Related papers: Causal Scene BERT: Improving object detection by s…
Recent advancements in computer graphics technology allow more realistic ren-dering of car driving environments. They have enabled self-driving car simulators such as DeepGTA-V and CARLA (Car Learning to Act) to generate large amounts of…
We describe basic ideas underlying research to build and understand artificially intelligent systems: from symbolic approaches via statistical learning to interventional models relying on concepts of causality. Some of the hard open…
Autonomous robots are required to reason about the behaviour of dynamic agents in their environment. The creation of models to describe these relationships is typically accomplished through the application of causal discovery techniques.…
Causal representation learning aims to unveil latent high-level causal representations from observed low-level data. One of its primary tasks is to provide reliable assurance of identifying these latent causal models, known as…
Accurately and promptly predicting accidents among surrounding traffic agents from camera footage is crucial for the safety of autonomous vehicles (AVs). This task presents substantial challenges stemming from the unpredictable nature of…
Causal networks are widely used in many fields to model the complex relationships between variables. A recent approach has sought to construct causal networks by leveraging the wisdom of crowds through the collective participation of…
Image caption generation is one of the most challenging problems at the intersection of vision and language domains. In this work, we propose a realistic captioning task where the input scenes may incorporate visual objects with no…
Perception systems, especially cameras, are the eyes of automated driving systems. Ensuring that they function reliably and robustly is therefore an important building block in the automation of vehicles. There are various approaches to…
Causal discovery aims to uncover cause-and-effect relationships encoded in causal graphs by leveraging observational, interventional data, or their combination. The majority of existing causal discovery methods are developed assuming…
In this paper, we present a method for detecting objects of interest, including cars, humans, and fire, in aerial images captured by unmanned aerial vehicles (UAVs) usually during vegetation fires. To achieve this, we use artificial neural…
Unsupervised semantic segmentation aims to achieve high-quality semantic grouping without human-labeled annotations. With the advent of self-supervised pre-training, various frameworks utilize the pre-trained features to train prediction…
Image classification models often learn to predict a class based on irrelevant co-occurrences between input features and an output class in training data. We call the unwanted correlations "data biases," and the visual features causing data…
Video-based computer vision tasks can benefit from estimation of the salient regions and interactions between those regions. Traditionally, this has been done by identifying the object regions in the images by utilizing pre-trained models…
Causal representation learning seeks to recover latent factors that generate observational data through a mixing function. Needing assumptions on latent structures or relationships to achieve identifiability in general, prior works often…
Most neural models of causality assume static causal graphs, failing to capture the dynamic and sparse nature of physical interactions where causal relationships emerge and dissolve over time. We introduce the Causal Process Framework and…
We provide explicit, finite-sample guarantees for learning causal representations from data with a sublinear number of environments. Causal representation learning seeks to provide a rigourous foundation for the general representation…
Recognition of the surrounding environment using a camera is an important technology in Advanced Driver-Assistance Systems and Autonomous Driving, and recognition technology is often solved by machine learning approaches such as deep…
The ability to perform causal and counterfactual reasoning are central properties of human intelligence. Decision-making systems that can perform these types of reasoning have the potential to be more generalizable and interpretable.…
Unconditional scene inference and generation are challenging to learn jointly with a single compositional model. Despite encouraging progress on models that extract object-centric representations (''slots'') from images, unconditional…
UAV based surveillance is gaining much interest worldwide due to its extensive applications in monitoring wildlife, urban planning, disaster management, campus security, etc. These videos are analyzed for strange/odd/anomalous patterns…