Generalized video anomaly event detection: Systematic taxonomy and comparison of deep models
Video Anomaly Detection (VAD) serves as a pivotal technology in the intelligent surveillance
systems, enabling the temporal or spatial identification of anomalous events within videos …
systems, enabling the temporal or spatial identification of anomalous events within videos …
Context de-confounded emotion recognition
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 …
aims to perceive the emotional states of the target person with contextual information …
Aide: A vision-driven multi-view, multi-modal, multi-tasking dataset for assistive driving perception
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 …
decade. Despite the growing development of vision-driven driver monitoring systems, the …
Robust emotion recognition in context debiasing
Context-aware emotion recognition (CAER) has recently boosted the practical applications
of affective computing techniques in unconstrained environments. Mainstream CAER …
of affective computing techniques in unconstrained environments. Mainstream CAER …
Efficient decision-based black-box patch attacks on video recognition
Abstract Although Deep Neural Networks (DNNs) have demonstrated excellent
performance, they are vulnerable to adversarial patches that introduce perceptible and …
performance, they are vulnerable to adversarial patches that introduce perceptible and …
Improving generalization in visual reinforcement learning via conflict-aware gradient agreement augmentation
Learning a policy with great generalization to unseen environments remains challenging but
critical in visual reinforcement learning. Despite the success of augmentation combination in …
critical in visual reinforcement learning. Despite the success of augmentation combination in …
Learning causality-inspired representation consistency for video anomaly detection
Video anomaly detection is an essential yet challenging task in the multimedia community,
with promising applications in smart cities and secure communities. Existing methods …
with promising applications in smart cities and secure communities. Existing methods …
Osin: Object-centric scene inference network for unsupervised video anomaly detection
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 …
community, which aims to understand the spatial and temporal contextual interactions …
Model robustness meets data privacy: Adversarial robustness distillation without original data
Large-scale deep learning models have achieved great performance based on large-scale
datasets. Moreover, the existing Adversarial Training (AT) can further improve the …
datasets. Moreover, the existing Adversarial Training (AT) can further improve the …
Boosting the transferability of adversarial attacks with global momentum initialization
Deep neural networks are vulnerable to adversarial examples, which attach human invisible
perturbations to benign inputs. Simultaneously, adversarial examples exhibit transferability …
perturbations to benign inputs. Simultaneously, adversarial examples exhibit transferability …