146 citations · 339 across the 30 of their papers we have counts for
42 papers
D-CLOT: Double Closed Loop Optimal Transport for Unsupervised Action Segmentation
Elena Bueno-Benito, Mariella Dimiccoli
Optimal transport (OT) has emerged as an effective framework for unsupervised action segmentation. Yet, in existing OT-based methods, the latent action prototypes that define the O…
BEA-GS: BEyond RAdiance Supervision in 3DGS for Precise Object Extraction
Alessio Mazzucchelli, Maria Naranjo-Almeida, Jorge Bustos-Sanchez +4
Most Gaussian Splatting techniques that provide a 3D semantic representation of the scene do not optimize the underlying 3D geometry, making object-level editing or asset extractio…
CLOT: Closed Loop Optimal Transport for Unsupervised Action Segmentation
Elena Bueno-Benito, Mariella Dimiccoli
Unsupervised action segmentation has recently pushed its limits with ASOT, an optimal transport (OT)-based method that simultaneously learns action representations and performs clu…
How Well Do Vision-Language Models Understand Movies?
Emmanouil Zaranis, António Farinhas, Saul Santos +28
Vision-language models (VLMs) can increasingly handle extended contexts and answer questions about long videos--but can they understand the narrative structure of movies as humans…
Temporal Context Consistency Above All: Enhancing Long-Term Anticipation by Learning and Enforcing Temporal Constraints
Alberto Maté, Mariella Dimiccoli
This paper proposes a method for long-term action anticipation (LTA), the task of predicting action labels and their duration in a video given the observation of an initial untrimm…
2by2: Weakly-Supervised Learning for Global Action Segmentation
Elena Bueno-Benito, Mariella Dimiccoli
This paper presents a simple yet effective approach for the poorly investigated task of global action segmentation, aiming at grouping frames capturing the same action across video…
3M-TRANSFORMER: A Multi-Stage Multi-Stream Multimodal Transformer for Embodied Turn-Taking Prediction
Mehdi Fatan, Emanuele Mincato, Dimitra Pintzou +1
Predicting turn-taking in multiparty conversations has many practical applications in human-computer/robot interaction. However, the complexity of human communication makes it a ch…
Leveraging triplet loss for unsupervised action segmentation
E. Bueno-Benito, B. Tura, M. Dimiccoli
In this paper, we propose a novel fully unsupervised framework that learns action representations suitable for the action segmentation task from the single input video itself, with…
Debiased-CAM to mitigate systematic error with faithful visual explanations of machine learning
Wencan Zhang, Mariella Dimiccoli, Brian Y. Lim
Model explanations such as saliency maps can improve user trust in AI by highlighting important features for a prediction. However, these become distorted and misleading when expla…
Enhancing Egocentric 3D Pose Estimation with Third Person Views
Ameya Dhamanaskar, Mariella Dimiccoli, Enric Corona +2
In this paper, we propose a novel approach to enhance the 3D body pose estimation of a person computed from videos captured from a single wearable camera. The key idea is to levera…
Learning grounded word meaning representations on similarity graphs
Mariella Dimiccoli, Herwig Wendt, Pau Batlle
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 le…
Graph Constrained Data Representation Learning for Human Motion Segmentation
Mariella Dimiccoli, Lluís Garrido, Guillem Rodriguez-Corominas +1
Recently, transfer subspace learning based approaches have shown to be a valid alternative to unsupervised subspace clustering and temporal data clustering for human motion segment…
Modeling long-term interactions to enhance action recognition
Alejandro Cartas, Petia Radeva, Mariella Dimiccoli
In this paper, we propose a new approach to under-stand actions in egocentric videos that exploits the semantics of object interactions at both frame and temporal levels. At the fr…
Interaction-GCN: A Graph Convolutional Network based framework for social interaction recognition in egocentric videos
Simone Felicioni, Mariella Dimiccoli
In this paper we propose a new framework to categorize social interactions in egocentric videos, we named InteractionGCN. Our method extracts patterns of relational and non-relatio…
Debiased-CAM to mitigate image perturbations with faithful visual explanations of machine learning
Wencan Zhang, Mariella Dimiccoli, Brian Y. Lim
Model explanations such as saliency maps can improve user trust in AI by highlighting important features for a prediction. However, these become distorted and misleading when expla…
Seeing and Hearing Egocentric Actions: How Much Can We Learn?
Alejandro Cartas, Jordi Luque, Petia Radeva +2
Our interaction with the world is an inherently multimodal experience. However, the understanding of human-to-object interactions has historically been addressed focusing on a sing…
Learning event representations for temporal segmentation of image sequences by dynamic graph embedding
Mariella Dimiccoli, Herwig Wendt
Recently, self-supervised learning has proved to be effective to learn representations of events suitable for temporal segmentation in image sequences, where events are understood…
Enhancing temporal segmentation by nonlocal self-similarity
Mariella Dimiccoli, Herwig Wendt
Temporal segmentation of untrimmed videos and photo-streams is currently an active area of research in computer vision and image processing. This paper proposes a new approach to i…
How Much Does Audio Matter to Recognize Egocentric Object Interactions?
Alejandro Cartas, Jordi Luque, Petia Radeva +2
Sounds are an important source of information on our daily interactions with objects. For instance, a significant amount of people can discern the temperature of water that it is b…
Social Relation Recognition in Egocentric Photostreams
Emanuel Sanchez Aimar, Petia Radeva, Mariella Dimiccoli
This paper proposes an approach to automatically categorize the social interactions of a user wearing a photo-camera 2fpm, by relying solely on what the camera is seeing. The probl…
On the Role of Event Boundaries in Egocentric Activity Recognition from Photostreams
Alejandro Cartas, Estefania Talavera, Petia Radeva +1
Event boundaries play a crucial role as a pre-processing step for detection, localization, and recognition tasks of human activities in videos. Typically, although their intrinsic…
Smartphone picture organization: A hierarchical approach
Stefan Lonn, Petia Radeva, Mariella Dimiccoli
We live in a society where the large majority of the population has a camera-equipped smartphone. In addition, hard drives and cloud storage are getting cheaper and cheaper, leadin…
Batch-based Activity Recognition from Egocentric Photo-Streams Revisited
Alejandro Cartas, Juan Marin, Petia Radeva +1
Wearable cameras can gather large a\-mounts of image data that provide rich visual information about the daily activities of the wearer. Motivated by the large number of health app…
Social Style Characterization from Egocentric Photo-streams
Maedeh Aghaei, Mariella Dimiccoli, Cristian Canton Ferrer +1
This paper proposes a system for automatic social pattern characterization using a wearable photo-camera. The proposed pipeline consists of three major steps. First, detection of p…