Mariella Dimiccoli

Computer Science · Physical Sciences

14h-index722citations93works0.02yr avg
OpenAlex↗ORCID↗Google Scholar↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Human Pose and Action Recognition(36), Video Analysis and Summarization(19), Video Surveillance and Tracking Methods(18), Multimodal Machine Learning Applications(16), Advanced Image and Video Retrieval Techniques(13)

Publications93 total

Movie Facts and Fibs (MF$^2$): A Benchmark for Long Movie Understanding
ArXiv.org·2025Open Access
Temporal Context Consistency Above All: Enhancing Long-Term Anticipation by Learning and Enforcing Temporal Constraints
arXiv (Cornell University)·2024Open Access
2by2: Weakly-Supervised Learning for Global Action Segmentation
Lecture notes in computer science·2024Open Access
3M-Transformer: A Multi-Stage Multi-Stream Multimodal Transformer for Embodied Turn-Taking Prediction
2024Open Access
3M-TRANSFORMER: A Multi-Stage Multi-Stream Multimodal Transformer for Embodied Turn-Taking Prediction
arXiv (Cornell University)·2023Open Access
Leveraging Triplet Loss for Unsupervised Action Segmentation
2023· 1 citedOpen Access
Leveraging triplet loss for unsupervised action segmentation
2023· 9 citedOpen Access
Enhancing egocentric 3D pose estimation with third person views
Pattern Recognition·2023· 15 citedOpen Access
Recognizing object surface material from impact sounds for robot manipulation
2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)·2022· 13 citedOpen Access
Debiased-CAM to mitigate image perturbations with faithful visual explanations of machine learning
CHI Conference on Human Factors in Computing Systems·2022· 12 citedOpen Access
Debiased-CAM to mitigate systematic error with faithful visual explanations of machine learning
arXiv (Cornell University)·2022Open Access
Enhancing Egocentric 3D Pose Estimation with Third Person Views
arXiv (Cornell University)·2022Open Access
Visual Event-Based Egocentric Human Action Recognition
Lecture notes in computer science·2022· 6 citedOpen Access
Learning grounded word meaning representations on similarity graphs
HAL (Le Centre pour la Communication Scientifique Directe)·2021Open Access
Graph Constrained Data Representation Learning for Human Motion Segmentation
2021 IEEE/CVF International Conference on Computer Vision (ICCV)·2021· 5 citedOpen Access
Interaction-GCN: A Graph Convolutional Network Based Framework for Social Interaction Recognition in Egocentric Videos
2021Open Access
Graph Constrained Data Representation Learning for Human Motion\n Segmentation
arXiv (Cornell University)·2021Open Access
Graph Constrained Data Representation Learning for Human Motion Segmentation
arXiv (Cornell University)·2021Open Access
Behavioural and neurophysiological signatures in the retrieval of individual memories of recent and remote real-life routine episodic events
Cortex·2021· 5 citedOpen Access
Modeling Long-Term Interactions to Enhance Action Recognition
2021Open Access
page 1 of 5Next →

Frequent Co-authors

Petia Radeva(27), Maedeh Aghaei(10), Alejandro Cartas(9), Philippe Salembier(6), Estefanía Talavera(5), Marc Bolaños(4), Juan Marín(3), Xavier Giró-i-Nieto(3), Francesc Moreno-Noguer(2), Herwig Wendt(2), Emanuel Sanchez Aimar(2), Cathal Gurrin(2), Anne‐Sophie Coquel(1), Jean-Pascal Jacob(1), Maël Primet(1), Alice Démarez(1), Thomas Julou(1), Lionel Moisan(1), Ariel B. Lindner(1), Hugues Berry(1)