in2IN: Leveraging individual Information to Generate Human INteractions

We introduced in2IN to generate more realistic human interactions leveraging individual information. And we also introduce DualMDM a model compostion technique that allows to combien interactions models with individual priors ton increase the diversity and controllability.

Text-driven multi-human motion generation

In this thesis, we introduce a novel Diffusion Model incorporating a Transformer-based architecture. This model is conditioned using textual descriptions of both the motion interactions and the individual motions within these interactions. By focusing on the individual components of the interaction, our method achieves more precise conditioning in the generation of these specific motions. Concurrently, the textual descriptions of the overall interaction enable our model to effectively capture the interplay between individual motions.

Poseidon: A data augmentation tool for small object detection datasets in maritime environments

We present POSEIDON, a data augmentation tool specifically designed for object detection datasets. Our approach generates new training samples by combining objects and samples from the original training set while utilizing the image metadata to make informed decisions. We evaluate our method using YOLOv5 and YOLOv8 and demonstrate its superiority over other balancing techniques.

Small Vessel Detection in Changing Seaborne Environments Using Anchor-Free Detectors on Aerial Images

We propose an anchor-free object detector to accurately locate small vessels in changing seaborne environments for search and rescue operations using aerial images. Using the YOLOX architecture, we have achieved high accuracy and real-time inference on the SeaDronesSee dataset. In order to face the high imbalance present in the dataset, the variations of the dataset and a weighted loss have been proposed and implemented.

Small Vessel Detection in Seaborne Environments using Deep Learning Techniques

In this thesis, we propose the use of deep learning based object detectors to autonomously locate small vessels in changing seaborne environments for search and rescue operations using aerial images. After extensive research on actual approaches and available datasets, using the YOLOX architecture we have achieved high accuracy and real-time inference on the SeaDronesSee dataset.