Stage Human-Object Interaction benchmarking-Saclay-H/F

Summary: This internship focuses on improving evaluation protocols for human-object interaction tasks using LLMs and VLMs. The candidate will conduct a state-of-the-art review, propose bias-correction pipelines, and develop a new benchmark to evaluate current methods.

### Sujet de stage

The interpretation of human interactions in images or videos has significantly improved with the emergence of Large Language Models (LLMs) and Vision-Language Models (VLMs). However, these large models, whether used directly or distilled into specialized models, still have significant limitations, particularly in accurately attributing interactions to the correct person in dense scenes and discriminating actions in the presence of objects.

Evaluation protocols and databases for this task do not always accurately reflect the true capabilities of the methods due to issues such as annotation imprecision or overly rigid semantic metrics. This internship tackles this problem.

### Description de l'offre

Context

The interpretation of human interactions in images or videos has significantly improved with the emergence of Large Language Models (LLMs) and Vision-Language Models (VLMs). However, these large models, whether used directly or distilled into specialized models, still have significant limitations, particularly in accurately attributing interactions to the correct person in dense scenes and discriminating actions in the presence of objects.

Evaluation protocols and databases for this task do not always accurately reflect the true capabilities of the methods due to issues such as annotation imprecision or overly rigid semantic metrics.

What do we expect from you?

To address these problems, the internship will focus on the following objectives:

• Conduct a state-of-the-art review of existing databases and analyze their biases (e.g., precision of detection boxes).
• Propose a semi-automatic pipeline for correcting these biases.
• Identify the biases and gaps in the metrics commonly used in the state-of-the-art.
• Propose a new benchmark, addressing various application domains.
• Evaluate the main state-of-the-art approaches on this benchmark.
• Write a publication about this benchmark.

#*Cea List*

### Profil du candidat

Profile

• Students in their 4th or 5th year of studies (M1, M2 or gap year)
• Computer vision skills
• Machine learning skills (deep learning, perception models, generative AI…)
• Python proficiency in a deep learning framework (especially TensorFlow or PyTorch)