no code implementations • 26 Nov 2022 • Wan-Cyuan Fan, Cheng-Fu Yang, Chiao-An Yang, Yu-Chiang Frank Wang
We tackle the problem of target-free text-guided image manipulation, which requires one to modify the input reference image based on the given text instruction, while no ground truth target image is observed during training.
no code implementations • 25 Sep 2022 • Cheng-Fu Yang, Yao-Hung Hubert Tsai, Wan-Cyuan Fan, Ruslan Salakhutdinov, Louis-Philippe Morency, Yu-Chiang Frank Wang
Since no ground truth captions are available for novel object images during training, our P2C leverages cross-modality (image-text) association modules to ensure the above caption characteristics can be properly preserved.
1 code implementation • 30 Aug 2022 • Cheng-Yen Hsieh, Chih-Jung Chang, Fu-En Yang, Yu-Chiang Frank Wang
In particular, we present a cross-scale patch-level correlation learning in SS-PRL, which allows the model to aggregate and associate information learned across patch scales.
1 code implementation • 29 Aug 2022 • Wan-Cyuan Fan, Yen-Chun Chen, Dongdong Chen, Yu Cheng, Lu Yuan, Yu-Chiang Frank Wang
Diffusion models (DMs) have shown great potential for high-quality image synthesis.
no code implementations • 16 Aug 2022 • Zih-Ching Chen, Lin-Hsi Tsao, Chin-Lun Fu, Shang-Fu Chen, Yu-Chiang Frank Wang
Face anti-spoofing (FAS) aims at distinguishing face spoof attacks from the authentic ones, which is typically approached by learning proper models for performing the associated classification task.
no code implementations • CVPR 2022 • Chiao-An Yang, Cheng-Yo Tan, Wan-Cyuan Fan, Cheng-Fu Yang, Meng-Lin Wu, Yu-Chiang Frank Wang
In particular, we propose a novel network of Scene Graph Transformer (SGT), which is designed to take node and edge features as inputs for modeling the associated structural information.
1 code implementation • CVPR 2022 • Zhi-Hao Lin, Wei-Chiu Ma, Hao-Yu Hsu, Yu-Chiang Frank Wang, Shenlong Wang
We present Neural Mixtures of Planar Experts (NeurMiPs), a novel planar-based scene representation for modeling geometry and appearance.
no code implementations • 23 Mar 2022 • Shang-Fu Chen, Yu-Min Liu, Chia-Ching Lin, Trista Pei-Chun Chen, Yu-Chiang Frank Wang
By observing normal and abnormal surface data across multiple source domains, our model is expected to be generalized to an unseen textured surface of interest, in which only a small number of normal data can be observed during testing.
no code implementations • 27 Dec 2021 • Yuan-Chia Cheng, Ci-Siang Lin, Fu-En Yang, Yu-Chiang Frank Wang
Few-shot classification aims to carry out classification given only few labeled examples for the categories of interest.
no code implementations • 27 Dec 2021 • Zu-Yun Shiau, Wei-Wei Lin, Ci-Siang Lin, Yu-Chiang Frank Wang
How to handle domain shifts when recognizing or segmenting visual data across domains has been studied by learning and vision communities.
no code implementations • NeurIPS 2021 • Fu-En Yang, Yuan-Chia Cheng, Zu-Yun Shiau, Yu-Chiang Frank Wang
Domain generalization (DG) aims to transfer the learning task from a single or multiple source domains to unseen target domains.
no code implementations • 2 Nov 2021 • Yuan-Hao Lee, Fu-En Yang, Yu-Chiang Frank Wang
Few-shot semantic segmentation addresses the learning task in which only few images with ground truth pixel-level labels are available for the novel classes of interest.
no code implementations • 29 Sep 2021 • Cheng-Fu Yang, Yao-Hung Hubert Tsai, Wan-Cyuan Fan, Yu-Chiang Frank Wang, Louis-Philippe Morency, Ruslan Salakhutdinov
Novel object captioning (NOC) learns image captioning models for describing objects or visual concepts which are unseen (i. e., novel) in the training captions.
