Related papers: AMD: Adaptive Momentum and Decoupled Contrastive L…

In order to drive safely and efficiently on public roads, autonomous vehicles will have to understand the intentions of surrounding vehicles, and adapt their own behavior accordingly. If experienced human drivers are generally good at…

In recent years, self-supervised representation learning for skeleton-based action recognition has advanced with the development of contrastive learning methods. However, most of contrastive paradigms are inherently discriminative and often…

Multi-modal contrastive learning as a self-supervised representation learning technique has achieved great success in foundation model training, such as CLIP~\citep{radford2021learning}. In this paper, we study the theoretical properties of…

Trajectory prediction is a critical part of many AI applications, for example, the safe operation of autonomous vehicles. However, current methods are prone to making inconsistent and physically unrealistic predictions. We leverage insights…

Vehicle taillight recognition is an important application for automated driving, especially for intent prediction of ado vehicles and trajectory planning of the ego vehicle. In this work, we propose an end-to-end deep learning framework to…

Deep neural networks have recently achieved notable progress in 3D point cloud recognition, yet their vulnerability to adversarial perturbations poses critical security challenges in practical deployments. Conventional defense mechanisms…

Trajectory prediction in autonomous driving has traditionally been studied from a model-centric perspective. However, existing datasets exhibit a strong long-tail distribution in scenario density, where common low-density cases dominate and…

We propose a continuous-time scheme for large-scale optimization that introduces individual, adaptive momentum coefficients regulated by the kinetic energy of each model parameter. This approach automatically adjusts to local landscape…

As medical diagnoses increasingly leverage multimodal data, machine learning models are expected to effectively fuse heterogeneous information while remaining robust to missing modalities. In this work, we propose a novel multimodal…

Predicting the behaviour (i.e., manoeuvre/trajectory) of other road users, including vehicles, is critical for the safe and efficient operation of autonomous vehicles (AVs), a.k.a., automated driving systems (ADSs). Due to the uncertain…

Detecting abnormal nodes from attributed networks is of great importance in many real applications, such as financial fraud detection and cyber security. This task is challenging due to both the complex interactions between the anomalous…

Optimization algorithms with momentum, e.g., (ADAM), have been widely used for building deep learning models due to the faster convergence rates compared with stochastic gradient descent (SGD). Momentum helps accelerate SGD in the relevant…

Heterogeneous graph neural networks (HGNNs) have significantly propelled the information retrieval (IR) field. Still, the effectiveness of HGNNs heavily relies on high-quality labels, which are often expensive to acquire. This challenge has…

Temporal link prediction is crucial for rapidly growing social networks. Existing methods often overlook the underlying causal mechanisms that drive link formation, making it difficult for algorithms to adapt to complex structures that…

Learning from tabular data is of paramount importance, as it complements the conventional analysis of image and video data by providing a rich source of structured information that is often critical for comprehensive understanding and…

Motion prediction is critical for autonomous vehicles to effectively navigate complex environments and accurately anticipate the behaviors of other traffic participants. As autonomous driving continues to evolve, the need to assimilate new…

Deep anomaly detection (AD) aims to provide robust and efficient classifiers for one-class and unbalanced settings. However current AD models still struggle on edge-case normal samples and are often unable to keep high performance over…

Distracted driving is one of the major reasons for vehicle accidents. Therefore, detecting distracted driving behaviors is of paramount importance to reduce the millions of deaths and injuries occurring worldwide. Distracted or anomalous…

Long-tailed semi-supervised learning poses a significant challenge in training models with limited labeled data exhibiting a long-tailed label distribution. Current state-of-the-art LTSSL approaches heavily rely on high-quality…

Alternating Direction Method of Multipliers (ADMM) has been used successfully in many conventional machine learning applications and is considered to be a useful alternative to Stochastic Gradient Descent (SGD) as a deep learning optimizer.…