Export Citations
Publications
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- research-article
r-FACE: Reference guided face component editing
AbstractAlthough recent studies have made significant processes in face portrait editing, simple and accurate face component editing remains a challenge. Face components, such as eyes, nose, and mouth, have a shape style that is difficult to transfer. ...
Highlights- A novel framework for diverse and controllable face component editing.
- An example-guided attention module for improving semantic transfer ability.
- A domain verification discriminator for improving the quality of generated images.
- research-article
Understanding Deep Face Representation via Attribute Recovery
IEEE Transactions on Information Forensics and Security, Volume 19•2024, pp 6949-6961 • https://doi.org/10.1109/TIFS.2024.3424291Deep neural networks have proven to be highly effective in the face recognition task, as they can map raw samples into a discriminative high-dimensional representation space. However, understanding this complex space proves to be challenging for human ...
- research-article
Multi-Faceted Knowledge-Driven Graph Neural Network for Iris Segmentation
IEEE Transactions on Information Forensics and Security, Volume 19•2024, pp 6015-6027 • https://doi.org/10.1109/TIFS.2024.3407508Accurate iris segmentation, especially around the iris inner and outer boundaries, is still a formidable challenge. Pixels within these areas are difficult to semantically distinguish since they have similar visual characteristics and close spatial ...
- research-article
Open-Set Single-Domain Generalization for Robust Face Anti-Spoofing
International Journal of Computer Vision, Volume 132, Issue 11•Nov 2024, pp 5151-5172 • https://doi.org/10.1007/s11263-024-02129-0AbstractFace anti-spoofing is a critical component of face recognition technology. However, it suffers from poor generalizability for cross-scenario target domains due to the simultaneous presence of unseen domains and unknown attack types. In this paper, ...
- research-article
Improving Transferability of Adversarial Samples via Critical Region-Oriented Feature-Level Attack
IEEE Transactions on Information Forensics and Security, Volume 19•2024, pp 6650-6664 • https://doi.org/10.1109/TIFS.2024.3404857Deep neural networks (DNNs) have received a lot of attention because of their impressive progress in computer vision. However, it has been recently shown that DNNs are vulnerable to being spoofed by carefully crafted adversarial samples. These samples are ...
- research-article
Open-Vocabulary Text-Driven Human Image Generation
International Journal of Computer Vision, Volume 132, Issue 10•Oct 2024, pp 4379-4397 • https://doi.org/10.1007/s11263-024-02079-7AbstractGenerating human images from open-vocabulary text descriptions is an exciting but challenging task. Previous methods (i.e., Text2Human) face two challenging problems: (1) they cannot well handle the open-vocabulary setting by arbitrary text inputs ...
- research-article
Sensing Micro-Motion Human Patterns using Multimodal mmRadar and Video Signal for Affective and Psychological Intelligence
MM '23: Proceedings of the 31st ACM International Conference on Multimedia•October 2023, pp 5935-5946• https://doi.org/10.1145/3581783.3611754Affective and psychological perception are pivotal in human-machine interaction and essential domains within artificial intelligence. Existing physiological signal-based affective and psychological datasets primarily rely on contact-based sensors, ...
- survey
Deep Learning Based Occluded Person Re-Identification: A Survey
ACM Transactions on Multimedia Computing, Communications, and Applications, Volume 20, Issue 3•March 2024, Article No.: 73, pp 1-27 • https://doi.org/10.1145/3610534Occluded person re-identification (Re-ID) focuses on addressing the occlusion problem when retrieving the person of interest across non-overlapping cameras. With the increasing demand for intelligent video surveillance and the application of person Re-ID ...
- research-article
PyMAF-X: Towards Well-Aligned Full-Body Model Regression From Monocular Images
IEEE Transactions on Pattern Analysis and Machine Intelligence, Volume 45, Issue 10•Oct. 2023, pp 12287-12303 • https://doi.org/10.1109/TPAMI.2023.3271691We present PyMAF-X, a regression-based approach to recovering a parametric full-body model from a single image. This task is very challenging since minor parametric deviation may lead to noticeable misalignment between the estimated mesh and the input ...
- research-article
Personalized Graph Generation for Monocular 3D Human Pose and Shape Estimation
IEEE Transactions on Circuits and Systems for Video Technology, Volume 34, Issue 4•April 2024, pp 2399-2413 • https://doi.org/10.1109/TCSVT.2023.33105253D human pose and shape estimation from a single RGB image is an appealing yet challenging task. Due to the graph-like nature of human parametric models, a growing number of graph neural network-based approaches have been proposed and achieved promising ...
