LIVIVO - Search results -

Search results

Result 1 - 10 of total 39

Search options

Article ; Online: Towards a Controllable and Reversible Privacy Protection System for Facial Images through Enhanced Multi-Factor Modifier Networks.

Pan, Yi-Lun / Chen, Jun-Cheng / Wu, Ja-Ling

2023 Volume 25, Issue 2

Abstract: Privacy protection data processing has been critical in recent years when pervasively equipped mobile devices could easily capture high-resolution personal images and videos that may disclose personal information. We propose a new controllable and ... ...

Abstract	Privacy protection data processing has been critical in recent years when pervasively equipped mobile devices could easily capture high-resolution personal images and videos that may disclose personal information. We propose a new controllable and reversible privacy protection system to address the concern in this work. The proposed scheme can automatically and stably anonymize and de-anonymize face images with one neural network and provide strong security protection with multi-factor identification solutions. Furthermore, users can include other attributes as identification factors, such as passwords and specific facial attributes. Our solution lies in a modified conditional-GAN-based training framework, the Multi-factor Modifier (MfM), to simultaneously accomplish the function of multi-factor facial anonymization and de-anonymization. It can successfully anonymize face images while generating realistic faces satisfying the conditions specified by the multi-factor features, such as gender, hair colors, and facial appearance. Furthermore, MfM can also de-anonymize de-identified faces to their corresponding original ones. One crucial part of our work is design of physically meaningful information-theory-based loss functions, which include mutual information between authentic and de-identification images and mutual information between original and re-identification images. Moreover, extensive experiments and analyses show that, with the correct multi-factor feature information, the MfM can effectively achieve nearly perfect reconstruction and generate high-fidelity and diverse anonymized faces to defend attacks from hackers better than other methods with compatible functionalities. Finally, we justify the advantages of this work through perceptual quality comparison experiments. Our experiments show that the resulting LPIPS (with a value of 0.35), FID (with a value of 28), and SSIM (with a value of 0.95) of MfM demonstrate significantly better de-identification effects than state-of-the-art works. Additionally, the MfM we designed can achieve re-identification, which improves real-world practicability.
Language	English
Publishing date	2023-02-01
Publishing country	Switzerland
Document type	Journal Article ; Review
ZDB-ID	2014734-X
ISSN	1099-4300 ; 1099-4300
ISSN (online)	1099-4300
ISSN	1099-4300
DOI	10.3390/e25020272
Database	MEDical Literature Analysis and Retrieval System OnLINE

Order via subito

This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

Article ; Online: Towards Adversarial Robustness for Multi-Mode Data through Metric Learning.

Khan, Sarwar / Chen, Jun-Cheng / Liao, Wen-Hung / Chen, Chu-Song

Sensors (Basel, Switzerland)

2023 Volume 23, Issue 13

Abstract: Adversarial attacks have become one of the most serious security issues in widely used deep neural networks. Even though real-world datasets usually have large intra-variations or multiple modes, most adversarial defense methods, such as adversarial ... ...

Abstract	Adversarial attacks have become one of the most serious security issues in widely used deep neural networks. Even though real-world datasets usually have large intra-variations or multiple modes, most adversarial defense methods, such as adversarial training, which is currently one of the most effective defense methods, mainly focus on the single-mode setting and thus fail to capture the full data representation to defend against adversarial attacks. To confront this challenge, we propose a novel multi-prototype metric learning regularization for adversarial training which can effectively enhance the defense capability of adversarial training by preventing the latent representation of the adversarial example changing a lot from its clean one. With extensive experiments on CIFAR10, CIFAR100, MNIST, and Tiny ImageNet, the evaluation results show the proposed method improves the performance of different state-of-the-art adversarial training methods without additional computational cost. Furthermore, besides Tiny ImageNet, in the multi-prototype CIFAR10 and CIFAR100 where we reorganize the whole datasets of CIFAR10 and CIFAR100 into two and ten classes, respectively, the proposed method outperforms the state-of-the-art approach by 2.22% and 1.65%, respectively. Furthermore, the proposed multi-prototype method also outperforms its single-prototype version and other commonly used deep metric learning approaches as regularization for adversarial training and thus further demonstrates its effectiveness.
MeSH term(s)	Learning ; Neural Networks, Computer
Language	English
Publishing date	2023-07-05
Publishing country	Switzerland
Document type	Journal Article
ZDB-ID	2052857-7
ISSN	1424-8220 ; 1424-8220
ISSN (online)	1424-8220
ISSN	1424-8220
DOI	10.3390/s23136173
Database	MEDical Literature Analysis and Retrieval System OnLINE

