Search

Your search keyword '"Chiu, Wei-Chen"' showing total 205 results
Start Over Author "Chiu, Wei-Chen"

Refine your results

more »

more »

more »

more »
205 results on '"Chiu, Wei-Chen"'

51. Class-Incremental Learning with Rectified Feature-Graph Preservation

Author

Lei, Cheng-Hsun, Chen, Yi-Hsin, Peng, Wen-Hsiao, Chiu, Wei-Chen, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Woeginger, Gerhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Ishikawa, Hiroshi, editor, Liu, Cheng-Lin, editor, Pajdla, Tomas, editor, and Shi, Jianbo, editor

Published
2021
Full Text
View/download PDF

52. Colorization of Depth Map via Disentanglement

Author

Lai, Chung-Sheng, You, Zunzhi, Huang, Ching-Chun, Tsai, Yi-Hsuan, Chiu, Wei-Chen, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Woeginger, Gerhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Vedaldi, Andrea, editor, Bischof, Horst, editor, Brox, Thomas, editor, and Frahm, Jan-Michael, editor

Published
2020
Full Text
View/download PDF

53. Towards Segmenting Consumer Stereo Videos: Benchmark, Baselines and Ensembles

Author

Chiu, Wei-Chen, Galasso, Fabio, and Fritz, Mario

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Are we ready to segment consumer stereo videos? The amount of this data type is rapidly increasing and encompasses rich information of appearance, motion and depth cues. However, the segmentation of such data is still largely unexplored. First, we propose therefore a new benchmark: videos, annotations and metrics to measure progress on this emerging challenge. Second, we evaluate several state of the art segmentation methods and propose a novel ensemble method based on recent spectral theory. This combines existing image and video segmentation techniques in an efficient scheme. Finally, we propose and integrate into this model a novel regressor, learnt to optimize the stereo segmentation performance directly via a differentiable proxy. The regressor makes our segmentation ensemble adaptive to each stereo video and outperforms the segmentations of the ensemble as well as a most recent RGB-D segmentation technique., Comment: accepted by ACCV 2016

Published
2016

54. STD2P: RGBD Semantic Segmentation Using Spatio-Temporal Data-Driven Pooling

Author

He, Yang, Chiu, Wei-Chen, Keuper, Margret, and Fritz, Mario

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

We propose a novel superpixel-based multi-view convolutional neural network for semantic image segmentation. The proposed network produces a high quality segmentation of a single image by leveraging information from additional views of the same scene. Particularly in indoor videos such as captured by robotic platforms or handheld and bodyworn RGBD cameras, nearby video frames provide diverse viewpoints and additional context of objects and scenes. To leverage such information, we first compute region correspondences by optical flow and image boundary-based superpixels. Given these region correspondences, we propose a novel spatio-temporal pooling layer to aggregate information over space and time. We evaluate our approach on the NYU--Depth--V2 and the SUN3D datasets and compare it to various state-of-the-art single-view and multi-view approaches. Besides a general improvement over the state-of-the-art, we also show the benefits of making use of unlabeled frames during training for multi-view as well as single-view prediction., Comment: To appear in CVPR 2017

Published
2016

57. See the Difference: Direct Pre-Image Reconstruction and Pose Estimation by Differentiating HOG

Author

Chiu, Wei-Chen and Fritz, Mario

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

The Histogram of Oriented Gradient (HOG) descriptor has led to many advances in computer vision over the last decade and is still part of many state of the art approaches. We realize that the associated feature computation is piecewise differentiable and therefore many pipelines which build on HOG can be made differentiable. This lends to advanced introspection as well as opportunities for end-to-end optimization. We present our implementation of $\nabla$HOG based on the auto-differentiation toolbox Chumpy and show applications to pre-image visualization and pose estimation which extends the existing differentiable renderer OpenDR pipeline. Both applications improve on the respective state-of-the-art HOG approaches.

