4 papers
Beyond Anonymous Captions: Grounding Character Identity in Video Captioning and Question Answering
Anas Filali Razzouki, Killian Steunou, Khalil Guetari +3
Linking people's appearance and actions to character identities is essential for understanding video narratives. We present a framework for identity-aware video captioning and pers…
Why Is Video Still So Expensive? A Survey of Inference-Efficiency Mechanisms in Video and Audiovisual LLMs
Killian Steunou, Yannis Tevissen, Mounîm A. El Yacoubi
Video understanding has rapidly evolved toward video large language models (VideoLLMs): systems that couple video representations with pretrained large language models and conditio…
PEEK: Picking Essential frames via Efficient Knowledge distillation
Killian Steunou, Anas Filali Razzouki, Khalil Guetari +2
Video-language models can process only a limited number of frames, making frame selection a key bottleneck for efficient video captioning. Most captioning pipelines still rely on u…
Sparse Representations Improve Adversarial Robustness of Neural Network Classifiers
Killian Steunou, Théo Druilhe, Sigurd Saue
Deep neural networks perform remarkably well on image classification tasks but remain vulnerable to carefully crafted adversarial perturbations. This work revisits linear dimension…