Order via subito

Book ; Online: BlenDA

Huang, Tzuhsuan / Huang, Chen-Che / Ku, Chung-Hao / Chen, Jun-Cheng

Domain Adaptive Object Detection through diffusion-based blending

2024

Abstract: Unsupervised domain adaptation (UDA) aims to transfer a model learned using labeled data from the source domain to unlabeled data in the target domain. To address the large domain gap issue between the source and target domains, we propose a novel ... ...

Abstract	Unsupervised domain adaptation (UDA) aims to transfer a model learned using labeled data from the source domain to unlabeled data in the target domain. To address the large domain gap issue between the source and target domains, we propose a novel regularization method for domain adaptive object detection, BlenDA, by generating the pseudo samples of the intermediate domains and their corresponding soft domain labels for adaptation training. The intermediate samples are generated by dynamically blending the source images with their corresponding translated images using an off-the-shelf pre-trained text-to-image diffusion model which takes the text label of the target domain as input and has demonstrated superior image-to-image translation quality. Based on experimental results from two adaptation benchmarks, our proposed approach can significantly enhance the performance of the state-of-the-art domain adaptive object detector, Adversarial Query Transformer (AQT). Particularly, in the Cityscapes to Foggy Cityscapes adaptation, we achieve an impressive 53.4% mAP on the Foggy Cityscapes dataset, surpassing the previous state-of-the-art by 1.5%. It is worth noting that our proposed method is also applicable to various paradigms of domain adaptive object detection. The code is available at:https://github.com/aiiu-lab/BlenDA Comment: ICASSP(2024):2024 IEEE International Conference on Acoustics, Speech and Signal Processing
Keywords	Computer Science - Computer Vision and Pattern Recognition
Subject code	004
Publishing date	2024-01-18
Publishing country	us
Document type	Book ; Online
Database	BASE - Bielefeld Academic Search Engine (life sciences selection)

Full text online

Full text

Inter-library loan at ZB MED

Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

Book ; Online: Video ControlNet

Chu, Ernie / Lin, Shuo-Yen / Chen, Jun-Cheng

Towards Temporally Consistent Synthetic-to-Real Video Translation Using Conditional Image Diffusion Models

2023

Abstract: In this study, we present an efficient and effective approach for achieving temporally consistent synthetic-to-real video translation in videos of varying lengths. Our method leverages off-the-shelf conditional image diffusion models, allowing us to ... ...

Abstract	In this study, we present an efficient and effective approach for achieving temporally consistent synthetic-to-real video translation in videos of varying lengths. Our method leverages off-the-shelf conditional image diffusion models, allowing us to perform multiple synthetic-to-real image generations in parallel. By utilizing the available optical flow information from the synthetic videos, our approach seamlessly enforces temporal consistency among corresponding pixels across frames. This is achieved through joint noise optimization, effectively minimizing spatial and temporal discrepancies. To the best of our knowledge, our proposed method is the first to accomplish diverse and temporally consistent synthetic-to-real video translation using conditional image diffusion models. Furthermore, our approach does not require any training or fine-tuning of the diffusion models. Extensive experiments conducted on various benchmarks for synthetic-to-real video translation demonstrate the effectiveness of our approach, both quantitatively and qualitatively. Finally, we show that our method outperforms other baseline methods in terms of both temporal consistency and visual quality.
Keywords	Computer Science - Computer Vision and Pattern Recognition
Subject code	006
Publishing date	2023-05-30
Publishing country	us
Document type	Book ; Online
Database	BASE - Bielefeld Academic Search Engine (life sciences selection)

Full text online

Full text

Inter-library loan at ZB MED

Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

Book ; Online: MeDM

Chu, Ernie / Huang, Tzuhsuan / Lin, Shuo-Yen / Chen, Jun-Cheng

Mediating Image Diffusion Models for Video-to-Video Translation with Temporal Correspondence Guidance

2023

Abstract: This study introduces an efficient and effective method, MeDM, that utilizes pre-trained image Diffusion Models for video-to-video translation with consistent temporal flow. The proposed framework can render videos from scene position information, such ... ...

Abstract	This study introduces an efficient and effective method, MeDM, that utilizes pre-trained image Diffusion Models for video-to-video translation with consistent temporal flow. The proposed framework can render videos from scene position information, such as a normal G-buffer, or perform text-guided editing on videos captured in real-world scenarios. We employ explicit optical flows to construct a practical coding that enforces physical constraints on generated frames and mediates independent frame-wise scores. By leveraging this coding, maintaining temporal consistency in the generated videos can be framed as an optimization problem with a closed-form solution. To ensure compatibility with Stable Diffusion, we also suggest a workaround for modifying observation-space scores in latent Diffusion Models. Notably, MeDM does not require fine-tuning or test-time optimization of the Diffusion Models. Through extensive qualitative, quantitative, and subjective experiments on various benchmarks, the study demonstrates the effectiveness and superiority of the proposed approach. Our project page can be found at https://medm2023.github.io Comment: Accepted as a conference paper in AAAI 2024. Project page: https://medm2023.github.io
Keywords	Computer Science - Computer Vision and Pattern Recognition
Subject code	004
Publishing date	2023-08-19
Publishing country	us
Document type	Book ; Online
Database	BASE - Bielefeld Academic Search Engine (life sciences selection)

Full text online

Full text

Inter-library loan at ZB MED

Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

Article ; Online: Pharmacokinetics of meloxicam in laying hens after single intravenous, oral, and intramuscular administration.

Shao, Hao-Tian / Yang, Fang / Chen, Jun-Cheng / Zhang, Mei / Song, Zhe-Wen / Yang, Fan

Journal of veterinary pharmacology and therapeutics

2022 Volume 45, Issue 5, Page(s) 488–494

Abstract: The objective of this study was to determine the pharmacokinetics of meloxicam after a single intravenous (IV), intramuscular (IM), and oral (PO) dose at 1 mg/kg body weight in Jing Hong laying hens. Blood samples were collected at predetermined time ... ...

Abstract	The objective of this study was to determine the pharmacokinetics of meloxicam after a single intravenous (IV), intramuscular (IM), and oral (PO) dose at 1 mg/kg body weight in Jing Hong laying hens. Blood samples were collected at predetermined time points. Plasma meloxicam concentrations were determined using a validated high-performance liquid chromatography (HPLC) assay method and then subjected to a non-compartmental analysis. After IV administration, meloxicam had a mean (±SD) volume of distribution at steady-state (Vd
MeSH term(s)	Administration, Intravenous/veterinary ; Administration, Oral ; Animals ; Anti-Inflammatory Agents, Non-Steroidal/pharmacokinetics ; Area Under Curve ; Biological Availability ; Chickens ; Female ; Half-Life ; Humans ; Injections, Intramuscular/veterinary ; Injections, Intravenous/veterinary ; Meloxicam
Chemical Substances	Anti-Inflammatory Agents, Non-Steroidal ; Meloxicam (VG2QF83CGL)
Language	English
Publishing date	2022-06-19
Publishing country	England
Document type	Journal Article
ZDB-ID	435216-6
ISSN	1365-2885 ; 0140-7783
ISSN (online)	1365-2885
ISSN	0140-7783
DOI	10.1111/jvp.13081
Database	MEDical Literature Analysis and Retrieval System OnLINE

