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

Trajectory Prediction (TP) is an important research topic in computer vision and robotics fields. Recently, many stochastic TP models have been proposed to deal with this problem and have achieved better performance than the traditional…

Machine learning (ML) tools such as encoder-decoder convolutional neural networks (CNN) can represent incredibly complex nonlinear functions which map between combinations of images and scalars. For example, CNNs can be used to map…

Autonomous driving systems (ADS) increasingly rely on deep learning-based perception models, which remain vulnerable to adversarial attacks. In this paper, we revisit adversarial attacks and defense methods, focusing on road sign…

Predicting vehicle trajectories, angle and speed is important for safe and comfortable driving. We demonstrate the best predicted angle, speed, and best performance overall winning the top three places of the ICCV 2019 Learning to Drive…

We propose a novel approach for detecting change points in high-dimensional linear regression models. Unlike previous research that relied on strict Gaussian/sub-Gaussian error assumptions and had prior knowledge of change points, we…

Temporal distances lie at the heart of many algorithms for planning, control, and reinforcement learning that involve reaching goals, allowing one to estimate the transit time between two states. However, prior attempts to define such…

Depth prediction is a critical problem in robotics applications especially autonomous driving. Generally, depth prediction based on binocular stereo matching and fusion of monocular image and laser point cloud are two mainstream methods.…

Monocular depth estimation is one of the fundamental tasks in environmental perception and has achieved tremendous progress in virtue of deep learning. However, the performance of trained models tends to degrade or deteriorate when employed…

3D perception plays an essential role for improving the safety and performance of autonomous driving. Yet, existing models trained on real-world datasets, which naturally exhibit long-tail distributions, tend to underperform on rare and…

Despite the recent success of deep neural networks, it remains challenging to effectively model the long-tail class distribution in visual recognition tasks. To address this problem, we first investigate the performance bottleneck of the…

Machine learning (ML) tools such as encoder-decoder deep convolutional neural networks (CNN) are able to extract relationships between inputs and outputs of large complex systems directly from raw data. For time-varying systems the…

In neutrino physics, analyses often depend on large simulated datasets, making it essential for models to generalise effectively to real-world detector data. Contrastive learning, a well-established technique in deep learning, offers a…

The design of the proposal distributions, and most notably the kernel parameters, are crucial for the performance of Markov chain Monte Carlo (MCMC) rendering. A poor selection of parameters can increase the correlation of the Markov chain…

In this paper, we present a novel trajectory prediction model for autonomous driving, combining a Characterized Diffusion Module and a Spatial-Temporal Interaction Network to address the challenges posed by dynamic and heterogeneous traffic…

Neural predictors have shown great potential in the evaluation process of neural architecture search (NAS). However, current predictor-based approaches overlook the fact that training a predictor necessitates a considerable number of…

We propose a hybrid meta-learning framework for forecasting and anomaly detection in nonlinear dynamical systems characterized by nonstationary and stochastic behavior. The approach integrates a physics-inspired simulator that captures…

Accurate motion forecasting is crucial for safe autonomous driving (AD). This study proposes CoT-Drive, a novel approach that enhances motion forecasting by leveraging large language models (LLMs) and a chain-of-thought (CoT) prompting…

End-to-end autonomous driving frameworks enable seamless integration of perception and planning but often rely on one-shot trajectory prediction, which may lead to unstable control and vulnerability to occlusions in single-frame perception.…

Widespread development of driverless vehicles has led to the formation of autonomous racing, where technological development is accelerated by the high speeds and competitive environment of motorsport. A particular challenge for an…

The core of any flight schedule is the trajectories. In particular, 4D trajectories are the most crucial component for flight attribute prediction. In particular, 4D trajectories are the most crucial component for flight attribute…