1 code implementation • CVPR 2021 • Cheng-Fu Yang, Wan-Cyuan Fan, Fu-En Yang, Yu-Chiang Frank Wang
To better exploit the text input, so that implicit objects or relationships can be properly inferred during layout generation, we propose a LayoutTransformer Network (LT-Net) in this paper.
no code implementations • 3 May 2021 • Yan-Bo Lin, Yu-Chiang Frank Wang
Human perceives rich auditory experience with distinct sound heard by ears.
no code implementations • 26 Feb 2021 • Fu-En Yang, Jing-Cheng Chang, Yuan-Hao Lee, Yu-Chiang Frank Wang
Generating videos with content and motion variations is a challenging task in computer vision.
no code implementations • 1 Jan 2021 • Cheng-Fu Yang, Wan-Cyuan Fan, Fu-En Yang, Yu-Chiang Frank Wang
In the areas of machine learning and computer vision, text-to-image synthesis aims at producing image outputs given the input text.
no code implementations • 2 Nov 2020 • Shang-Fu Chen, Jia-Wei Yan, Ya-Fan Su, Yu-Chiang Frank Wang
Representation disentanglement aims at learning interpretable features, so that the output can be recovered or manipulated accordingly.
no code implementations • 21 Oct 2020 • Jia-Wei Yan, Ci-Siang Lin, Fu-En Yang, Yu-Jhe Li, Yu-Chiang Frank Wang
Learning interpretable and interpolatable latent representations has been an emerging research direction, allowing researchers to understand and utilize the derived latent space for further applications such as visual synthesis or recognition.
no code implementations • 19 Oct 2020 • Ci-Siang Lin, Yuan-Chia Cheng, Yu-Chiang Frank Wang
That is, while a number of labeled source-domain datasets are available, we do not have access to any target-domain training data.
Domain Generalization
Generalizable Person Re-identification
+1
no code implementations • 2 Oct 2020 • Chih-Ting Liu, Yu-Jhe Li, Shao-Yi Chien, Yu-Chiang Frank Wang
As a result, our approach is able to augment the labeled training data in the semi-supervised setting.
no code implementations • ECCV 2020 • Yun-Chun Chen, Chao-Te Chou, Yu-Chiang Frank Wang
To address semi-supervised learning from both labeled and unlabeled data, we present a novel meta-learning scheme.
no code implementations • 17 Jul 2020 • Hao-Hsiang Yang, Chao-Han Huck Yang, Yu-Chiang Frank Wang
Wavelet transform and the inverse wavelet transform are substituted for down-sampling and up-sampling so feature maps from the wavelet transform and convolutions contain different frequencies and scales.
no code implementations • 2 Jun 2020 • Yen-Ting Liu, Yu-Jhe Li, Yu-Chiang Frank Wang
Video summarization is among challenging tasks in computer vision, which aims at identifying highlight frames or shots over a lengthy video input.
no code implementations • 19 Feb 2020 • Yu-Jhe Li, Yun-Chun Chen, Yen-Yu Lin, Yu-Chiang Frank Wang
Person re-identification (re-ID) aims at matching images of the same person across camera views.
no code implementations • ICCV 2019 • Yu-Jhe Li, Ci-Siang Lin, Yan-Bo Lin, Yu-Chiang Frank Wang
Person re-identification (re-ID) aims at recognizing the same person from images taken across different cameras.
Ranked #15 on
Unsupervised Domain Adaptation
on Market to Duke
no code implementations • ICCV 2019 • Yu-Jhe Li, Yun-Chun Chen, Yen-Yu Lin, Xiaofei Du, Yu-Chiang Frank Wang
Person re-identification (re-ID) aims at matching images of the same identity across camera views.
1 code implementation • 5 Aug 2019 • Chih-Ting Liu, Chih-Wei Wu, Yu-Chiang Frank Wang, Shao-Yi Chien
Video-based person re-identification (Re-ID) aims at matching video sequences of pedestrians across non-overlapping cameras.
Ranked #11 on
Person Re-Identification
on MARS
no code implementations • 25 Jul 2019 • Yun-Chun Chen, Yu-Jhe Li, Xiaofei Du, Yu-Chiang Frank Wang
Moreover, the extension of our model for semi-supervised re-ID further confirms the scalability of our proposed method for real-world scenarios and applications.
10 code implementations • ICLR 2019 • Wei-Yu Chen, Yen-Cheng Liu, Zsolt Kira, Yu-Chiang Frank Wang, Jia-Bin Huang
Few-shot classification aims to learn a classifier to recognize unseen classes during training with limited labeled examples.
2 code implementations • 20 Feb 2019 • Yan-Bo Lin, Yu-Jhe Li, Yu-Chiang Frank Wang
Audio-visual event localization requires one to identify theevent which is both visible and audible in a video (eitherat a frame or video level).
no code implementations • 29 Nov 2018 • Yi-Lun Liao, Yao-Cheng Yang, Yu-Chiang Frank Wang
Aiming at inferring 3D shapes from 2D images, 3D shape reconstruction has drawn huge attention from researchers in computer vision and deep learning communities.
