Related papers: CaMiT: A Time-Aware Car Model Dataset for Classifi…

Recent advancements in video generation have substantially improved visual quality and temporal coherence, making these models increasingly appealing for applications such as autonomous driving, particularly in the context of driving…

Autonomous driving has received a lot of attention in the automotive industry and is often seen as the future of transportation. Passenger vehicles equipped with a wide array of sensors (e.g., cameras, front-facing radars, LiDARs, and IMUs)…

Videos capture events that typically contain multiple sequential, and simultaneous, actions even in the span of only a few seconds. However, most large-scale datasets built to train models for action recognition in video only provide a…

We propose the use of latent space generative world models to address the covariate shift problem in autonomous driving. A world model is a neural network capable of predicting an agent's next state given past states and actions. By…

Recent work on time-series models has leveraged self-supervised training to learn meaningful features and patterns in order to improve performance on downstream tasks and generalize to unseen modalities. While these pretraining methods have…

Understanding occupant-vehicle interactions by modeling control transitions is important to ensure safe approaches to passenger vehicle automation. Models which contain contextual, semantically meaningful representations of driver states…

Quality assessment and aesthetics assessment aim to evaluate the perceived quality and aesthetics of visual content. Current learning-based methods suffer greatly from the scarcity of labeled data and usually perform sub-optimally in terms…

Continual learning requires a model to adapt to ongoing changes in the data distribution, and often to the set of tasks to be performed. It is rare, however, that the data and task changes are completely unpredictable. Given a description…

The ubiquity of time series data creates a strong demand for general-purpose foundation models, yet developing them for classification remains a significant challenge, largely due to the high cost of labeled data. Foundation models capable…

Time introduces fundamental challenges in model development and deployment: models are usually trained on historical data while deployed on future data where semantic distributions and domain knowledge may evolve. Unfortunately, existing…

For the foreseeble future, human beings will likely remain an integral part of the driving task, monitoring the AI system as it performs anywhere from just over 0% to just under 100% of the driving. The governing objectives of the MIT…

Recent advances in training vision-language models have demonstrated unprecedented robustness and transfer learning effectiveness; however, standard computer vision datasets are image-only, and therefore not well adapted to such training…

Reliable anticipation of traffic accidents is essential for advancing autonomous driving systems. However, this objective is limited by two fundamental challenges: the scarcity of diverse, high-quality training data and the frequent absence…

Real-world vision models in dynamic environments face rapid shifts in domain distributions, leading to decreased recognition performance. Using unlabeled test data, continuous test-time adaptation (CTTA) directly adjusts a pre-trained…

Deep models, e.g., CNNs and Vision Transformers, have achieved impressive achievements in many vision tasks in the closed world. However, novel classes emerge from time to time in our ever-changing world, requiring a learning system to…

Understanding temporal information and how the visual world changes over time is a fundamental ability of intelligent systems. In video understanding, temporal information is at the core of many current challenges, including compression,…

The need for simulated data in autonomous driving applications has become increasingly important, both for validation of pretrained models and for training new models. In order for these models to generalize to real-world applications, it…

Recently, images that distort or fabricate facts using generative models have become a social concern. To cope with continuous evolution of generative artificial intelligence (AI) models, model attribution (MA) is necessary beyond just…

Dynamic Item Response Models extend the standard Item Response Theory (IRT) to capture temporal dynamics in learner ability. While these models have the potential to allow instructional systems to actively monitor the evolution of learner…

The success of deep learning in computer vision is based on availability of large annotated datasets. To lower the need for hand labeled images, virtually rendered 3D worlds have recently gained popularity. Creating realistic 3D content is…