相关论文: CaMiT: A Time-Aware Car Model Dataset for Classifi…

Self-driving vehicles are the future of transportation. With current advancements in this field, the world is getting closer to safe roads with almost zero probability of having accidents and eliminating human errors. However, there is…

When faced with learning challenging new tasks, humans often follow sequences of steps that allow them to incrementally build up the necessary skills for performing these new tasks. However, in machine learning, models are most often…

In continual time series analysis using neural networks, catastrophic forgetting (CF) of previously learned models when training on new data domains has always been a significant challenge. This problem is especially challenging in vehicle…

Crop yield prediction is essential for agricultural planning but remains challenging due to the complex interactions between weather, climate, and management practices. To address these challenges, we introduce a deep learning-based…

We present an integrated approach for perception and control for an autonomous vehicle and demonstrate this approach in a high-fidelity urban driving simulator. Our approach first builds a model for the environment, then trains a policy…

Deep learning has contributed remarkably to the advancement of time series analysis. Still, deep models can encounter performance bottlenecks in real-world data-scarce scenarios, which can be concealed due to the performance saturation with…

When designing robots to assist in everyday human activities, it is crucial to enhance user requests with visual cues from their surroundings for improved intent understanding. This process is defined as a multimodal classification task.…

Motor condition monitoring is essential for ensuring system reliability and preventing catastrophic failures. However, data-driven diagnostic methods often suffer from sparse fault labels and severe class imbalance, which limit their…

SimMIM is a widely used method for pretraining vision transformers using masked image modeling. However, despite its success in fine-tuning performance, it has been shown to perform sub-optimally when used for linear probing. We propose an…

Person re-identification is a standard and established problem in the computer vision community. In recent years, vehicle re-identification is also getting more attention. In this paper, we focus on both these tasks and propose a method for…

Self-attention learns pairwise interactions to model long-range dependencies, yielding great improvements for video action recognition. In this paper, we seek a deeper understanding of self-attention for temporal modeling in videos. We…

While today's video recognition systems parse snapshots or short clips accurately, they cannot connect the dots and reason across a longer range of time yet. Most existing video architectures can only process <5 seconds of a video without…

While traditional machine learning can effectively tackle a wide range of problems, it primarily operates within a closed-world setting, which presents limitations when dealing with streaming data. As a solution, incremental learning…

Semi-supervised video action recognition tends to enable deep neural networks to achieve remarkable performance even with very limited labeled data. However, existing methods are mainly transferred from current image-based methods (e.g.,…

Recent advances in AI-generated content (AIGC) have led to the emergence of powerful text-to-video generation models. Despite these successes, evaluating the quality of AIGC-generated videos remains challenging due to limited…

Prior to the deployment of robotic systems, pre-training the deep-recognition models on all potential visual cases is infeasible in practice. Hence, test-time adaptation (TTA) allows the model to adapt itself to novel environments and…

The integration of deep learning based systems in clinical practice is often impeded by challenges rooted in limited and heterogeneous medical datasets. In addition, the field has increasingly prioritized marginal performance gains on a…

With the increasing global popularity of self-driving cars, there is an immediate need for challenging real-world datasets for benchmarking and training various computer vision tasks such as 3D object detection. Existing datasets either…

In the past years, connectivity has been introduced in automotive production series, enabling vehicles as highly mobile Internet of Things sensors and participants. The Horizon 2020 research project AutoMat addressed this scenario by…

Text-to-image generation models represent the next step of evolution in image synthesis, offering a natural way to achieve flexible yet fine-grained control over the result. One emerging area of research is the fast adaptation of large…