Search Results for author: Alina Marcu

Found 9 papers, 2 papers with code

Maia: A Real-time Non-Verbal Chat for Human-AI Interaction

no code implementations9 Feb 2024 Dragos Costea, Alina Marcu, Cristina Lazar, Marius Leordeanu

Our goal is to track and analyze facial expressions, and other non-verbal cues in real-time, and use this information to build models that can predict and understand human behavior.

Retrieval

Self-supervised novel 2D view synthesis of large-scale scenes with efficient multi-scale voxel carving

no code implementations26 Jun 2023 Alexandra Budisteanu, Dragos Costea, Alina Marcu, Marius Leordeanu

First, we manage to stay anchored in the real 3D world, by introducing an efficient multi-scale voxel carving method, which is able to accommodate significant noises in pose, depth, and illumination variations, while being able to reconstruct the view of the world from drastically different poses at test time.

Novel View Synthesis

Semi-Supervised Learning for Multi-Task Scene Understanding by Neural Graph Consensus

3 code implementations2 Oct 2020 Marius Leordeanu, Mihai Pirvu, Dragos Costea, Alina Marcu, Emil Slusanschi, Rahul Sukthankar

The unsupervised learning process is repeated over several generations, in which each edge becomes a "student" and also part of different ensemble "teachers" for training other students.

Scene Understanding Semantic Segmentation

Semantics through Time: Semi-supervised Segmentation of Aerial Videos with Iterative Label Propagation

2 code implementations2 Oct 2020 Alina Marcu, Vlad Licaret, Dragos Costea, Marius Leordeanu

Motivated by the lack of a large video aerial dataset, we also introduce Ruralscapes, a new dataset with high resolution (4K) images and manually-annotated dense labels every 50 frames - the largest of its kind, to the best of our knowledge.

Clustering Robot Navigation +1

A Multi-Stage Multi-Task Neural Network for Aerial Scene Interpretation and Geolocalization

no code implementations4 Apr 2018 Alina Marcu, Dragos Costea, Emil Slusanschi, Marius Leordeanu

The first stage of our network predicts pixelwise class labels, while the second stage provides a precise location using two branches.

Segmentation Semantic Segmentation

Dual Local-Global Contextual Pathways for Recognition in Aerial Imagery

no code implementations18 May 2016 Alina Marcu, Marius Leordeanu

Our model learns to combine local object appearance as well as information from the larger scene at the same time and in a complementary way, such that together they form a powerful classifier.

Object Recognition Road Segmentation +1

Cannot find the paper you are looking for? You can Submit a new open access paper.