10 accepted papers
The deployment of quantized neural networks on edge devices, combined with privacy regulations like GDPR, creates an urgent need for machine unlearning in quantized models. However, existing methods face critical challenges: they induce forgetting by training models to memorize incorrect labels, con…
Depth completion from sparse LiDAR points and images is a key perception task for autonomous robots, enabling dense 3D understanding in challenging environments. However, most recent researches achieve accuracy gains by greatly enlarging network size, making them unsuitable for realtime deployment o…
Large language models are extensively utilized in creative writing applications. Creative writing requires a balance between subjective writing quality (e.g., literariness and emotional expression) and objective constraint following (e.g., format requirements and word limits). Existing reinforcement
Eye movement classification can decode cognitive processes, offering valuable insights for a wide range of applications. However, existing eye movement classification models primarily focus on static fixation-based features and often neglect the encoding of spatiotemporal eye movement features, whic…
Intelligent optimization algorithm (IOA) has been widely applied to active noise control (ANC) in recent years. Compared to the conventional filtered-x least mean square (FxLMS) algorithm-based ANC, IOA-based ANC not only eliminates the necessity for secondary path identification but also avoids the…
Lane detection methods based on anchors have received increasing attention, but fixed-shape anchors make it difficult to model complex lane line shapes. To solve this problem, we propose an Enhanced Curve Perception Network (ECPNet). Specifically, we propose a Layer-by-layer Context Fusion (LCF) mod…
Security vulnerabilities, illustrated by the menace of track traffic or vehicle hacking, present a substantial risk to the Controller Area Network (CAN) bus, enabling unauthorized remote access and intrusion. Nevertheless, existing vehicle intrusion detection models encounter challenges in capturing…
Current video saliency prediction methods have made great progress relying on the feature extraction capability of CNN, but there are still many defects in hierarchical feature fusion, limiting the further improvement of accuracy. To address this issue, we propose a 3D convolutional Hierarchical Spa…
"Compositional Zero-Shot Learning (CZSL) aims to recognize novel compositions using knowledge learned from seen attribute-object compositions in the training set. Previous works mainly project an image and a composition into a common embedding space to measure their compatibility score. However, bot…
Due to the increasing usage of Deep Neural Network (DNN) based autonomous driving systems (ADS) where erroneous or unexpected behaviours can lead to catastrophic accidents, testing such systems is of growing importance. Existing approaches often just focus on finding erroneous behaviours and have no…