Jia-Fong Yeh, Wen-Chin Chen, Winston H. Hsu

MuRAL identifies informative regions of various scales to reduce annotation costs for well-learned objects and improve training performance.

Active Learning Object +2

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