D Yang, Z Chen, Y Wang, S Wang… - Proceedings of the …, 2023 - openaccess.thecvf.com
Abstract Context-Aware Emotion Recognition (CAER) is a crucial and challenging task that aims to perceive the emotional states of the target person with contextual information …
D Yang, S Huang, Z Xu, Z Li, S Wang… - Proceedings of the …, 2023 - openaccess.thecvf.com
Driver distraction has become a significant cause of severe traffic accidents over the past decade. Despite the growing development of vision-driven driver monitoring systems, the …
D Yang, K Yang, M Li, S Wang… - Proceedings of the …, 2024 - openaccess.thecvf.com
Context-aware emotion recognition (CAER) has recently boosted the practical applications of affective computing techniques in unconstrained environments. Mainstream CAER …
Abstract Although Deep Neural Networks (DNNs) have demonstrated excellent performance, they are vulnerable to adversarial patches that introduce perceptible and …
Learning a policy with great generalization to unseen environments remains challenging but critical in visual reinforcement learning. Despite the success of augmentation combination in …
Video anomaly detection is an essential yet challenging task in the multimedia community, with promising applications in smart cities and secure communities. Existing methods …
Y Liu, Z Guo, J Liu, C Li, L Song - IEEE Signal Processing …, 2023 - ieeexplore.ieee.org
Video Anomaly Detection (VAD) is an essential yet challenging task in the signal processing community, which aims to understand the spatial and temporal contextual interactions …
Large-scale deep learning models have achieved great performance based on large-scale datasets. Moreover, the existing Adversarial Training (AT) can further improve the …
Deep neural networks are vulnerable to adversarial examples, which attach human invisible perturbations to benign inputs. Simultaneously, adversarial examples exhibit transferability …