Publications

TANGO: Training-free Embodied AI Agents for Open-world Tasks

Filippo Ziliotto, Tommaso Campari, Luciano Serafini, Lamberto Ballan

IEEE/CVF International Conference on Computer Vision and Pattern Recognition (CVPR), 2025

arXiv preprint

Following the Human Thread in Social Navigation

Luca Scofano*, Alessio Sampieri*, Tommaso Campari*, Valentino Sacco*, Indro Spinelli, Lamberto Ballan, Fabio Galasso

International Conference on Learning Representations (ICLR), 2025 [Spotlight]

arXiv preprint

Towards Polyp Counting in Full-Procedure Colonoscopy Videos

Luca Parolari, Andrea Cherubini, Lamberto Ballan, Carlo Biffi

IEEE International Symposium on Biomedical Imaging (ISBI), 2025

Paper (in press) arXiv preprint

Distilling Knowledge for Short-to-Long Term Trajectory Prediction

Sourav Das, Guglielmo Camporese, Shaokang Cheng, Lamberto Ballan

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2024

Paper arXiv preprint

Harlequin: Color-driven Generation of Synthetic Data for Referring Expression Comprehension

Luca Parolari, Elena Izzo, Lamberto Ballan

International Conference on Pattern Recognition (ICPR), 2024
CVPR Workshop on Synthetic Data for Computer Vision (SynData4CV), 2024 [Extended Abstract]

Paper arXiv preprint Extended Abstract Code & Dataset

Multi-Modal Transformer with Language Modality Distillation for Early Pedestrian Action Anticipation

Nada Osman, Guglielmo Camporese, Lamberto Ballan

Computer Vision and Image Understanding, Vol. 249, 2024

Paper

FastSTI: A Fast Conditional Pseudo Numerical Diffusion Model for Spatio-temporal Traffic Data Imputation

Shaokang Cheng, Nada Osman, Shiru Qu, Lamberto Ballan

IEEE Transactions on Intelligent Transportation Systems (T-ITS), Vol. 25, Issue 12, pp. 20547-20560, 2024

Paper arXiv preprint

DSP-ST: Dynamic Structural Prior Spatio-temporal Graph Attention Networks for Traffic Speed Prediction

Shaokang Cheng, Nada Osman, Shiru Qu, Lamberto Ballan

IEEE Intelligent Transportation Systems Magazine, Vol. in press, 2024

Paper (in press)

Temporal Divide-and-Conquer Anomaly Actions Localization in Semi-Supervised Videos with Hierarchical Transformer

Nada Osman, Marwan Torki

International Conference on Pattern Recognition (ICPR), 2024

arXiv preprint

Exploiting Proximity-Aware Tasks for Embodied Social Navigation

Enrico Cancelli*, Tommaso Campari*, Luciano Serafini, Angel X. Chang, Lamberto Ballan

IEEE/CVF International Conference on Computer Vision (ICCV), 2023
CVPR Embodied AI Workshop, 2023 [Extended Abstract]

Paper arXiv preprint Extended Abstract Code & Dataset

Weakly-Supervised Visual-Textual Grounding with Semantic Prior Refinement

Davide Rigoni, Luca Parolari, Luciano Serafini, Alessandro Sperduti, Lamberto Ballan

British Machine Vision Conference (BMVC), 2023

arXiv preprint

TAMFormer: Multi-Modal Transformer with Learned Attention Mask for Early Intent Prediction

Nada Osman, Guglielmo Camporese, Lamberto Ballan

IEEE Int'l Conference on Acoustics Speech and Signal Processing (ICASSP), 2023 [Oral]

Paper arXiv preprint Code & Dataset

On the Problem of Recommendation for Sensitive Users and Influential Items: Simultaneously Maintaining Interest and Diversity

Alvise De Biasio, Merylin Monaro, Luca Oneto, Lamberto Ballan, Nicolo Navarin

Knowledge-Based Systems, Vol. 275, Article 110699, 2023

Paper

Deep Symbolic Learning: Discovering Symbols and Rules from Perceptions

Alessandro Daniele, Tommaso Campari, Sagar Malhotra, Luciano Serafini

International Joint Conference on Artificial Intelligence (IJCAI), 2023

Paper arXiv preprint

Empowering Convolutional Neural Nets with MetaSin Activation

Farnood Salehi, Tunc Ozan Aydin, Andre Gaillard, Guglielmo Camporese, Yuxuan Wang

