AIConfPaper
← Search

Mariella Dimiccoli

6 accepted papers

2026

BEA-GS: BEyond RAdiance Supervision in 3DGS for Precise Object Extraction

Alessio Mazzucchelli, Maria Naranjo-Almeida, Jorge Bustos-Sanchez, Mariella Dimiccoli, Francesc Moreno-Noguer, Jordi Sanchez-Riera +1
CVPR 2026

Most Gaussian Splatting techniques that provide a 3D semantic representation of the scene don't optimize the underlying 3D geometry of the scene. This makes object-level editing or asset extraction challenging. Recent methods, like COBGS, Trace3D, and ObjectGS, acknowledge this limitation and propos

Cited by 0Source ↗Scholar ↗
2025

CLOT: Closed Loop Optimal Transport for Unsupervised Action Segmentation

Elena Bueno-Benito, Mariella Dimiccoli
ICCV 2025poster

Unsupervised action segmentation has recently pushed its limits with ASOT, an optimal transport (OT)-based method that simultaneously learns action representations and performs clustering using pseudo-labels. Unlike other OT-based approaches, ASOT makes no assumptions about action ordering and can d…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2024

3M-Transformer: A Multi-Stage Multi-Stream Multimodal Transformer for Embodied Turn-Taking Prediction

Mehdi Fatan, Emanuele Mincato, Dimitra Pintzou, Mariella Dimiccoli
ICASSP 2024accepted

Predicting turn-taking in multiparty conversations has many practical applications in human-computer/robot interaction. However, the complexity of human communication makes it a challenging task. Recent advances have shown that synchronous multi-perspective egocentric data can significantly improve…

Cited by 0Source ↗Scholar ↗
2022

Recognizing object surface material from impact sounds for robot manipulation

Mariella Dimiccoli, Shubhan Patni, Matej Hoffmann, Francesc Moreno-Noguer
IROS 2022poster

We investigated the use of impact sounds generated during exploratory behaviors in a robotic manipulation setup as cues for predicting object surface material and for recognizing individual objects. We collected and make available the YCB-impact sounds dataset which includes over 3,000 impact sounds…

Cited by 12Source ↗Scholar ↗
2021

Graph Constrained Data Representation Learning for Human Motion Segmentation

Mariella Dimiccoli, Lluís Garrido, Guillem Rodriguez-Corominas, Herwig Wendt
ICCV 2021poster

Recently, transfer subspace learning based approaches have shown to be a valid alternative to unsupervised subspace clustering and temporal data clustering for human motion segmentation (HMS). These approaches leverage prior knowledge from a source domain to improve clustering performance on a targe…

Cited by 8PDF ↗code ↗Scholar ↗
2021

Learning grounded word meaning representations on similarity graphs

Mariella Dimiccoli, Herwig Wendt, Pau Batlle Franch
EMNLP 2021main

This paper introduces a novel approach to learn visually grounded meaning representations of words as low-dimensional node embeddings on an underlying graph hierarchy. The lower level of the hierarchy models modality-specific word representations, conditioned to another modality, through dedicated b…

Cited by 1Source ↗PDF ↗code ↗Scholar ↗