Related papers: Are current long-term video understanding datasets…
Action recognition in videos is a challenging task due to the complexity of the spatio-temporal patterns to model and the difficulty to acquire and learn on large quantities of video data. Deep learning, although a breakthrough for image…
Activity recognition from long unstructured egocentric photo-streams has several applications in assistive technology such as health monitoring and frailty detection, just to name a few. However, one of its main technical challenges is to…
Long-form egocentric video understanding provides rich contextual information and unique insights into long-term human behaviors, holding significant potential for applications in embodied intelligence, long-term activity analysis, and…
Vision-language-action (VLA) models provide a promising foundation for general-purpose robotics. However, their successful deployment in real-world scenarios requires the ability to continually acquire new skills while retaining previously…
In many real-world sequential decision making problems, the number of available actions (decisions) can vary over time. While problems like catastrophic forgetting, changing transition dynamics, changing rewards functions, etc. have been…
In this paper, we propose to improve the traditional use of RNNs by employing a many to many model for video classification. We analyze the importance of modeling spatial layout and temporal encoding for daily living action recognition.…
Video understanding is one of the most challenging topics in computer vision. In this paper, a four-stage video understanding pipeline is presented to simultaneously recognize all atomic actions and the single on-going activity in a video.…
Body-worn cameras are now commonly used for logging daily life, sports, and law enforcement activities, creating a large volume of archived footage. This paper studies the problem of classifying frames of footage according to the activity…
In video action recognition, transformers consistently reach state-of-the-art accuracy. However, many models are too heavyweight for the average researcher with limited hardware resources. In this work, we explore the limitations of video…
A dominant paradigm for learning-based approaches in computer vision is training generic models, such as ResNet for image recognition, or I3D for video understanding, on large datasets and allowing them to discover the optimal…
While many action recognition datasets consist of collections of brief, trimmed videos each containing a relevant action, videos in the real-world (e.g., on YouTube) exhibit very different properties: they are often several minutes long,…
Research on video activity detection has primarily focused on identifying well-defined human activities in short video segments. The majority of the research on video activity recognition is focused on the development of large parameter…
Foundation models (FMs) are large neural networks trained on broad datasets, excelling in downstream tasks with minimal fine-tuning. Human activity recognition in video has advanced with FMs, driven by competition among different…
We propose an action parsing algorithm to parse a video sequence containing an unknown number of actions into its action segments. We argue that context information, particularly the temporal information about other actions in the video…
Spatio-temporal action detection is an important and challenging problem in video understanding. The existing action detection benchmarks are limited in aspects of small numbers of instances in a trimmed video or low-level atomic actions.…
We study the task of robust feature representations, aiming to generalize well on multiple datasets for action recognition. We build our method on Transformers for its efficacy. Although we have witnessed great progress for video action…
Deep learning algorithms have pushed the boundaries of computer vision research and have depicted commendable performance in a variety of applications. However, training a robust deep neural network necessitates a large amount of labeled…
We propose a new long-term tracking performance evaluation methodology and present a new challenging dataset of carefully selected sequences with many target disappearances. We perform an extensive evaluation of six long-term and nine…
Action recognition is an open and challenging problem in computer vision. While current state-of-the-art models offer excellent recognition results, their computational expense limits their impact for many real-world applications. In this…
Humans share a strong tendency to memorize/forget some of the visual information they encounter. This paper focuses on providing computational models for the prediction of the intrinsic memorability of visual content. To address this new…