3D Reconstruction
3D Shape Reconstruction From A Single 2D Image
1 code implementation • NeurIPS 2018 • Alexander H. Liu, Yen-Cheng Liu, Yu-Ying Yeh, Yu-Chiang Frank Wang
We present a novel and unified deep learning framework which is capable of learning domain-invariant representation from data across multiple domains.
no code implementations • ECCV 2018 • Hsuan-I Ho, Wei-Chen Chiu, Yu-Chiang Frank Wang
Video highlight or summarization is among interesting topics in computer vision, which benefits a variety of applications like viewing, searching, or storage.
no code implementations • ECCV 2018 • Hong-Min Chu, Chih-Kuan Yeh, Yu-Chiang Frank Wang
In order to train learning models for multi-label classification (MLC), it is typically desirable to have a large amount of fully annotated multi-label data.
4 code implementations • 5 May 2018 • Yu-Jhe Li, Hsin-Yu Chang, Yu-Jing Lin, Po-Wei Wu, Yu-Chiang Frank Wang
Deep reinforcement learning has shown its success in game playing.
no code implementations • 25 Apr 2018 • Yu-Jhe Li, Fu-En Yang, Yen-Cheng Liu, Yu-Ying Yeh, Xiaofei Du, Yu-Chiang Frank Wang
Person re-identification (Re-ID) aims at recognizing the same person from images taken across different cameras.
Ranked #18 on
Unsupervised Domain Adaptation
on Duke to Market
no code implementations • ECCV 2018 • Hsuan-I Ho, Wei-Chen Chiu, Yu-Chiang Frank Wang
Video highlight or summarization is among interesting topics in computer vision, which benefits a variety of applications like viewing, searching, or storage.
1 code implementation • CVPR 2018 • Chung-Wei Lee, Wei Fang, Chih-Kuan Yeh, Yu-Chiang Frank Wang
In this paper, we propose a novel deep learning architecture for multi-label zero-shot learning (ML-ZSL), which is able to predict multiple unseen class labels for each input instance.
1 code implementation • 18 Jul 2017 • Shang-Fu Chen, Yi-Chen Chen, Chih-Kuan Yeh, Yu-Chiang Frank Wang
In this paper, we propose the joint learning attention and recurrent neural network (RNN) models for multi-label classification.
1 code implementation • 3 Jul 2017 • Chih-Kuan Yeh, Wei-Chieh Wu, Wei-Jen Ko, Yu-Chiang Frank Wang
Multi-label classification is a practical yet challenging task in machine learning related fields, since it requires the prediction of more than one label category for each input instance.
no code implementations • 7 Jun 2017 • Chih-Kuan Yeh, Yao-Hung Hubert Tsai, Yu-Chiang Frank Wang
In other words, our GDVM casts the supervised learning task as a generative learning process, with data discrimination to be jointly exploited for improved classification.
no code implementations • CVPR 2018 • Yen-Cheng Liu, Yu-Ying Yeh, Tzu-Chien Fu, Sheng-De Wang, Wei-Chen Chiu, Yu-Chiang Frank Wang
While representation learning aims to derive interpretable features for describing visual data, representation disentanglement further results in such features so that particular image attributes can be identified and manipulated.
9 code implementations • ICCV 2017 • Yi-Hsin Chen, Wei-Yu Chen, Yu-Ting Chen, Bo-Cheng Tsai, Yu-Chiang Frank Wang, Min Sun
Despite the recent success of deep-learning based semantic segmentation, deploying a pre-trained road scene segmenter to a city whose images are not presented in the training set would not achieve satisfactory performance due to dataset biases.
no code implementations • CVPR 2016 • Yao-Hung Hubert Tsai, Yi-Ren Yeh, Yu-Chiang Frank Wang
With the goal of deriving a domain-invariant feature subspace for HDA, our CDLS is able to identify representative cross-domain data, including the unlabeled ones in the target domain, for performing adaptation.
no code implementations • ICCV 2015 • Tzu Ming Harry Hsu, Wei Yu Chen, Cheng-An Hou, Yao-Hung Hubert Tsai, Yi-Ren Yeh, Yu-Chiang Frank Wang
For standard unsupervised domain adaptation, one typically obtains labeled data in the source domain and only observes unlabeled data in the target domain.
no code implementations • CVPR 2015 • Jen-Hao Rick Chang, Yu-Chiang Frank Wang
In this paper, we propose the propagation filter as a novel image filtering operator, with the goal of smoothing over neighboring image pixels while preserving image context like edges or textural regions.