Learning with noisy labels aims to ensure model generalization given a label-corrupted training set. The sample selection strategy achieves promising performance by selecting a label-reliable subset for model training...
详细信息
Time Sensitive Network (TSN) provides strict low latency and bounded jitter requirements for applications such as industrial systems, autonomous driving, etc. One of the important problems in TSN is to achieve high re...
详细信息
Virtual reality technology is providing a new method for psychologi-cal relaxation training, but most systems focus primarily on medi-tation as a singular relaxation method. We propose a novel virtual reality relaxati...
详细信息
ISBN:
(数字)9798350374490
ISBN:
(纸本)9798350374506
Virtual reality technology is providing a new method for psychologi-cal relaxation training, but most systems focus primarily on medi-tation as a singular relaxation method. We propose a novel virtual reality relaxation system called TaoRelax. Building upon traditional Taoist culture, the system integrates both meditation and progressive muscle relaxation training. It combines electromyography (EMG) as a means of feedback and assessment during training, providing users with a dual experience of relaxation for both body and mind. Our preliminary results indicate that after training in our system, participants experienced a significant reduction in psychological stress and a notable improvement in meditation abilities.
Efficient fine-tuning is vital for adapting large language models (LLMs) to downstream tasks. However, it requires non-trivial efforts to implement these methods on different models. We present LLAMAFACTORY, a unified...
详细信息
The data such as features involved in recommendation systems often contain private information that can cause serious security problems if leaked to other participants in the system. At present, Federated Learning (FL...
详细信息
As graphs grow larger, full-batch GNN training becomes hard for single GPU memory. Therefore, to enhance the scalability of GNN training, some studies have proposed sampling-based mini-batch training and distributed g...
详细信息
In gamma ray imaging for nuclear medicine, coded aperture is used to improve sensitivity. one of the main reconstructing methods is inverse filtering (deconvolution), where the recorded image is cross-correlated with ...
详细信息
Camouflaged object detection (COD) aims to identify objects that blend into the surrounding backgrounds, which has been a hot topic in recent years, with many different optimization strategies being explored. Among th...
详细信息
ISBN:
(数字)9798350359312
ISBN:
(纸本)9798350359329
Camouflaged object detection (COD) aims to identify objects that blend into the surrounding backgrounds, which has been a hot topic in recent years, with many different optimization strategies being explored. Among these, collaborative detection, a recently proposed solution for COD, has shown outstanding performance. However, current collaborative detection methods adopt a "one-to-many" pattern, failing to fully leverage the advantages of collaborative detection. Moreover, existing approaches to disguised target detection overlook the importance of high-level features. To address these issues, we propose a novel dualcross query network (DCQNet). It effectively capitalizes on the commonalities among objects and the directive role of high-level features in enhancing low-level features. Specifically, we designed a cross-sample query module and a cross-scale query module to collaboratively locate the object and guide low-level features, respectively. Extensive experimental results demonstrate that DCQNet outperforms state-of-the-art (SOTA) methods on the CoCOD8K dataset.
Image-to-Image synthesis paradigms have been widely used for facial expression synthesis. However, current generators are apt to either produce artifacts for largely posed and non-aligned faces or unduly change the id...
Image-to-Image synthesis paradigms have been widely used for facial expression synthesis. However, current generators are apt to either produce artifacts for largely posed and non-aligned faces or unduly change the identity information like AdaIN-based generator. In this work, we suggest to use image style feature to surrogate the expression cues in the generator, and propose a multi-task learning paradigm to explore this style information via the supervision learning and feature disentanglement. While the supervision learning can make the encoded style specifically represent the expression cues and enable the generator to produce correct expression, the feature disentanglement of content and style cues enables the generator to better preserve the identity information in expression synthesis. Experimental results show that the proposed algorithm can well reduce the artifacts for the synthesis of posed and non-aligned expressions, and achieves competitive performances in terms of FID, PNSR and classification accuracy, compared with four publicly available GANs. The code and pre-trained models are available at https://***/lumanxi236/MTSS.
暂无评论