Doctoral thesis defense in Computer Science by Ms. Oumaima MOUTIK

Euromed University of Fes (UEMF) is pleased to inform the public of the

doctoral thesis defense in ”Computer Science”

The thesis defense will take place on Saturday October 12, 2024 at 10:00 AM at UEMF 

Location: the Main Hall of the Incubator (LOC001994) 

The thesis will be presented by Ms. Oumaima

MOUTIK Under the theme:

“Supervised and self-supervised deep learning techniques for skeleton-based human action recognition in visual media data”

Abstract 

Artificial Intelligence is revolutionizing video understanding applications, seamlessly integrating into our daily routines. However, thus far, action recognition algorithms are incapable of reasoning about videos as humans do. To this end, our thesis aims to develop action recognition solutions that compare with the current state-of-the-art in accuracy but with reduced time and financial costs.

First, we studied the possibility of improving Human-Object Interaction detection by integrating scene information using a compression technique named Knowledge Distillation. This auxiliary task has demonstrated effectiveness in distinguishing between actions. We then considered the surrounding objects, including their motions, to improve Skeleton-based action recognition. This involved designing a set encompassing object information from RGB modality, which was then consistently integrated into the 3-dimensions skeleton data using a novel early fusion technique.

During our thesis journey, we investigated Self-supervised Learning for Skeleton-based action recognition task, driven by the need to mitigate the high cost associated with human annotations. We proposed a novel Pretext Task, "Questions Form Puzzle," based on statistical operations. This work has provided significant results across well-known Skeleton-based datasets and paved the way for extensive future research. Through these contributions, our thesis advances the field of action recognition, striving for human-like video understanding while substantially reducing computational and annotation resource requirements.

Abstract 

Artificial intelligence is revolutionizing video understanding applications, integrating seamlessly into our daily lives. However, to date, action recognition algorithms are unable to reason about videos as humans do. To this end, our thesis aims to develop action recognition solutions that match the current state of the art in accuracy, but with reduced time and resource costs.

First, we studied the possibility of improving human-object interaction detection by integrating scene information using a compression technique called knowledge distillation. This auxiliary task proved effective in distinguishing actions. We then considered surrounding objects, including their movements, to improve skeleton-based action recognition. This involved designing a set that integrates object information from the RGB modality, which was then coherently integrated into 3-dimensional skeleton data using a new early fusion technique.

During our thesis journey, we explored Self-supervised Learning for skeleton-based action recognition tasks, motivated by the need to reduce the high costs associated with human annotations. We proposed a new pretext task, "Questions Form Puzzle," based on statistical operations. This work yielded significant results on well-known skeleton-based datasets and opened the way for further in-depth research. Through these contributions, our thesis advances the field of action recognition, striving for video understanding comparable to that of humans while significantly reducing computational and annotation resource requirements.

This thesis will be presented before the jury members: