works on

From the 3 of 14 papers with an AI index.

most citedOnline Handwriting Trajectory Reconstruction from Kinematic Sensors using Temporal Convolutional Network

11 citations

14 papers

cs.LG20261 cited

Domain adaptation for handwriting trajectory reconstruction from IMU sensors

Florent Imbert, Romain Tavenard, Yann Soullard +1

The paper proposes a domain adaptation method to create a unified feature representation for reconstructing handwriting trajectories from IMU-equipped digital pens, addressing sign…

cs.CV202611 cited

Online Handwriting Trajectory Reconstruction from Kinematic Sensors using Temporal Convolutional Network

Wassim Swaileh, Florent Imbert, Yann Soullard +2

The paper presents a pipeline that uses sensor data from a digital pen and a temporal convolutional network to reconstruct online handwriting trajectories, aligning differing sampl…

cs.LG20266 cited

Mixture-of-experts for handwriting trajectory reconstruction from IMU sensors

Florent Imbert, Eric Anquetil, Yann Soullard +1

The paper proposes a mixture-of-experts model to reconstruct online handwriting trajectories from IMU-equipped digital pens, handling both touching and hovering phases, and introdu…

eess.IV2026

Discovering shared interpretable operations in image compression autoencoders

Caroline Mazini Rodrigues, Nicolas Keriven, Thomas Maugey

With the increasing adoption of deep learning for applications such as image compression, improvements in the rate-distortion trade-off have been achieved at the cost of increasing…

math.OC2026

Sliced Transport Plans

Eloi Tanguy, Laetitia Chapel, Julie Delon

Since the introduction of the Sliced Wasserstein distance in the literature, its simplicity and efficiency have made it one of the most interesting surrogate for the Wasserstein di…

cs.AI2026

Exploration and Online Transfer with Behavioral Foundation Models

Louis Bagot, Mathieu Lefort, Laëtitia Matignon

Zero-shot Transfer in Reinforcement Learning (RL) aims to train an agent that can generate optimal policies for any reward function, without additional learning at transfer time, w…