Search Results for author: Kuo-Chin Lien

Found 4 papers, 0 papers with code

Pair DETR: Contrastive Learning Speeds Up DETR Training

no code implementations29 Oct 2022 Seyed Mehdi Iranmanesh, Xiaotong Chen, Kuo-Chin Lien

In this approach, we detect an object bounding box as a pair of keypoints, the top-left corner and the center, using two decoders.

Contrastive Learning object-detection +3

PatchTrack: Multiple Object Tracking Using Frame Patches

no code implementations1 Jan 2022 Xiaotong Chen, Seyed Mehdi Iranmanesh, Kuo-Chin Lien

In this paper, we present PatchTrack, a Transformer-based joint-detection-and-tracking system that predicts tracks using patches of the current frame of interest.

Multiple Object Tracking Object

Structure-Attentioned Memory Network for Monocular Depth Estimation

no code implementations10 Sep 2019 Jing Zhu, Yunxiao Shi, Mengwei Ren, Yi Fang, Kuo-Chin Lien, Junli Gu

To this end, we introduce a new Structure-Oriented Memory (SOM) module to learn and memorize the structure-specific information between RGB image domain and the depth domain.

Domain Adaptation Monocular Depth Estimation

Learning Object-specific Distance from a Monocular Image

no code implementations ICCV 2019 Jing Zhu, Yi Fang, Husam Abu-Haimed, Kuo-Chin Lien, Dongdong Fu, Junli Gu

Environment perception, including object detection and distance estimation, is one of the most crucial tasks for autonomous driving.

Autonomous Driving Object +2

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