Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- abstractJune 2024
MVRMLM 2024: Multimodal Video Retrieval and Multimodal Language Modelling
- Hui Wang,
- Josef Kittler,
- Mark Gales,
- Rob Cooper,
- Maurice Mulvenna,
- Wing Ng,
- Yang Hua,
- Richard Gault,
- Abbas Haider,
- Guanfeng Wu
ICMR '24: Proceedings of the 2024 International Conference on Multimedia RetrievalPages 1345–1346https://doi.org/10.1145/3652583.3660001As the proliferation of video content continues, and many video archives lack suitable metadata, therefore, video retrieval, particularly through example-based search, has become increasingly crucial. Existing metadata often fails to meet the needs of ...
- research-articleFebruary 2024
Siren<inline-formula><tex-math notation="LaTeX">$^+$</tex-math><alternatives><mml:math><mml:msup><mml:mrow/><mml:mo>+</mml:mo></mml:msup></mml:math><inline-graphic xlink:href="song-ieq1-3362534.gif"/></alternatives></inline-formula>: Robust Federated Learning With Proactive Alarming and Differential Privacy
IEEE Transactions on Dependable and Secure Computing (TDSC), Volume 21, Issue 5Pages 4843–4860https://doi.org/10.1109/TDSC.2024.3362534Federated learning (FL), an emerging machine learning paradigm that trains a global model across distributed clients without violating data privacy, has recently attracted significant attention. However, FL's distributed nature and iterative ...
- research-articleFebruary 2024
Unpaired Caricature-Visual Face Recognition via Feature Decomposition-Restoration-Decomposition
IEEE Transactions on Circuits and Systems for Video Technology (IEEETCSVT), Volume 34, Issue 7Pages 5693–5703https://doi.org/10.1109/TCSVT.2024.3361799Existing caricature-visual face recognition methods train the models based on caricature-visual image pairs from the same identities. Unfortunately, in many real-world applications, facial caricatures and visual facial images are usually unpaired in the ...
- research-articleMay 2024
Eliminating domain bias for federated learning in representation space
NIPS '23: Proceedings of the 37th International Conference on Neural Information Processing SystemsArticle No.: 625, Pages 14204–14227Recently, federated learning (FL) is popular for its privacy-preserving and collaborative learning abilities. However, under statistically heterogeneous scenarios, we observe that biased data domains on clients cause a representation bias phenomenon and ...
- research-articleSeptember 2023
Robust Searching-Based Gradient Collaborative Management in Intelligent Transportation System
ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), Volume 20, Issue 2Article No.: 34, Pages 1–23https://doi.org/10.1145/3549939With the rapid development of big data and the Internet of Things (IoT), traffic data from an Intelligent Transportation System (ITS) is becoming more and more accessible. To understand and simulate the traffic patterns from the traffic data, Multimedia ...
-
- research-articleAugust 2023
FedCP: Separating Feature Information for Personalized Federated Learning via Conditional Policy
KDD '23: Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data MiningPages 3249–3261https://doi.org/10.1145/3580305.3599345Recently, personalized federated learning (pFL) has attracted increasing attention in privacy protection, collaborative learning, and tackling statistical heterogeneity among clients, e.g., hospitals, mobile smartphones, etc. Most existing pFL methods ...
- research-articleJuly 2023
Adversarial example does good: preventing painting imitation from diffusion models via adversarial examples
ICML'23: Proceedings of the 40th International Conference on Machine LearningArticle No.: 856, Pages 20763–20786Recently, Diffusion Models (DMs) boost a wave in AI for Art yet raise new copyright concerns, where infringers benefit from using unauthorized paintings to train DMs to generate novel paintings in a similar style. To address these emerging copyright ...
- surveyJuly 2023
Resource-Efficient Convolutional Networks: A Survey on Model-, Arithmetic-, and Implementation-Level Techniques
- JunKyu Lee,
- Lev Mukhanov,
- Amir Sabbagh Molahosseini,
- Umar Minhas,
- Yang Hua,
- Jesus Martinez del Rincon,
- Kiril Dichev,
- Cheol-Ho Hong,
- Hans Vandierendonck
ACM Computing Surveys (CSUR), Volume 55, Issue 13sArticle No.: 276, Pages 1–36https://doi.org/10.1145/3587095Convolutional neural networks (CNNs) are used in our daily life, including self-driving cars, virtual assistants, social network services, healthcare services, and face recognition, among others. However, deep CNNs demand substantial compute resources ...
- research-articleJune 2023
MCAS-GP: Deep Learning-Empowered Middle Cerebral Artery Segmentation and Gate Proposition
IEEE/ACM Transactions on Computational Biology and Bioinformatics (TCBB), Volume 21, Issue 4Pages 924–935https://doi.org/10.1109/TCBB.2023.3281776With the fast development of AI technologies, deep learning is widely applied for biomedical data analytics and digital healthcare. However, there remain gaps between AI-aided diagnosis and real-world healthcare demands. For example, hemodynamic ...