Full text online

Accessible to users with ZB MED library card

In stock of ZB MED Cologne/Königswinter

Zs.A 2226: Show issues

Location:
Je nach Verfügbarkeit (siehe Angabe bei Bestand)
bis Jg. 1994: Bestellungen von Artikeln über das Online-Bestellformular
Jg. 1995 - 2021: Lesesall (1.OG)
ab Jg. 2022: Lesesaal (EG)

Order via subito

Details ▾

Article ; Online: DEFAEK: Domain Effective Fast Adaptive Network for Face Anti-Spoofing.

Lin, Jiun-Da / Han, Yue-Hua / Huang, Po-Han / Tan, Julianne / Chen, Jun-Cheng / Tanveer, M / Hua, Kai-Lung

Neural networks : the official journal of the International Neural Network Society

2023 Volume 161, Page(s) 83–91

Abstract: Existing deep learning based face anti-spoofing (FAS) or deepfake detection approaches usually rely on large-scale datasets and powerful networks with significant amount of parameters to achieve satisfactory performance. However, these make them resource- ...

Abstract	Existing deep learning based face anti-spoofing (FAS) or deepfake detection approaches usually rely on large-scale datasets and powerful networks with significant amount of parameters to achieve satisfactory performance. However, these make them resource-heavy and unsuitable for handheld devices. Moreover, they are limited by the types of spoof in the dataset they train on and require considerable training time. To produce a robust FAS model, they need large datasets covering the widest variety of predefined presentation attacks possible. Testing on new or unseen attacks or environments generally results in poor performance. Ideally, the FAS model should learn discriminative features that can generalize well even on unseen spoof types. In this paper, we propose a fast learning approach called Domain Effective Fast Adaptive nEt-worK (DEFAEK), a face anti-spoofing approach based on the optimization-based meta-learning paradigm that effectively and quickly adapts to new tasks. DEFAEK treats differences in an environment as domains and simulates multiple domain shifts during training. To further improve the effectiveness and efficiency of meta-learning, we adopt the metric learning in the inner loop update with careful sample selection. With extensive experiments on the challenging CelebA-Spoof and FaceForensics++ datasets, the evaluation results show that DEFAEK can learn cues independent of the environment with good generalization capability. In addition, the resulting model is lightweight following the design principle of modern lightweight network architecture and still generalizes well on unseen classes. In addition, we also demonstrate our model's capabilities by comparing the numbers of parameters, FLOPS, and model performance with other state-of-the-art methods.
MeSH term(s)	Cues ; Generalization, Psychological
Language	English
Publishing date	2023-01-25
Publishing country	United States
Document type	Journal Article
ZDB-ID	740542-x
ISSN	1879-2782 ; 0893-6080
ISSN (online)	1879-2782
ISSN	0893-6080
DOI	10.1016/j.neunet.2023.01.018
Database	MEDical Literature Analysis and Retrieval System OnLINE

In stock of ZB MED Cologne/Königswinter

Zs.A 2365: Show issues

Location:
Je nach Verfügbarkeit (siehe Angabe bei Bestand)
bis Jg. 1994: Bestellungen von Artikeln über das Online-Bestellformular
Jg. 1995 - 2021: Lesesall (2.OG)
ab Jg. 2022: Lesesaal (EG)

Order via subito

Details ▾
- See ZB MED holdings
- Order with fees

Article: Pharmacokinetics of Danofloxacin in Gushi Chickens after Single Oral and Intravenous Administration.

