2 citations · 4 across the 11 of their papers we have counts for
12 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…
Frame Sampling Strategies Matter: A Benchmark for small vision language models
Marija Brkic, Anas Filali Razzouki, Yannis Tevissen +2
Comparing vision language models on videos is particularly complex, as the performances is jointly determined by the model's visual representation capacity and the frame-sampling s…
Disability Representations: Finding Biases in Automatic Image Generation
Yannis Tevissen
Recent advancements in image generation technology have enabled widespread access to AI-generated imagery, prominently used in advertising, entertainment, and progressively in ever…
Towards Retrieval Augmented Generation over Large Video Libraries
Yannis Tevissen, Khalil Guetari, Frédéric Petitpont
Video content creators need efficient tools to repurpose content, a task that often requires complex manual or automated searches. Crafting a new video from large video libraries r…
Multimodal Chaptering for Long-Form TV Newscast Video
Khalil Guetari, Yannis Tevissen, Frédéric Petitpont
We propose a novel approach for automatic chaptering of TV newscast videos, addressing the challenge of structuring and organizing large collections of unsegmented broadcast conten…
Inserting Faces inside Captions: Image Captioning with Attention Guided Merging
Yannis Tevissen, Khalil Guetari, Marine Tassel +2
Image captioning models are widely used to describe recent and archived pictures with the objective of improving their accessibility and retrieval. Yet, these approaches tend to be…
Privacy Preserving Personal Assistant with On-Device Diarization and Spoken Dialogue System for Home and Beyond
Gérard Chollet, Hugues Sansen, Yannis Tevissen +4
In the age of personal voice assistants, the question of privacy arises. These digital companions often lack memory of past interactions, while relying heavily on the internet for…
Home monitoring for frailty detection through sound and speaker diarization analysis
Yannis Tevissen, Dan Istrate, Vincent Zalc +4
As the French, European and worldwide populations are aging, there is a strong interest for new systems that guarantee a reliable and privacy preserving home monitoring for frailty…
Towards Measuring and Scoring Speaker Diarization Fairness
Yannis Tevissen, Jérôme Boudy, Gérard Chollet +1
Speaker diarization, or the task of finding "who spoke and when", is now used in almost every speech processing application. Nevertheless, its fairness has not yet been evaluated b…
The Newsbridge -Telecom SudParis VoxCeleb Speaker Recognition Challenge 2022 System Description
Yannis Tevissen, Jérôme Boudy, Frédéric Petitpont
We describe the system used by our team for the VoxCeleb Speaker Recognition Challenge 2022 (VoxSRC 2022) in the speaker diarization track. Our solution was designed around a new c…