Published
2015

61. Summarizing First-Person Videos from Third Persons’ Points of Views

Author

Ho, Hsuan-I, Chiu, Wei-Chen, Wang, Yu-Chiang Frank, Hutchison, David, Series Editor, Kanade, Takeo, Series Editor, Kittler, Josef, Series Editor, Kleinberg, Jon M., Series Editor, Mattern, Friedemann, Series Editor, Mitchell, John C., Series Editor, Naor, Moni, Series Editor, Pandu Rangan, C., Series Editor, Steffen, Bernhard, Series Editor, Terzopoulos, Demetri, Series Editor, Tygar, Doug, Series Editor, Weikum, Gerhard, Series Editor, Ferrari, Vittorio, editor, Hebert, Martial, editor, Sminchisescu, Cristian, editor, and Weiss, Yair, editor

Published
2018
Full Text
View/download PDF

67. Towards Segmenting Consumer Stereo Videos: Benchmark, Baselines and Ensembles

Author

Chiu, Wei-Chen, Galasso, Fabio, Fritz, Mario, Hutchison, David, Series editor, Kanade, Takeo, Series editor, Kittler, Josef, Series editor, Kleinberg, Jon M., Series editor, Mattern, Friedemann, Series editor, Mitchell, John C., Series editor, Naor, Moni, Series editor, Pandu Rangan, C., Series editor, Steffen, Bernhard, Series editor, Terzopoulos, Demetri, Series editor, Tygar, Doug, Series editor, Weikum, Gerhard, Series editor, Lai, Shang-Hong, editor, Lepetit, Vincent, editor, Nishino, Ko, editor, and Sato, Yoichi, editor

Published
2017
Full Text
View/download PDF

80. Attractive Factors of Environment-Friendly Daily Necessities

Author

Chiu, Wei-Chen and Ho, Chun-Heng

Subjects
Attractive Factors, Quantification Theory Type I, Miryoku Engineering, Evaluation Grid Method, Environment-Friendly Product
Abstract

Going green is increasingly important to the market. The present research indicates that functional and emotional factors can achieve the best-perceived effects when choosing an environment-friendly product. Therefore, this study aims to gather these attractive factors from high-involvement groups by using Miryoku engineering. First, we capture the factors through the Evaluation Grid Method and use Quantification Theory Type I for quantitative analysis. Then, generalize four feelings about environment-friendly products, namely “Assured,” “Responsible,” “Safe,” and “Comfortable.” We also define a linear dimension with short-, normal-, and far-sight for locating attractive factors and feelings. The result shows that high-involvement groups are more concerned about the long-term impacts of “Responsible” feelings, while low-involvement groups focus more on the obvious benefits of “Responsible” and “Safe” feelings. Moreover, the emphasis on natural ingredients is necessary for achieving “Assured” and “Comfortable” feelings for both the high- and low-involvement groups.

Published
2022

91. BiFuse++: Self-Supervised and Efficient Bi-Projection Fusion for 360° Depth Estimation

Author

Wang, Fu-En, Yeh, Yu-Hsuan, Tsai, Yi-Hsuan, Chiu, Wei-Chen, and Sun, Min

Abstract

Due to the rise of spherical cameras, monocular 360$^\circ$∘ depth estimation becomes an important technique for many applications (e.g., autonomous systems). Thus, state-of-the-art frameworks for monocular 360$^\circ$∘ depth estimation such as bi-projection fusion in BiFuse are proposed. To train such a framework, a large number of panoramas along with the corresponding depth ground truths captured by laser sensors are required, which highly increases the cost of data collection. Moreover, since such a data collection procedure is time-consuming, the scalability of extending these methods to different scenes becomes a challenge. To this end, self-training a network for monocular depth estimation from 360$^\circ$∘ videos is one way to alleviate this issue. However, there are no existing frameworks that incorporate bi-projection fusion into the self-training scheme, which highly limits the self-supervised performance since bi-projection fusion can leverage information from different projection types. In this paper, we propose BiFuse++ to explore the combination of bi-projection fusion and the self-training scenario. To be specific, we propose a new fusion module and Contrast-Aware Photometric Loss to improve the performance of BiFuse and increase the stability of self-training on real-world videos. We conduct both supervised and self-supervised experiments on benchmark datasets and achieve state-of-the-art performance.

Published
2023
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results