14 accepted papers
Diffusion models have achieved remarkable success in image and video generation. However, their inherently multiple step inference process imposes substantial computational overhead, hindering real-world deployment. Accelerating diffusion models is therefore essential, yet determining how to combine
Federated learning has become a promising solution for collaboration among medical institutions. However, data owned by each institution would be highly heterogeneous and the distribution is always non-independent and identical distribution (non-IID), resulting in client drift and unsatisfactory per…
Federated learning has wide applications in the medical field. It enables knowledge sharing among different healthcare institutes while protecting patients' privacy. However, existing federated learning systems are typically centralized, requiring clients to upload client-specific knowledge to a cen…
Semi-supervised Domain adaptation (SSDA) has shown promising results by leveraging unlabeled data and limited labeled samples in the target domain. However, accessibility to source data is hindered by data privacy concerns, giving rise to Semi-supervised Source Hypothesis Transfer (SSHT). Integratin…
Federated learning is widely used in medical applications for training global models without needing local data access, but varying computational capabilities and network architectures (system heterogeneity) across clients pose significant challenges in effectively aggregating information from non-i…
Federated learning (FL) allows different participants to collaborate on model training without transmitting raw data, thereby protecting user data privacy. However, FL faces a series of security and privacy issues (e.g. the leakage of raw data from publicly shared parameters). Several privacy protec…
Representation learning frameworks in unlabeled time series have been proposed for medical signal processing. Despite the numerous excellent progresses have been made in previous works, we observe the representation extracted for the time series still does not generalize well. In this paper, we pres…
3D photography renders a static image into a video with appealing 3D visual effects. Existing approaches typically first conduct monocular depth estimation, then render the input frame to subsequent frames with various viewpoints, and finally use an inpainting model to fill those missing/occluded re…
At present, backdoor attacks attract attention as they do great harm to deep learning models. By poisoning the training data, the adversary makes the model trained based on this dataset being injected with a backdoor. In the field of text, however, existing works do not provide sufficient defense ag…
Existing zero-shot cross-lingual transfer methods rely on parallel corpora or bilingual dictionaries, which are expensive and impractical for low-resource languages. To disengage from these dependencies, researchers have explored training multilingual models on English-only resources and transferrin…
Online/offline identity-based signature (OO-IBS) is an adequate cryptographic tool to provide the message authentication and integrity in mobile devices, since it lightens the computational burden after the signer receives the message and eliminates the overhead of certificate management. It has sev…
Previous studies have proved that cross-lingual knowledge distillation can significantly improve the performance of pre-trained models for cross-lingual similarity matching tasks. However, the student model needs to be large in this operation. Otherwise, its performance will drop sharply, thus makin…
Infinite visual synthesis aims to generate high-resolution images, long-duration videos, and even visual generation of infinite size. Some recent work tried to solve this task by first dividing data into processable patches and then training the models on them without considering the dependencies be…
"This paper presents a unified multimodal pre-trained model called NÃœWA that can generate new or manipulate existing visual data (i.e., image and video) for various visual synthesis tasks. To cover language, image, and video at the same time for different scenarios, a 3D transformer encoder-decoder…