Chen, Jun-Cheng / Yang, Fang / Li, Guang-Hui / Duan, Ming-Hui / Li, Ze-En / Dai, Yan / Zhang, Mei / Yang, Fan

Metabolites

2023 Volume 13, Issue 8

Abstract: This study aimed to determine the pharmacokinetics of danofloxacin in Gushi chickens after a single oral (PO) and intravenous (IV) dose at 5 mg/kg body weight (BW). Thirty-two Gushi chickens, aged 20 weeks, were selected and divided into two groups at ... ...

Abstract	This study aimed to determine the pharmacokinetics of danofloxacin in Gushi chickens after a single oral (PO) and intravenous (IV) dose at 5 mg/kg body weight (BW). Thirty-two Gushi chickens, aged 20 weeks, were selected and divided into two groups at random, with each group consisting of 16 chickens, evenly distributed between males and females. Following danofloxacin administration, blood samples were taken at predetermined time intervals and the plasma was separated. The concentrations of danofloxacin in plasma were quantified by HPLC with a fluorescence detector. Then the concentrations versus time data were subjected to non-compartmental analysis (NCA) using Phoenix software (version: 8.1.0). After administering danofloxacin orally at a dose of 5 mg/kg BW to Gushi chickens, our results demonstrated that the peak concentration reached 0.53 μg/mL at 4 h. The half-life of absorption (t
Language	English
Publishing date	2023-08-02
Publishing country	Switzerland
Document type	Journal Article
ZDB-ID	2662251-8
ISSN	2218-1989
ISSN	2218-1989
DOI	10.3390/metabo13080906
Database	MEDical Literature Analysis and Retrieval System OnLINE

Order via subito

Article ; Online: Pharmacokinetics of meloxicam in pigeons after single intravenous, oral, and intramuscular administration.

Chen, Jun-Cheng / Yang, Fang / Duan, Ming-Hui / Li, Ze-En / Dai, Yan / Zhang, Mei / Yang, Fan

Poultry science

2023 Volume 102, Issue 9, Page(s) 102869

Abstract: This study aimed to determine the pharmacokinetics of meloxicam in pigeons. Twenty-four 7-wk-old meat pigeons (Columba livia) were randomly divided into 3 groups (PO, IM, and IV) and given a single dose of 1 mg/kg body weight of meloxicam. Plasma samples ...

Abstract	This study aimed to determine the pharmacokinetics of meloxicam in pigeons. Twenty-four 7-wk-old meat pigeons (Columba livia) were randomly divided into 3 groups (PO, IM, and IV) and given a single dose of 1 mg/kg body weight of meloxicam. Plasma samples were taken at predetermined times, which were then analyzed using a validated high-performance liquid chromatography (HPLC) method and subjected to noncompartmental analysis using Phoenix software. Results indicated that meloxicam was absorbed effectively and quickly after PO and IM dosing. Peak concentrations (0.83 ± 0.21 and 1.59 ± 0.49 μg/mL) were achieved at 2 and 0.26 h, respectively, with mean absorption times of 2.56 ± 1.50 and 1.47 ± 0.89 h. Bioavailability was high at 86.31 ± 43.45% and 81.57 ± 52.58%, respectively, and the area under the concentration-time curve (AUC
MeSH term(s)	Animals ; Meloxicam ; Columbidae ; Anti-Inflammatory Agents, Non-Steroidal ; Thiazines/pharmacokinetics ; Thiazoles/pharmacokinetics ; Area Under Curve ; Half-Life ; Chickens ; Administration, Oral ; Injections, Intravenous/veterinary ; Injections, Intramuscular/veterinary
Chemical Substances	Meloxicam (VG2QF83CGL) ; Anti-Inflammatory Agents, Non-Steroidal ; Thiazines ; Thiazoles
Language	English
Publishing date	2023-06-14
Publishing country	England
Document type	Randomized Controlled Trial, Veterinary ; Journal Article
ZDB-ID	242586-5
ISSN	1525-3171 ; 0032-5791
ISSN (online)	1525-3171
ISSN	0032-5791
DOI	10.1016/j.psj.2023.102869
Database	MEDical Literature Analysis and Retrieval System OnLINE