International Conference on Neural Information Processing Systems (NeurIPS), 2023

OpenReview preprint

Online Learning of Reusable Abstract Models for Object Goal Navigation

Tommaso Campari, Leonardo Lamanna, Paolo Traverso, Luciano Serafini, Lamberto Ballan

IEEE/CVF International Conference on Computer Vision and Pattern Recognition (CVPR), 2022

Paper arXiv preprint Poster

How many Observations are Enough? Knowledge Distillation for Trajectory Forecasting

Alessio Monti, Angelo Porrello, Simone Calderara, Pasquale Coscia, Lamberto Ballan, Rita Cucchiara

IEEE/CVF International Conference on Computer Vision and Pattern Recognition (CVPR), 2022

Paper arXiv preprint

Goal-driven Self-Attentive Recurrent Networks for Trajectory Prediction

Luigi Filippo Chiara, Pasquale Coscia, Sourav Das, Simone Calderara, Rita Cucchiara, Lamberto Ballan

CVPR Precognition Workshop, 2022

Paper arXiv preprint Code & Dataset

Where are my Neighbors? Exploiting Patches Relations in Self-Supervised Vision Transformer

Guglielmo Camporese, Elena Izzo, Lamberto Ballan

British Machine Vision Conference (BMVC), 2022 [Spotlight]
CVPR Workshop on Transformers for Vision (T4V), 2022 [Extended Abstract]

Paper arXiv preprint Extended Abstract Poster Video Code & Dataset

Early Pedestrian Intent Prediction via Features Estimation

Nada Osman, Enrico Cancelli, Guglielmo Camporese, Pasquale Coscia, Lamberto Ballan

IEEE International Conference on Image Processing (ICIP), 2022

Paper Poster Code & Dataset

Mechanisms underlying directional motion processing and form-motion integration assessed with visual perceptual learning

Rita Donato*, Andrea Pavan*, Giovanni Cavallin, Lamberto Ballan, Luca Betteto, Massimo Nucci, Gianluca Campana

Vision, S.I. "Symposium on Perception and Cognition and Kanizsa Lecture", Vol. 6, No. 2:29, pp. 1-19, 2022

Paper

Aligning and linking entity mentions in image, text, and knowledge base

Shahi Dost, Luciano Serafini, Marco Rospocher, Lamberto Ballan, Alessandro Sperduti

Data & Knowledge Engineering, Vol. 138, 2022

Paper Code & Dataset

Retrospectives on the Embodied AI Workshop

Matt Deitke, Dhruv Batra, Yonatan Bisk, Tommaso Campari, Angel X. Chang, Devendra Singh Chaplot, Changan Chen, Claudia Pérez D'Arpino, Kiana Ehsani, Ali Farhadi, Li Fei-Fei, Anthony Francis, Chuang Gan, Kristen Grauman, David Hall, Winson Han, Unnat Jain, Aniruddha Kembhavi, Jacob Krantz, Stefan Lee, Chengshu Li, Sagnik Majumder, Oleksandr Maksymets, Roberto Martín-Martín, Roozbeh Mottaghi, Sonia Raychaudhuri, Mike Roberts, Silvio Savarese, Manolis Savva, Mohit Shridhar, Niko Sünderhauf, Andrew Szot, Ben Talbot, Joshua B. Tenenbaum, Jesse Thomason, Alexander Toshev, Joanne Truong, Luca Weihs, Jiajun Wu

arXiv preprint: 2210.06849, 2022

arXiv preprint

Conditional Variational Capsule Network for Open Set Recognition

Yunrui Guo*, Guglielmo Camporese*, Wenjing Yang, Alessandro Sperduti, Lamberto Ballan

IEEE/CVF International Conference on Computer Vision (ICCV), 2021

Paper arXiv preprint Poster Code & Dataset

SlowFast Rolling-Unrolling LSTMs for Action Anticipation in Egocentric Videos

Nada Osman, Guglielmo Camporese, Pasquale Coscia, Lamberto Ballan

ICCV Workshop on Egocentric Perception Interaction and Computing (EPIC), 2021

Paper arXiv preprint

AC-VRNN: Attentive Conditional-VRNN for Multi-Future Trajectory Prediction

Alessia Bertugli, Simone Calderara, Pasquale Coscia, Lamberto Ballan, Rita Cucchiara

