Loris Bazzani

AI Research Leader

Hi, I'm Loris, an AI Research Leader with 15+ years of experience in AI between academia and big tech. My research focus is in adaptive and collaborative multimodal learning and generation.

~10 yrs
at Amazon
8+
Products Launched
$100M+
Business Impact
50+
Publications
6800+
Citations
28
H-index
The Data Space: Controllable Multimodal Data Generation & Privacy
The Model Space: Multimodal Adaptation & Specialization
The Interaction Space: Human-AI Co-Design
The Industry Space: Clear Impact on Real-world Use Cases
2026-now
I am searching for a new home to join or create together, where I can lead high-stakes innovation and drive the next generation of AI for industry.
2025-now

Adjunct Professor and Honorary Research Fellow @ University of Verona

Part-time. Driving research on adaptive and collaborative multimodal intelligence, focusing on the intersection of LMMs and interactive systems. Contributing to joint research projects and co-authoring papers with a network of international institutions. Teaching the Data Visualization course as part of the Master’s degree in Data Science.
2016-2025

Principal Scientist @ Amazon

Led high-impact core research and launched 8+ products across Prime Video, Alexa, and mobile/.com shopping generating $100M+ in business impact, related to movies and TV series autotagging, image accessibility, live sports highlights, virtual try-on, interactive product recommendations, and shopping assistants, used by millions of users worldwide. I led scientists and developed novel models and architectures for video understanding, vision-language representation, Large Multimodal Models, and diffusion models.
2014-2015

Postdoc @ Dartmouth College

Research on video understanding, saliency in videos and object localization and detection. Collaborating with Prof. Lorenzo Torresani and Prof. Hugo Larochelle.
2011-2013

Postdoc @ Italian Institute of Technology

Research on video understanding, object recognition, Bayesian networks and Kernel-based methods. Collaborating with Prof. Vittorio Murino.
2009-2012

PhD in Computer Vision and Machine Learning @ University of Verona

Research on person re-identification, video understanding, tracking and attentional models. Supervised by Prof. Vittorio Murino and Prof. Marco Cristani.
2010

Visiting Student @ University of British Columbia

Collaborating with Prof. Nando de Freitas and Prof. Hugo Larochelle.

📢 News

More

📝 Research, Publications and Patents [Google Scholar]

Interactive Episodic Memory with User Feedback

N. Subedi, L. Bazzani, Z. Al-Halah
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2026

ProMoE-FL: Prototype-conditioned Mixture of Experts for Multimodal Federated Learning with Missing Modalities

A. Chhetri, B. Niroula, E. Vasquez, Y. R. Shrestha, P. K. Gyawali, L. Bazzani, B. Bhattarai
International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), 2026

Multi-Level Conditioning by Pairing Localized Text and Sketch for Fashion Image Generation

Z. Liu, D. Talon, F. Girella, Z. Ruan, M. Mondo, L. Bazzani, Y. Wang, M. Cristani
Arxiv, 2026

Med-MMFL: A Multimodal Federated Learning Benchmark in Healthcare

A. Chhetri, B. Niroula, P. Shrestha, Y. R. Shrestha, L. A. Anderson, P. K. Gyawali, L. Bazzani, B. Bhattarai
Arxiv, 2026

Benchmarking Interaction, Beyond Policy: a Reproducible Benchmark for Collaborative Instance Object Navigation

E. Zorzi, F. Taioli, Y. Wang, M. Cristani, A. Farinelli, A. Castellini, L. Bazzani
Arxiv, 2026

Learning Visual Hierarchies in Hyperbolic Space for Image Retrieval

Z. Wang, S. Ramasinghe, C. Xu, J. Monteil, L. Bazzani, T. Ajanthan
International Conference on Computer Vision (ICCV), 2025
PDF

LatteCLIP: Unsupervised CLIP Fine-Tuning via LMM-Synthetic Texts

A. Cao, M. Jaritz, M. Guillaumin, R. de Charette, L. Bazzani
IEEE Winter Conference on Applications of Computer Vision (WACV), 2025

UniCoRN: Unified Commented Retrieval Network with LMMs

M. Jaritz, M. Guillaumin, S. Sternig, L. Bazzani
Arxiv, 2025
PDF

ToFu: Visual Tokens Reduction via Fusion for Multi-modal, Multi-patch, Multi-image Task

V. Pippi, M. Guillaumin, S. Casciarelli, R. Cucchiara, M. Jaritz, L. Bazzani
Arxiv, 2025
PDF

ViewFusion: Towards Multi-View Consistency via Interpolated Denoising

X. Yang, Y. Zuo, S. Ramasinghe, L. Bazzani, G. Avraham, A. van den Hengel
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024

iEdit: Localised Text-guided Image Editing with Weak Supervision

R. Bodur, E. Gundogdu, B. Bhattarai, T-K Kim, M. Donoser, L. Bazzani
Computer Vision and Pattern Recognition (CVPR) Workshops, 2024
PDF

