373 citations · 455 across the 17 of their papers we have counts for
15 papers · 1 filter
Meta Transferring for Deblurring
Po-Sheng Liu, Fu-Jen Tsai, Yan-Tsung Peng +3
Most previous deblurring methods were built with a generic model trained on blurred images and their sharp counterparts. However, these approaches might have sub-optimal deblurring…
Stripformer: Strip Transformer for Fast Image Deblurring
Fu-Jen Tsai, Yan-Tsung Peng, Yen-Yu Lin +2
Images taken in dynamic scenes may contain unwanted motion blur, which significantly degrades visual quality. Such blur causes short- and long-range region-specific smoothing artif…
DGGAN: Depth-image Guided Generative Adversarial Networks for Disentangling RGB and Depth Images in 3D Hand Pose Estimation
Liangjian Chen, Shih-Yao Lin, Yusheng Xie +3
Estimating3D hand poses from RGB images is essentialto a wide range of potential applications, but is challengingowing to substantial ambiguity in the inference of depth in-formati…
Regularizing Meta-Learning via Gradient Dropout
Hung-Yu Tseng, Yi-Wen Chen, Yi-Hsuan Tsai +3
With the growing attention on learning-to-learn new tasks using only a few examples, meta-learning has been widely used in numerous problems such as few-shot classification, reinfo…
Deep Semantic Matching with Foreground Detection and Cycle-Consistency
Yun-Chun Chen, Po-Hsiang Huang, Li-Yu Yu +3
Establishing dense semantic correspondences between object instances remains a challenging problem due to background clutter, significant scale and pose differences, and large intr…
Cross-Resolution Adversarial Dual Network for Person Re-Identification and Beyond
Yu-Jhe Li, Yun-Chun Chen, Yen-Yu Lin +1
Person re-identification (re-ID) aims at matching images of the same person across camera views. Due to varying distances between cameras and persons of interest, resolution mismat…
CrDoCo: Pixel-level Domain Transfer with Cross-Domain Consistency
Yun-Chun Chen, Yen-Yu Lin, Ming-Hsuan Yang +1
Unsupervised domain adaptation algorithms aim to transfer the knowledge learned from one domain to another (e.g., synthetic to real images). The adapted representations often do no…
Referring Expression Object Segmentation with Caption-Aware Consistency
Yi-Wen Chen, Yi-Hsuan Tsai, Tiantian Wang +2
Referring expressions are natural language descriptions that identify a particular object within a scene and are widely used in our daily conversations. In this work, we focus on s…
Recover and Identify: A Generative Dual Model for Cross-Resolution Person Re-Identification
Yu-Jhe Li, Yun-Chun Chen, Yen-Yu Lin +2
Person re-identification (re-ID) aims at matching images of the same identity across camera views. Due to varying distances between cameras and persons of interest, resolution mism…
Show, Match and Segment: Joint Weakly Supervised Learning of Semantic Matching and Object Co-segmentation
Yun-Chun Chen, Yen-Yu Lin, Ming-Hsuan Yang +1
We present an approach for jointly matching and segmenting object instances of the same category within a collection of images. In contrast to existing algorithms that tackle the t…
Unseen Object Segmentation in Videos via Transferable Representations
Yi-Wen Chen, Yi-Hsuan Tsai, Chu-Ya Yang +2
In order to learn object segmentation models in videos, conventional methods require a large amount of pixel-wise ground truth annotations. However, collecting such supervised data…
Learning Conditional Random Fields with Augmented Observations for Partially Observed Action Recognition
Shih-Yao Lin, Yen-Yu Lin, Chu-Song Chen +1
This paper aims at recognizing partially observed human actions in videos. Action videos acquired in uncontrolled environments often contain corrupt frames, which make actions part…
Generating Realistic Training Images Based on Tonality-Alignment Generative Adversarial Networks for Hand Pose Estimation
Liangjian Chen, Shih-Yao Lin, Yusheng Xie +5
Hand pose estimation from a monocular RGB image is an important but challenging task. The main factor affecting its performance is the lack of a sufficiently large training dataset…
Adversarial Learning for Semi-Supervised Semantic Segmentation
Wei-Chih Hung, Yi-Hsuan Tsai, Yan-Ting Liou +2
We propose a method for semi-supervised semantic segmentation using an adversarial network. While most existing discriminators are trained to classify input images as real or fake…
Descriptor Ensemble: An Unsupervised Approach to Descriptor Fusion in the Homography Space
Yuan-Ting Hu, Yen-Yu Lin, Hsin-Yi Chen +2
With the aim to improve the performance of feature matching, we present an unsupervised approach to fuse various local descriptors in the space of homographies. Inspired by the obs…