Related papers: From Photo Streams to Evolving Situations
State-of-the-art approaches for image captioning require supervised training data consisting of captions with paired image data. These methods are typically unable to use unsupervised data such as textual data with no corresponding images,…
While deep learning surpasses human-level performance in narrow and specific vision tasks, it is fragile and over-confident in classification. For example, minor transformations in perspective, illumination, or object deformation in the…
Reasoning about images/objects and their hierarchical interactions is a key concept for the next generation of computer vision approaches. Here we present a new framework to deal with it through a visual hierarchical context-based…
A common challenge in the natural sciences is to disentangle distinct, unknown sources from observations. Examples of this source separation task include deblending galaxies in a crowded field, distinguishing the activity of individual…
Extracting information related to weather and visual conditions at a given time and space is indispensable for scene awareness, which strongly impacts our behaviours, from simply walking in a city to riding a bike, driving a car, or…
Visual object tracking under challenging conditions of motion and light can be hindered by the capabilities of conventional cameras, prone to producing images with motion blur. Event cameras are novel sensors suited to robustly perform…
Finding and localizing the conceptual changes in two scenes in terms of the presence or removal of objects in two images belonging to the same scene at different times in special care applications is of great significance. This is mainly…
Understanding a scene by decoding the visual relationships depicted in an image has been a long studied problem. While the recent advances in deep learning and the usage of deep neural networks have achieved near human accuracy on many…
Real-time video surveillance has become a crucial technology for smart cities, made possible through the large-scale deployment of mobile and fixed video cameras. In this paper, we propose situation-aware streaming, for real-time…
Real world learning scenarios involve a nonstationary distribution of classes with sequential dependencies among the samples, in contrast to the standard machine learning formulation of drawing samples independently from a fixed, typically…
One of the key challenges of performing label prediction over a data stream concerns with the emergence of instances belonging to unobserved class labels over time. Previously, this problem has been addressed by detecting such instances and…
Despite Graph neural networks' significant performance gain over many classic techniques in various graph-related downstream tasks, their successes are restricted in shallow models due to over-smoothness and the difficulties of…
Graph-based semi-supervised learning usually involves two separate stages, constructing an affinity graph and then propagating labels for transductive inference on the graph. It is suboptimal to solve them independently, as the correlation…
In many real-life tasks of application of supervised learning approaches, all the training data are not available at the same time. The examples are lifelong image classification or recognition of environmental objects during interaction of…
Due to the high cost of manual annotation, learning directly from the web has attracted broad attention. One issue that limits their performance is the problem of visual polysemy. To address this issue, we present an adaptive multi-model…
Current robot platforms are being employed to collaborate with humans in a wide range of domestic and industrial tasks. These environments require autonomous systems that are able to classify and communicate anomalous situations such as…
In this paper a new formulation of event recognition task is examined: it is required to predict event categories in a gallery of images, for which albums (groups of photos corresponding to a single event) are unknown. We propose the novel…
In this paper we propose a novel learning framework called Supervised and Weakly Supervised Learning where the goal is to learn simultaneously from weakly and strongly labeled data. Strongly labeled data can be simply understood as fully…
Scene classification is a fundamental perception task for environmental understanding in today's robotics. In this paper, we have attempted to exploit the use of popular machine learning technique of deep learning to enhance scene…
Image super-resolution is a fundamentally ill-posed problem because multiple valid high-resolution images exist for one low-resolution image. Super-resolution methods based on diffusion probabilistic models can deal with the ill-posed…