Related papers: PreTraM: Self-Supervised Pre-training via Connecti…

This paper proposes a pre-trained neural network for handling event camera data. Our model is a self-supervised learning framework, and uses paired event camera data and natural RGB images for training. Our method contains three modules…

In automated driving, predicting trajectories of surrounding vehicles supports reasoning about scene dynamics and enables safe planning for the ego vehicle. However, existing models handle predictions as an instantaneous task of forecasting…

Recent advances in Deep Learning have greatly improved performance on various tasks such as object detection, image segmentation, sentiment analysis. The focus of most research directions up until very recently has been on beating…

Benchmarking anomaly detection approaches for multivariate time series is a challenging task due to a lack of high-quality datasets. Current publicly available datasets are too small, not diverse and feature trivial anomalies, which hinders…

This paper jointly addresses three key limitations in conventional pedestrian trajectory forecasting: pedestrian perception errors, real-world data collection costs, and person ID annotation costs. We propose a novel framework, RealTraj,…

Deep learning has been successful in automating the design of features in machine learning pipelines. However, the algorithms optimizing neural network parameters remain largely hand-designed and computationally inefficient. We study if we…

Masked video modeling (MVM) has emerged as a simple and scalable self-supervised pretraining paradigm, but only encodes motion information implicitly, limiting the encoding of temporal dynamics in the learned representations. As a result,…

As an agent moves through the world, the apparent motion of scene elements is (usually) inversely proportional to their depth. It is natural for a learning agent to associate image patterns with the magnitude of their displacement over…

Self-supervised pretraining has been observed to be effective at improving feature representations for transfer learning, leveraging large amounts of unlabelled data. This review summarizes recent research into its usage in X-ray, computed…

Deep pretrained transformer networks are effective at various ranking tasks, such as question answering and ad-hoc document ranking. However, their computational expenses deem them cost-prohibitive in practice. Our proposed approach, called…

We introduce ForeSight, a novel joint detection and forecasting framework for vision-based 3D perception in autonomous vehicles. Traditional approaches treat detection and forecasting as separate sequential tasks, limiting their ability to…

Graphs can model complex relationships between objects, enabling a myriad of Web applications such as online page/article classification and social recommendation. While graph neural networks(GNNs) have emerged as a powerful tool for graph…

The rising demand for Active Safety systems in automotive applications stresses the need for a reliable short to mid-term trajectory prediction. Anticipating the unfolding path of road users, one can act to increase the overall safety. In…

Making accurate motion prediction of surrounding agents such as pedestrians and vehicles is a critical task when robots are trying to perform autonomous navigation tasks. Recent research on multi-modal trajectory prediction, including…

Pretraining DNA language models (DNALMs) on the full human genome is resource-intensive, yet often considered necessary for strong downstream performance. Inspired by recent findings in NLP and long-context modeling, we explore an…

Trajectory Representation Learning (TRL) is a powerful tool for spatial-temporal data analysis and management. TRL aims to convert complicated raw trajectories into low-dimensional representation vectors, which can be applied to various…

Numerous methods for human activity recognition have been proposed in the past two decades. Many of these methods are based on sparse representation, which describes the whole video content by a set of local features. Trajectories, being…

Self-supervised learning has emerged as a powerful tool for pretraining deep networks on unlabeled data, prior to transfer learning of target tasks with limited annotation. The relevance between the pretraining pretext and target tasks is…

Large Multimodal Models (LMMs) have recently gained prominence in autonomous driving research, showcasing promising capabilities across various emerging benchmarks. LMMs specifically designed for this domain have demonstrated effective…

Recent progress of deep learning has empowered various intelligent transportation applications, especially in car-sharing platforms. While the traditional operations of the car-sharing service highly relied on human engagements in fleet…