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
AlignCLIP: Align Multi Domains of Texts Input for CLIP models with Object-IoU Loss
MM '24: Proceedings of the 32nd ACM International Conference on Multimedia•October 2024, pp 1092-1100• https://doi.org/10.1145/3664647.3681636Since the release of the CLIP model by OpenAI, it has received widespread attention. However, categories in the real world often exhibit a long-tail distribution, and existing CLIP models struggle to effectively recognize rare, tail-end classes, such as ...
- research-article
Bilateral Adaptive Cross-Modal Fusion Prompt Learning for CLIP
MM '24: Proceedings of the 32nd ACM International Conference on Multimedia•October 2024, pp 9001-9009• https://doi.org/10.1145/3664647.3681218In the realm of CLIP adaptation through prompt learning, it is important to emphasize the pivotal role that the proper alignment of visual and textual representations plays when adapting the CLIP to downstream tasks. We propose that the proper alignment ...
- Article
Enhancing Tampered Text Detection Through Frequency Feature Fusion and Decomposition
Computer Vision – ECCV 2024•September 2024, pp 200-217• https://doi.org/10.1007/978-3-031-73414-4_12AbstractDocument image tampering poses a grave risk to the veracity of information, with potential consequences ranging from misinformation dissemination to financial and identity fraud. Current detection methods use frequency information to uncover ...
- Article
TF-FAS: Twofold-Element Fine-Grained Semantic Guidance for Generalizable Face Anti-spoofing
Computer Vision – ECCV 2024•September 2024, pp 148-168• https://doi.org/10.1007/978-3-031-72667-5_9AbstractGeneralizable Face anti-spoofing (FAS) approaches have recently garnered considerable attention due to their robustness in unseen scenarios. Some recent methods incorporate vision-language models into FAS, leveraging their impressive pre-trained ...
- research-article
Towards Unified Defense for Face Forgery and Spoofing Attacks via Dual Space Reconstruction Learning
International Journal of Computer Vision, Volume 132, Issue 12•Dec 2024, pp 5862-5887 • https://doi.org/10.1007/s11263-024-02151-2AbstractReal-world face recognition systems are vulnerable to diverse face attacks, ranging from digitally manipulated artifacts to physically crafted spoofing attacks. Existing works primarily focus on using an image classification network to address one ...
- research-article
PCE-palm: palm crease energy based two-stage realistic pseudo-palmprint generation
- Jianlong Jin,
- Lei Shen,
- Ruixin Zhang,
- Chenglong Zhao,
- Ge Jin,
- Jingyun Zhang,
- Shouhong Ding,
- Yang Zhao,
- Wei Jia
AAAI'24/IAAI'24/EAAI'24: Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence and Thirty-Sixth Conference on Innovative Applications of Artificial Intelligence and Fourteenth Symposium on Educational Advances in Artificial Intelligence•February 2024, Article No.: 291, pp 2616-2624• https://doi.org/10.1609/aaai.v38i3.28039The lack of large-scale data seriously hinders the development of palmprint recognition. Recent approaches address this issue by generating large-scale realistic pseudo palm-prints from Bézier curves. However, the significant difference between Bézier ...
- research-article
Domain-hallucinated updating for multi-domain face anti-spoofing
AAAI'24/IAAI'24/EAAI'24: Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence and Thirty-Sixth Conference on Innovative Applications of Artificial Intelligence and Fourteenth Symposium on Educational Advances in Artificial Intelligence•February 2024, Article No.: 244, pp 2193-2201• https://doi.org/10.1609/aaai.v38i3.27992Multi-Domain Face Anti-Spoofing (MD-FAS) is a practical setting that aims to update models on new domains using only novel data while ensuring that the knowledge acquired from previous domains is not forgotten. Prior methods utilize the responses from ...
- research-article
MmAP: multi-modal alignment prompt for cross-domain multi-task learning
AAAI'24/IAAI'24/EAAI'24: Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence and Thirty-Sixth Conference on Innovative Applications of Artificial Intelligence and Fourteenth Symposium on Educational Advances in Artificial Intelligence•February 2024, Article No.: 1792, pp 16076-16084• https://doi.org/10.1609/aaai.v38i14.29540Multi-Task Learning (MTL) is designed to train multiple correlated tasks simultaneously, thereby enhancing the performance of individual tasks. Typically, a multi-task network structure consists of a shared backbone and task-specific decoders. However, ...
- research-article
HDMixer: hierarchical dependency with extendable patch for multivariate time series forecasting
AAAI'24/IAAI'24/EAAI'24: Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence and Thirty-Sixth Conference on Innovative Applications of Artificial Intelligence and Fourteenth Symposium on Educational Advances in Artificial Intelligence•February 2024, Article No.: 1407, pp 12608-12616• https://doi.org/10.1609/aaai.v38i11.29155Multivariate time series (MTS) prediction has been widely adopted in various scenarios. Recently, some methods have employed patching to enhance local semantics and improve model performance. However, length-fixed patch are prone to losing temporal ...
