Related papers: MineObserver 2.0: A Deep Learning & In-Game Framew…
MirBot is a collaborative application for smartphones that allows users to perform object recognition. This app can be used to take a photograph of an object, select the region of interest and obtain the most likely class (dog, chair, etc.)…
The growing realism of AI-generated images produced by recent GAN and diffusion models has intensified concerns over the reliability of visual media. Yet, despite notable progress in deepfake detection, current forensic systems degrade…
High-dimensional observations and complex real-world dynamics present major challenges in reinforcement learning for both function approximation and exploration. We address both of these challenges with two complementary techniques: First,…
Humans naturally decompose their environment into entities at the appropriate level of abstraction to act in the world. Allowing machine learning algorithms to derive this decomposition in an unsupervised way has become an important line of…
We introduce a novel framework for evaluating multimodal deep learning models with respect to their language understanding and generalization abilities. In this approach, artificial data is automatically generated according to the…
Retrieving tracked-vehicles by natural language descriptions plays a critical role in smart city construction. It aims to find the best match for the given texts from a set of tracked vehicles in surveillance videos. Existing works…
This paper presents a framework for the analysis of changes in visual streams: ordered sequences of images, possibly separated by significant time gaps. We propose a new approach to incorporating unlabeled data into training to generate…
With the advent of state-of-the-art machine learning and deep learning technologies, several industries are moving towards the field. Applications of such technologies are highly diverse ranging from natural language processing to computer…
We propose a method to infer a dense depth map from a single image, its calibration, and the associated sparse point cloud. In order to leverage existing models (teachers) that produce putative depth maps, we propose an adaptive knowledge…
With growing concerns over image authenticity and digital safety, the field of AI-generated image (AIGI) detection has progressed rapidly. Yet, most AIGI detectors still struggle under real-world degradations, particularly motion blur,…
We present Word2Minecraft, a system that leverages large language models to generate playable game levels in Minecraft based on structured stories. The system transforms narrative elements-such as protagonist goals, antagonist challenges,…
Understanding the mechanisms behind decisions taken by large foundation models in sequential decision making tasks is critical to ensuring that such systems operate transparently and safely. In this work, we perform exploratory analysis on…
Deep Q-Learning has been successfully applied to a wide variety of tasks in the past several years. However, the architecture of the vanilla Deep Q-Network is not suited to deal with partially observable environments such as 3D video games.…
Recent advances in open-vocabulary object detection models will enable Automatic Target Recognition systems to be sustainable and repurposed by non-technical end-users for a variety of applications or missions. New, and potentially nuanced,…
When performing complex tasks, humans naturally reason at multiple temporal and spatial resolutions simultaneously. We contend that for an artificially intelligent agent to effectively model human teammates, i.e., demonstrate computational…
Understanding and analyzing video actions are essential for producing insightful and contextualized descriptions, especially for video-based applications like intelligent monitoring and autonomous systems. The proposed work introduces a…
To widen their accessibility and increase their utility, intelligent agents must be able to learn complex behaviors as specified by (non-expert) human users. Moreover, they will need to learn these behaviors within a reasonable amount of…
Many ecological questions center on complex phenomena, such as species interactions, behaviors, phenology, and responses to disturbance, that are inherently difficult to observe and sparsely documented. Community science platforms such as…
Object detectors often experience a drop in performance when new environmental conditions are insufficiently represented in the training data. This paper studies how to automatically fine-tune a pre-existing object detector while exploring…
Many users struggle to notice when a more efficient workflow exists in feature-rich tools like Excel. Existing AI assistants offer help only after users describe their goals or problems, which can be effortful and imprecise. We present…