Description du poste
Domaine
Mathématiques, information scientifique, logiciel
Contrat
Stage
Intitulé de l'offre
Stage Human-Object Interaction benchmarking-Saclay-H/F
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.
Durée du contrat (en mois)
6 mois
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
Moyens / Méthodes / Logiciels
AI, Deep Neural Network, Computer Vision, Human behavior analysis
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)
Localisation du poste
Site
Saclay
Localisation du poste
France, Ile-de-France, Essonne (91)
Ville
Saclay
Critères candidat
Diplôme préparé
Bac+5 - Master 2
Formation recommandée
AI, Deep Learning, Computer Vision
Possibilité de poursuite en thèse
Oui
Demandeur
Disponibilité du poste
01/02/2027
Domaine
Mathématiques, information scientifique, logiciel
Contrat
Stage
Intitulé de l'offre
Stage Human-Object Interaction benchmarking-Saclay-H/F
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.
Durée du contrat (en mois)
6 mois
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
Moyens / Méthodes / Logiciels
AI, Deep Neural Network, Computer Vision, Human behavior analysis
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)
Localisation du poste
Site
Saclay
Localisation du poste
France, Ile-de-France, Essonne (91)
Ville
Saclay
Critères candidat
Diplôme préparé
Bac+5 - Master 2
Formation recommandée
AI, Deep Learning, Computer Vision
Possibilité de poursuite en thèse
Oui
Demandeur
Disponibilité du poste
01/02/2027