- research-article
MFAE: Masked Frequency Autoencoders for Domain Generalization Face Anti-Spoofing
IEEE Transactions on Information Forensics and Security, Volume 19•2024, pp 4058-4069 • https://doi.org/10.1109/TIFS.2024.3371266The generalizable face anti-spoofing (FAS) has attracted much attention recently. Even though many existing methods perform well under intra-domain settings, the model’s performance in the unseen domain is not satisfying. In this paper, we shift ...
- research-article
Content-based unrestricted adversarial attack
NIPS '23: Proceedings of the 37th International Conference on Neural Information Processing Systems•December 2023, Article No.: 2253, pp 51719-51733Unrestricted adversarial attacks typically manipulate the semantic content of an image (e.g., color or texture) to create adversarial examples that are both effective and photorealistic, demonstrating their ability to deceive human perception and deep ...
- research-article
CrossGNN: confronting noisy multivariate time series via cross interaction refinement
NIPS '23: Proceedings of the 37th International Conference on Neural Information Processing Systems•December 2023, Article No.: 2031, pp 46885-46902Recently, multivariate time series (MTS) forecasting techniques have seen rapid development and widespread applications across various fields. Transformer-based and GNN-based methods have shown promising potential due to their strong ability to model ...
- research-article
Seeing in Flowing: Adapting CLIP for Action Recognition with Motion Prompts Learning
MM '23: Proceedings of the 31st ACM International Conference on Multimedia•October 2023, pp 5339-5347• https://doi.org/10.1145/3581783.3612490The Contrastive Language-Image Pre-training (CLIP) has recently shown remarkable generalization on "zero-shot" training and has applied to many downstream tasks. We explore the adaptation of CLIP to achieve a more efficient and generalized action ...
- research-article
SonarGuard: Ultrasonic Face Liveness Detection on Mobile Devices
IEEE Transactions on Circuits and Systems for Video Technology, Volume 33, Issue 8•Aug. 2023, pp 4401-4414 • https://doi.org/10.1109/TCSVT.2023.3236303Liveness detection has been widely applied in face authentication systems to combat malicious attacks. However, existing methods purely depending on visual frames become vulnerable once visual perception is not reliable. The emerging face spoof and forge ...
- research-article
Delving into the adversarial robustness of federated learning
AAAI'23/IAAI'23/EAAI'23: Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence and Thirty-Fifth Conference on Innovative Applications of Artificial Intelligence and Thirteenth Symposium on Educational Advances in Artificial Intelligence•February 2023, Article No.: 1262, pp 11245-11253• https://doi.org/10.1609/aaai.v37i9.26331In Federated Learning (FL), models are as fragile as centrally trained models against adversarial examples. However, the adversarial robustness of federated learning remains largely unexplored. This paper casts light on the challenge of adversarial ...
- research-article
Attack can benefit: an adversarial approach to recognizing facial expressions under noisy annotations
AAAI'23/IAAI'23/EAAI'23: Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence and Thirty-Fifth Conference on Innovative Applications of Artificial Intelligence and Thirteenth Symposium on Educational Advances in Artificial Intelligence•February 2023, Article No.: 408, pp 3660-3668• https://doi.org/10.1609/aaai.v37i3.25477The real-world Facial Expression Recognition (FER) datasets usually exhibit complex scenarios with coupled noise annotations and imbalanced class distribution, which undoubtedly impede the development of FER methods. To address the aforementioned issues, ...
- research-article
Query-Efficient Decision-Based Black-Box Patch Attack
IEEE Transactions on Information Forensics and Security, Volume 18•2023, pp 5522-5536 • https://doi.org/10.1109/TIFS.2023.3307908Deep neural networks (DNNs) have been showed to be highly vulnerable to imperceptible adversarial perturbations. As a complementary type of adversary, patch attacks that introduce perceptible perturbations to the images have attracted the interest of ...
- research-article
Adv-attribute: inconspicuous and transferable adversarial attack on face recognition
NIPS '22: Proceedings of the 36th International Conference on Neural Information Processing Systems•November 2022, Article No.: 2474, pp 34136-34147Deep learning models have shown their vulnerability when dealing with adversarial attacks. Existing attacks almost perform on low-level instances, such as pixels and super-pixels, and rarely exploit semantic clues. For face recognition attacks, existing ...
- research-article
DENSE: data-free one-shot federated learning
NIPS '22: Proceedings of the 36th International Conference on Neural Information Processing Systems•November 2022, Article No.: 1556, pp 21414-21428One-shot Federated Learning (FL) has recently emerged as a promising approach, which allows the central server to learn a model in a single communication round. Despite the low communication cost, existing one-shot FL methods are mostly impractical or ...
- Article
ECO-TR: Efficient Correspondences Finding via Coarse-to-Fine Refinement
- Dongli Tan,
- Jiang-Jiang Liu,
- Xingyu Chen,
- Chao Chen,
- Ruixin Zhang,
- Yunhang Shen,
- Shouhong Ding,
- Rongrong Ji
Computer Vision – ECCV 2022•October 2022, pp 317-334• https://doi.org/10.1007/978-3-031-20080-9_19AbstractModeling sparse and dense image matching within a unified functional correspondence model has recently attracted increasing research interest. However, existing efforts mainly focus on improving matching accuracy while ignoring its efficiency, ...
