Related papers: ClassiFIM: An Unsupervised Method To Detect Phase …

In this paper, we introduce a novel training method for making any monocular depth network learn absolute scale and estimate metric road-scene depth just from regular training data, i.e., driving videos. We refer to this training framework…

Foundation models (FMs) such as CLIP have demonstrated impressive zero-shot performance across various tasks by leveraging large-scale, unsupervised pre-training. However, they often inherit harmful or unwanted knowledge from noisy…

Deep learning has led to many recent advances in object detection and instance segmentation, among other computer vision tasks. These advancements have led to wide application of deep learning based methods and related methodologies in…

The design of reliable indicators to anticipate critical transitions in complex systems is an im portant task in order to detect a coming sudden regime shift and to take action in order to either prevent it or mitigate its consequences. We…

Masked Image Modeling (MIM) is a technique in self-supervised learning that focuses on acquiring detailed visual representations from unlabeled images by estimating the missing pixels in randomly masked sections. It has proven to be a…

Existing supervised action segmentation methods depend on the quality of frame-wise classification using attention mechanisms or temporal convolutions to capture temporal dependencies. Even boundary detection-based methods primarily depend…

Multivariate time series classification supports applications from wearable sensing to biomedical monitoring and demands models that can capture both short-term patterns and multi-scale temporal dependencies. Despite recent advances,…

To make sense of their surroundings, intelligent systems must transform complex sensory inputs to structured codes that are reduced to task-relevant information such as object category. Biological agents achieve this in a largely autonomous…

Deep neural networks need a big amount of training data, while in the real world there is a scarcity of data available for training purposes. To resolve this issue unsupervised methods are used for training with limited data. In this…

Contrastive Language-Image Pre-training (CLIP) provides a foundation model by integrating natural language into visual concepts, enabling zero-shot recognition on downstream tasks. It is usually expected that satisfactory overall accuracy…

Click-Through Rate (CTR) prediction is a crucial task in recommendation systems, online searches, and advertising platforms, where accurately capturing users' real interests in content is essential for performance. However, existing methods…

Existing Video Frame interpolation (VFI) models tend to suffer from time-to-location ambiguity when trained with video of non-uniform motions, such as accelerating, decelerating, and changing directions, which often yield blurred…

In quantum multi-parameter estimation, the precision of estimating unknown parameters is bounded by the Cramer-Rao bound (CRB), defined via the inverse of the Fisher information matrix (FIM). However, in certain scenarios such as…

We consider the problem of estimating an object's physical properties such as mass, friction, and elasticity directly from video sequences. Such a system identification problem is fundamentally ill-posed due to the loss of information…

Large-scale multi-modal training with image-text pairs imparts strong generalization to CLIP model. Since training on a similar scale for videos is infeasible, recent approaches focus on the effective transfer of image-based CLIP to the…

Foundation Vision-Language Models (VLMs) like CLIP exhibit strong generalization capabilities due to large-scale pretraining on diverse image-text pairs. However, their performance often degrades when applied to target datasets with…

Decisions made by convolutional neural networks(CNN) can be understood and explained by visualizing discriminative regions on images. To this end, Class Activation Map (CAM) based methods were proposed as powerful interpretation tools,…

Standard approaches for uncertainty quantification in deep learning and physics-informed learning have persistent limitations. Indicatively, strong assumptions regarding the data likelihood are required, the performance highly depends on…

This paper tackles the challenging problem of estimating the intensity of Facial Action Units with few labeled images. Contrary to previous works, our method does not require to manually select key frames, and produces state-of-the-art…

State estimation or filtering serves as a fundamental task to enable intelligent decision-making in applications such as autonomous vehicles, robotics, healthcare monitoring, smart grids, intelligent transportation, and predictive…