Computer Vision and Image Understanding, Vol. 210, 2021

Paper arXiv preprint Code & Dataset

Am I Done? Predicting Action Progress in Videos

Federico Becattini, Tiberio Uricchio, Lorenzo Seidenari, Lamberto Ballan, Alberto Del Bimbo

ACM Trans. on Multimedia Computing, Communications, and Applications (TOMM), Vol. 16, Issue 4, pp. 1-24, 2021

Paper arXiv preprint

Improved Robustness to Disfluencies in RNN-Transducer Based Speech Recognition

Valentin Mendelev, Tina Raissi, Guglielmo Camporese, Manuel Giollo

IEEE Int'l Conference on Acoustics Speech and Signal Processing (ICASSP), 2021

Paper arXiv preprint

Exploiting Scene-specific Features for Object Goal Navigation

Tommaso Campari, Paolo Eccher, Luciano Serafini, Lamberto Ballan

ECCV Workshop on Assistive Computer Vision and Robotics (ACVR), 2020

Paper arXiv preprint

Knowledge Distillation for Action Anticipation via Label Smoothing

Guglielmo Camporese, Pasquale Coscia, Antonino Furnari, Giovanni Maria Farinella, Lamberto Ballan

International Conference on Pattern Recognition (ICPR), 2020

Paper arXiv preprint Poster Video

A CNN-RNN Framework for Image Annotation from Visual Cues and Social Network Metadata

Tobia Tesan, Pasquale Coscia, Lamberto Ballan

International Conference on Pattern Recognition (ICPR), 2020

Paper arXiv preprint

On Visual-Textual-Knowledge Entity Linking

Shahi Dost, Luciano Serafini, Marco Rospocher, Lamberto Ballan, Alessandro Sperduti

European Conference on Artificial Intelligence (ECAI), 2020 [Highlight]
IEEE International Conference on Semantic Computing (ICSC), 2020

Paper Extended Abstract Code & Dataset

VTKEL: A resource for Visual-Textual-Knowledge Entity Linking

Shahi Dost, Luciano Serafini, Marco Rospocher, Lamberto Ballan, Alessandro Sperduti

ACM Symposium on Applied Computing (ACM-SAC), 2020

Paper Code & Dataset

Social and Scene-aware Trajectory Prediction in Crowded Spaces

Matteo Lisotto, Pasquale Coscia, Lamberto Ballan

ICCV Workshop on Assistive Computer Vision and Robotics (ACVR), 2019

Paper arXiv preprint Code

Long-term Path Prediction in Urban Scenarios using Circular Distributions

Pasquale Coscia, Francesco Castaldo, Francesco Palmieri, Alexandre Alahi, Silvio Savarese, Lamberto Ballan

Image and Vision Computing, Vol. 69, pp. 81-91, 2018

Paper IVC Best Paper Award 2021

Context-aware Trajectory Prediction

Federico Bartoli, Giuseppe Lisanti, Lamberto Ballan, Alberto Del Bimbo

International Conference on Pattern Recognition (ICPR), 2018

Paper arXiv preprint

Learning without Prejudice: Avoiding Bias in Webly-Supervised Action Recognition

Christian Rupprecht, Ansh Kapil, Nan Liu, Lamberto Ballan, Federico Tombari

Computer Vision and Image Understanding, Vol. 173, pp. 24-32, 2018

Paper arXiv preprint

Human Action Anticipation: Deep Learning Approaches Across Diverse Domains

Nada Osman

University of Padova, PhD Thesis, April 2024

Thesis

Embodied AI with Common-Sense

Tommaso Campari

University of Padova, PhD Thesis, March 2023

Thesis

Prediction of Activities and Visual Concepts Under Complex and Changing Conditions

Guglielmo Camporese

University of Padova, PhD Thesis, February 2023

Thesis

Object and event recognition in multimedia archives using local visual features

Lamberto Ballan

University of Florence, PhD Thesis, April 2011

Thesis