- research-article
AIF-LFNet: All-in-Focus Light Field Super-Resolution Method Considering the Depth-Varying Defocus
IEEE Transactions on Circuits and Systems for Video Technology, Volume 33, Issue 8•Aug. 2023, pp 3976-3988 • https://doi.org/10.1109/TCSVT.2023.3237593As an aperture-divided computational imaging system, microlens array (MLA) -based light field (LF) imaging is playing an increasingly important role in computer vision. As the trade-off between the spatial and angular resolutions, deep learning (DL) -...
- research-article
GAN-Based Facial Attribute Manipulation
IEEE Transactions on Pattern Analysis and Machine Intelligence, Volume 45, Issue 12•Dec. 2023, pp 14590-14610 • https://doi.org/10.1109/TPAMI.2023.3298868Facial Attribute Manipulation (FAM) aims to aesthetically modify a given face image to render desired attributes, which has received significant attention due to its broad practical applications ranging from digital entertainment to biometric forensics. ...
- research-article
Multiscale Dynamic Graph Representation for Biometric Recognition With Occlusions
IEEE Transactions on Pattern Analysis and Machine Intelligence, Volume 45, Issue 12•Dec. 2023, pp 15120-15136 • https://doi.org/10.1109/TPAMI.2023.3298836Occlusion is a common problem with biometric recognition in the wild. The generalization ability of CNNs greatly decreases due to the adverse effects of various occlusions. To this end, we propose a novel unified framework integrating the merits of both ...
- research-article
Color-Unrelated Head-Shoulder Networks for Fine-Grained Person Re-identification
ACM Transactions on Multimedia Computing, Communications, and Applications, Volume 19, Issue 6•November 2023, Article No.: 210, pp 1-21 • https://doi.org/10.1145/3599730Person re-identification (re-id) attempts to match pedestrian images with the same identity across non-overlapping cameras. Existing methods usually study person re-id by learning discriminative features based on the clothing attributes (e.g., color, ...
- research-article
Dilated Convolution-based Feature Refinement Network for Crowd Localization
ACM Transactions on Multimedia Computing, Communications, and Applications, Volume 19, Issue 6•November 2023, Article No.: 217, pp 1-16 • https://doi.org/10.1145/3571134As an emerging computer vision task, crowd localization has received increasing attention due to its ability to produce more accurate spatially predictions. However, continuous scale variations in complex crowd scenes lead to tiny individuals at the edges,...
- research-article
Semantic-based conditional generative adversarial hashing with pairwise labels
Highlights- A general two-stage cGANs framework is proposed to learn hash codes based on the pairwise label information.
- In the first stage, the conditional information is generated via a general Bayesian framework, which has several advantages ...
AbstractHashing has been widely exploited in recent years due to the rapid growth of image and video data on the web. Benefiting from recent advances in deep learning, deep hashing methods have achieved promising results with supervised information. ...
- research-article
Contextualized Relation Predictive Model for Self-Supervised Group Activity Representation Learning
IEEE Transactions on Multimedia, Volume 26•2024, pp 353-366 • https://doi.org/10.1109/TMM.2023.3265280Group activity analysis has attracted remarkable attention recently due to the widespread applications in security, entertainment and military. This article targets at learning group activity representations with self-supervision, which differs from the ...
- research-article
A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications
IEEE Transactions on Knowledge and Data Engineering, Volume 35, Issue 4•April 2023, pp 3313-3332 • https://doi.org/10.1109/TKDE.2021.3130191Generative adversarial networks (GANs) have recently become a hot research topic; however, they have been studied since 2014, and a large number of algorithms have been proposed. Nevertheless, few comprehensive studies explain the connections among ...
- research-article
Towards Spatially Disentangled Manipulation of Face Images With Pre-Trained StyleGANs
IEEE Transactions on Circuits and Systems for Video Technology, Volume 33, Issue 4•April 2023, pp 1725-1739 • https://doi.org/10.1109/TCSVT.2022.3213662Generative Adversarial Networks with style-based generators could successfully synthesize realistic images from input latent code. Moreover, recent studies have revealed that interpretable translations of generated images could be obtained by linearly ...
- research-article
Adversarial Learning Domain-Invariant Conditional Features for Robust Face Anti-spoofing
International Journal of Computer Vision, Volume 131, Issue 7•Jul 2023, pp 1680-1703 • https://doi.org/10.1007/s11263-023-01778-xAbstractFace anti-spoofing has been widely exploited in recent years to ensure security in face recognition systems; however, this technology suffers from poor generalization performance on unseen samples. Most previous methods align the marginal ...