- research-articleMay 2023
WH2D2N2: Distributed AI-enabled OK-ASN Service for Web of Things
ACM Transactions on Asian and Low-Resource Language Information Processing (TALLIP), Volume 22, Issue 5Article No.: 145, Pages 1–16https://doi.org/10.1145/3564242Model data-driven ontology and knowledge presentation for evolving semantic Asian social networks (OK-ASN) is a critical strategy for web of things (WoT) services. Meanwhile, Deep Neural Network (DNN)-based OK-ASN service in WoT is growing rapidly. ...
- research-articleFebruary 2023
FedALA: adaptive local aggregation for personalized 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 IntelligenceArticle No.: 1261, Pages 11237–11244https://doi.org/10.1609/aaai.v37i9.26330A key challenge in federated learning (FL) is the statistical heterogeneity that impairs the generalization of the global model on each client. To address this, we propose a method Federated learning with Adaptive Local Aggregation (FedALA) by capturing ...
- ArticleMarch 2023
Self-supervised Multi-object Tracking with Cycle-Consistency
AbstractMulti-object tracking is a challenging video task that requires both locating the objects in the frames and associating the objects among the frames, which usually utilizes the tracking-by-detection paradigm. Supervised multi-object tracking ...
- research-articleJanuary 2023
Pth moment attractivity analysis for first order uncertain differential systems
Journal of Intelligent & Fuzzy Systems: Applications in Engineering and Technology (JIFS), Volume 45, Issue 5Pages 8365–8370https://doi.org/10.3233/JIFS-232233It is generally considered that attractivity is a concept that describes the overall characteristics of a system. This paper aims to study Pth moment attractivity for one order uncertain differential systems. According to the theory of uncertain ...
- research-articleNovember 2022
CSM-Net: Automatic joint segmentation of intima-media complex and lumen in carotid artery ultrasound images
Computers in Biology and Medicine (CBIM), Volume 150, Issue Chttps://doi.org/10.1016/j.compbiomed.2022.106119AbstractThe intima-media thickness (IMT) is an effective biomarker for atherosclerosis, which is commonly measured by ultrasound technique. However, the intima-media complex (IMC) segmentation for the IMT is challenging due to confused IMC boundaries and ...
Highlights- Joint segmentation of intima-media complex and lumen in carotid ultrasound images.
- The cascaded dilated convolutions rectified by the squeeze-excitation net.
- A triple spatial attention module to exploit useful features after skip ...
- ArticleOctober 2022
TDViT: Temporal Dilated Video Transformer for Dense Video Tasks
AbstractDeep video models, for example, 3D CNNs or video transformers, have achieved promising performance on sparse video tasks, i.e., predicting one result per video. However, challenges arise when adapting existing deep video models to dense video ...
- ArticleOctober 2022
Efficient One-Stage Video Object Detection by Exploiting Temporal Consistency
AbstractRecently, one-stage detectors have achieved competitive accuracy and faster speed compared with traditional two-stage detectors on image data. However, in the field of video object detection (VOD), most existing VOD methods are still based on two-...
- research-articleMay 2023
A Transfer Learning and Image Augmentation Method for Carotid Artery Vulnerable Plaque Segmentation in Ultrasound Images
AIPR '22: Proceedings of the 2022 5th International Conference on Artificial Intelligence and Pattern RecognitionPages 427–434https://doi.org/10.1145/3573942.3574044Evaluating carotid artery plaque by ultrasound technique is a crucial factor in the screening of atherosclerosis. However, vulnerable plaque segmentation remains a challenging task because of the heterogeneities of inter-plaques and intra-plaques, and ...
- research-articleJuly 2022
Perceptual Data Augmentation for Biomedical Coronary Vessel Segmentation
IEEE/ACM Transactions on Computational Biology and Bioinformatics (TCBB), Volume 20, Issue 4Pages 2494–2505https://doi.org/10.1109/TCBB.2022.3188148Sufficient annotated data is critical to the success of deep learning methods. Annotating for vessel segmentation in X-ray coronary angiograms is extremely difficult because of the small and complex structures to be processed. Although unsupervised domain ...
- research-articleJune 2022
Hierarchical CADNet: Learning from B-Reps for Machining Feature Recognition
AbstractDeep learning approaches have been shown to be capable of recognizing shape features (e.g. machining features) in Computer-Aided Design (CAD) models in certain circumstances, yet still have issues when the features intersect, and in exploiting ...
Highlights- A novel representation and deep learning framework for learning from B-Rep CAD models.
- A complex CAD model dataset with labeled machining features is proposed.
- Improvements over current state-of-the-art deep learning frameworks for ...
- research-articleFebruary 2022
Hierarchical Satellite System Graph for Approximate Nearest Neighbor Search on Big Data
ACM/IMS Transactions on Data Science (TDS), Volume 2, Issue 4Article No.: 32, Pages 1–15https://doi.org/10.1145/3488377Approximate nearest neighbor search is a classical problem in data science, which is widely applied in many fields. With the rapid growth of data in the real world, it becomes more and more important to speed up the nearest neighbor search process. ...