6 accepted papers
Realistic talking-head video generation is critical for virtual avatars, film production, and interactive systems. Current methods struggle with nuanced emotional expressions due to the lack of fine-grained emotion control. To address this issue, we introduce a novel two-stage method (AUHead) to dis…
Medical imaging is now a widely used test for the preoperative evaluation of focal cortical dysplasia (FCD). Deep learning-based methods can learn lesion features from image data to automatically recognize and segment FCD in epilepsy treatment. However, the existing FCD segmentation networks lack th…
Large-scale place recognition based on point clouds remains a challenge due to the geometric transformations in the scene. Among many geometric transformations, rotation is particularly challenging to handle in practice. Only a few works try to encode rotation invariance into learning based place re
Point cloud based place recognition remains a challenging issue due to the difficulty in extracting and encoding local features into robust and discriminative global descriptors from large-scale scenes. In this paper, we propose a novel deep neural network named SAGE-Net (Spatial Attention and Geome
Model poisoning attacks greatly jeopardize the application of federated learning (FL). The effectiveness of existing defenses is susceptible to the latest model poisoning attacks, leading to a decrease in prediction accuracy. Besides, these defenses are intractable to distinguish benign outliers fro…
"Recent contrastive based 3D action representation learning has made great progress. However, the strict positive/negative constraint is yet to be relaxed and the use of non-self positive is yet to be explored. In this paper, a Contrastive Positive Mining (CPM) framework is proposed for unsupervised…