853 citations
- Sorbonne UniversitéFR398 papers
- Centre National de la Recherche ScientifiqueFR380 papers
- Université Paris CitéFR136 papers
- Université Pierre-et-Marie-CurieFR97 papers
- University of EdinburghGB89 papers
- Institut national de recherche en sciences et technologies du numériqueFR85 papers
- Université Paris-SaclayFR67 papers
- University of OxfordGB54 papers
- École PolytechniqueFR50 papers
- Sorbonne Paris CitéFR48 papers
- Massachusetts Institute of TechnologyUS45 papers
- Universidade Federal do Rio de JaneiroBR45 papers
18 papers · 1 filter
Leveraging Vision-Language Models to Detect Attention in Educational Videos
Gabriel Becquet, Sébastien Lallé, Vanda Luengo +1
Educational videos are a cornerstone of remote and blended learning. However, learners' fluctuating attention remains a significant barrier to effective information retention. Prio…
Interpret, prune and distill Donut : towards lightweight VLMs for VQA on document
Adnan Ben Mansour, Ayoub Karine, David Naccache
Recent advances in Visually-rich Document Understanding rely on large Vision-Language Models like Donut, which perform document-level Visual Question Answering without Optical Char…
EDNet: Edge-Optimized Small Target Detection in UAV Imagery -- Faster Context Attention, Better Feature Fusion, and Hardware Acceleration
Zhifan Song, Yuan Zhang, Abd Al Rahman M. Abu Ebayyeh
Detecting small targets in drone imagery is challenging due to low resolution, complex backgrounds, and dynamic scenes. We propose EDNet, a novel edge-target detection framework bu…
Can SAR improve RSVQA performance?
Lucrezia Tosato, Sylvain Lobry, Flora Weissgerber +1
Remote sensing visual question answering (RSVQA) has been involved in several research in recent years, leading to an increase in new methods. RSVQA automatically extracts informat…
I2CKD : Intra- and Inter-Class Knowledge Distillation for Semantic Segmentation
Ayoub Karine, Thibault Napoléon, Maher Jridi
This paper proposes a new knowledge distillation method tailored for image semantic segmentation, termed Intra- and Inter-Class Knowledge Distillation (I2CKD). The focus of this me…
Optimising Graph Representation for Hardware Implementation of Graph Convolutional Networks for Event-based Vision
Kamil Jeziorek, Piotr Wzorek, Krzysztof Blachut +2
Event-based vision is an emerging research field involving processing data generated by Dynamic Vision Sensors (neuromorphic cameras). One of the latest proposals in this area are…