24 citations · 45 across the 13 of their papers we have counts for
14 papers · 1 filter
Learning to Understand Body Language from Flight through Robust 3D Avatar Placing
Dragos Costea, Alina Marcu, Cristina Lazar +1
Perceiving human motion and intent at long range is a prerequisite for socially intelligent aerial robots, yet the data to learn it barely exists. We introduce Drones2BodyLanguage,…
Real-time body pose non-verbal communication with a consistency-based reliability measure
Alina Marcu, Dragos Costea, Cristina Lazar +1
Body movement communicates intent at distances and in conditions where neither the face, nor speech can be captured. We study the recognition of communicative intent from 2D body p…
Non-verbal Real-time Human-AI Interaction in Constrained Robotic Environments
Dragos Costea, Alina Marcu, Cristina Lazar +1
We study the ongoing debate regarding the statistical fidelity of AI-generated data compared to human-generated data in the context of non-verbal communication using full body moti…
A self-supervised cyclic neural-analytic approach for novel view synthesis and 3D reconstruction
Dragos Costea, Alina Marcu, Marius Leordeanu
Generating novel views from recorded videos is crucial for enabling autonomous UAV navigation. Recent advancements in neural rendering have facilitated the rapid development of met…
Maia: A Real-time Non-Verbal Chat for Human-AI Interaction
Dragos Costea, Alina Marcu, Cristina Lazar +1
Modeling face-to-face communication in computer vision, which focuses on recognizing and analyzing nonverbal cues and behaviors during interactions, serves as the foundation for ou…
Multi-Task Hypergraphs for Semi-supervised Learning using Earth Observations
Mihai Pirvu, Alina Marcu, Alexandra Dobrescu +2
There are many ways of interpreting the world and they are highly interdependent. We exploit such complex dependencies and introduce a powerful multi-task hypergraph, in which ever…
Self-supervised Hypergraphs for Learning Multiple World Interpretations
Alina Marcu, Mihai Pirvu, Dragos Costea +5
We present a method for learning multiple scene representations given a small labeled set, by exploiting the relationships between such representations in the form of a multi-task…
Self-supervised novel 2D view synthesis of large-scale scenes with efficient multi-scale voxel carving
Alexandra Budisteanu, Dragos Costea, Alina Marcu +1
The task of generating novel views of real scenes is increasingly important nowadays when AI models become able to create realistic new worlds. In many practical applications, it i…
Semantics through Time: Semi-supervised Segmentation of Aerial Videos with Iterative Label Propagation
Alina Marcu, Vlad Licaret, Dragos Costea +1
Semantic segmentation is a crucial task for robot navigation and safety. However, current supervised methods require a large amount of pixelwise annotations to yield accurate resul…
Semi-Supervised Learning for Multi-Task Scene Understanding by Neural Graph Consensus
Marius Leordeanu, Mihai Pirvu, Dragos Costea +3
We address the challenging problem of semi-supervised learning in the context of multiple visual interpretations of the world by finding consensus in a graph of neural networks. Ea…
Towards Automatic Annotation for Semantic Segmentation in Drone Videos
Alina Marcu, Dragos Costea, Vlad Licaret +1
Semantic segmentation is a crucial task for robot navigation and safety. However, it requires huge amounts of pixelwise annotations to yield accurate results. While recent progress…
A Multi-Stage Multi-Task Neural Network for Aerial Scene Interpretation and Geolocalization
Alina Marcu, Dragos Costea, Emil Slusanschi +1
Semantic segmentation and vision-based geolocalization in aerial images are challenging tasks in computer vision. Due to the advent of deep convolutional nets and the availability…
A Local-Global Approach to Semantic Segmentation in Aerial Images
Alina Elena Marcu
Aerial images are often taken under poor lighting conditions and contain low resolution objects, many times occluded by other objects. In this domain, visual context could be of gr…
Dual Local-Global Contextual Pathways for Recognition in Aerial Imagery
Alina Marcu, Marius Leordeanu
Visual context is important in object recognition and it is still an open problem in computer vision. Along with the advent of deep convolutional neural networks (CNN), using conte…