In stock of ZB MED Cologne/Königswinter

Zs.B 853: Show issues

Location:
Je nach Verfügbarkeit (siehe Angabe bei Bestand)
bis Jg. 2021: Bestellungen von Artikeln über das Online-Bestellformular
ab Jg. 2022: Lesesaal (EG)

Order via subito

Details ▾
- See ZB MED holdings
- Order with fees

Article ; Online: Depletion of tilmicosin residue in Gushi chickens following oral administration via drinking water.

Zhang, Mei / Qian, Kun / Li, Guang-Hui / Duan, Ming-Hui / Li, Ze-En / Dai, Yan / Chen, Jun-Cheng / Yang, Fan

Journal of veterinary pharmacology and therapeutics

2023 Volume 47, Issue 2, Page(s) 114–120

Abstract: This study aimed to examine the depletion of tilmicosin residues in Gushi chickens following the administration at a concentration of 75 mg/L in their drinking water for three consecutive days. Plasma, liver, kidney, lung, muscle, and skin + fat samples ... ...

Abstract	This study aimed to examine the depletion of tilmicosin residues in Gushi chickens following the administration at a concentration of 75 mg/L in their drinking water for three consecutive days. Plasma, liver, kidney, lung, muscle, and skin + fat samples were collected from 6 chickens at 6 h, 1, 3, 5, and 7 days after the treatment. Tilmicosin concentrations in the samples were determined using a high-performance liquid chromatography (HPLC) method. The findings revealed that the highest tilmicosin residues were detected in the liver, followed by the kidney, lung, skin + fat, muscle, and plasma. Notably, at 7 days post-treatment, no drug residue was detected in all samples except for the liver and kidney. The non-compartmental model was employed to calculate relevant pharmacokinetic parameters. The elimination half-lives (t
MeSH term(s)	Animals ; Anti-Bacterial Agents ; Drinking Water ; Chickens ; Administration, Oral ; Tylosin/analogs & derivatives
Chemical Substances	tilmicosin (XL4103X2E3) ; Anti-Bacterial Agents ; Drinking Water ; Tylosin (YEF4JXN031)
Language	English
Publishing date	2023-11-10
Publishing country	England
Document type	Journal Article
ZDB-ID	435216-6
ISSN	1365-2885 ; 0140-7783
ISSN (online)	1365-2885
ISSN	0140-7783
DOI	10.1111/jvp.13416
Database	MEDical Literature Analysis and Retrieval System OnLINE

In stock of ZB MED Cologne/Königswinter

Zs.A 2226: Show issues

Location:
Je nach Verfügbarkeit (siehe Angabe bei Bestand)
bis Jg. 1994: Bestellungen von Artikeln über das Online-Bestellformular
Jg. 1995 - 2021: Lesesall (1.OG)
ab Jg. 2022: Lesesaal (EG)

Order via subito

Details ▾
- See ZB MED holdings
- Order with fees

To top

More links

Kategorien

Order via subito

More links

Kategorien

Order via subito

Full text online

More links

Kategorien

Inter-library loan at ZB MED

Full text online

More links

Kategorien

Inter-library loan at ZB MED

Full text online

More links

Kategorien

Inter-library loan at ZB MED

Full text online

More links

Kategorien

In stock of ZB MED Cologne/Königswinter

Order via subito

More links

Kategorien

In stock of ZB MED Cologne/Königswinter

Order via subito

More links

Kategorien

Order via subito

More links

Kategorien

In stock of ZB MED Cologne/Königswinter

Order via subito

More links

Kategorien

In stock of ZB MED Cologne/Königswinter

Order via subito