[Patent] Interactive Retrieval Using Visual Semantic Matching

US-11720942, 2023
PDF

[Patent] Localized Visual Similarity

US-11809520, 2023
PDF

[Patent] Attribute-based Interactive Product Recommendations

US-11829445, 2023
PDF

[Patent] Visual Blending of Content

US 11416910, 2022
PDF

[Patent] Machine Learning System to Score Alt-text in Image Data

US-11361212, 2022
PDF

Contrastive Language-Action Pre-training for Temporal Localization

M. Xu, E. Gundogdu, M. Lapin, B. Ghanem, M. Donoser, L. Bazzani
Arxiv, 2022
PDF

Learning Attribute-driven Disentangled Representations for Interactive Fashion Retrieval

Y. Hou, E. Vig, M. Donoser, L. Bazzani
International Conference on Computer Vision (ICCV), 2021

Revamping Cross-Modal Recipe Retrieval with Hierarchical Transformers and Self-supervised Learning

A. Salvador, E. Gundogdu, L. Bazzani, M. Donoser
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021

Localized Triplet Loss for Fine-Grained Fashion Image Retrieval

A. D’Innocente, N. Garg, Y. Zhang, L. Bazzani, M. Donoser
Computer Vision and Pattern Recognition (CVPR) Workshops, 2021
PDF

Learning Joint Visual Semantic Matching Embeddings for Language-guided Retrieval

Y. Chen, L. Bazzani
European Conference on Computer Vision (ECCV), 2020
PDF

Image Search with Text Feedback by Visiolinguistic Attention Learning

Y. Chen, S. Gong, L. Bazzani
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020

[Patent] Automated Video Ratings

US-10643074, 2020
PDF

Image Captioning as Neural Machine Translation Task in SOCKEYE

L. Bazzani, T. Domhan, F. Hieber
Arxiv, 2018

Recurrent Mixture Density Network for Spatiotemporal Visual Attention

L. Bazzani, H. Larochelle, L. Torresani
International Conference on Learning Representations (ICLR), 2017

Group Detection and Tracking using Sociological Features

S. Vascon, and L. Bazzani
Group and Crowd Behavior for Computer Vision, 2017
PDF

Image and Video Understanding in Big Data

V. Murino, S. Gong, C. C. Loy and L. Bazzani
Special Issue in CVIU, 2017
PDF

Approximate Log-Hilbert-Schmidt Distances Between Covariance Operators for Image Classification

H. Q. Minh, M. San Biagio, L. Bazzani, V. Murino
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016
PDF

Self-taught Object Localization with Deep Networks

L. Bazzani, A. Bergamo, D. Anguelov, L. Torresani
IEEE Winter Conference on Applications of Computer Vision (WACV), 2016

A Unifying Framework in Vector-valued Reproducing Kernel Hilbert Spaces for Manifold Regularization and Co-Regularized Multi-view Learning

H. Q. Minh, L. Bazzani, V. Murino
Journal of Machine Learning Research (JMLR), 2016

Kernel Methods on Approximate Infinite-Dimensional Covariance Operators for Image Classification

H. Q. Minh, M. San Biagio, L. Bazzani, V. Murino
Arxiv, 2016
PDF

Joint Individual-Group Modeling for Tracking

L. Bazzani*, M. Zanotto*, M. Cristani, V. Murino
IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 2015

SDALF: Modeling Human Appearance with Symmetry-driven Accumulation of Local Features

L. Bazzani, M. Cristani, V. Murino
Person Re-identification, 2014

Weighted Bag of Visual Words for Object Recognition

L. Bazzani*, M. San Biagio*, M. Cristani, V. Murino
IEEE International Conference on Image Processing (ICIP), 2014
PDF

A Unifying Framework for Vector-valued Manifold Regularization and Multi-view Learning

H. Q. Minh, L. Bazzani, V. Murino
The 30th International Conference on Machine Learning (ICML), 2013

Semi-Supervised Multi-Feature Learning for Person Re-Identification

D. Figueira, L. Bazzani, H.Q. Minh, M. Cristani, A. Bernardino, V. Murino
International Conference on Advanced Video and Signal-based Surveillance (AVSS), 2013
PDF

Person Re-Identification with a PTZ Camera: An Introductory Study

P. Salvagnini, L. Bazzani, M. Cristani, V. Murino
International Conference on Image Processing (ICIP), 2013
PDF

Symmetry-Driven Accumulation of Local Features for Human Characterization and Re-Identification

L. Bazzani, M. Cristani, V. Murino
Computer Vision and Image Understanding (CVIU), 2013

Social Interactions by Visual Focus of Attention in a Three-Dimensional Environment

L. Bazzani, D. Tosato, M. Cristani, M. Farenzena, G. Pagetti, G. Menegaz, and V. Murino
Expert Systems 2013

Decentralized Particle Filter for Joint Individual-Group Tracking

L. Bazzani, M. Cristani, V. Murino
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2012

Learning Where to Attend with Deep Architectures for Image Tracking

M. Denil, L. Bazzani, H. Larochelle, and N. de Freitas
Neural Computation, 2012

Re-Identification with RGB-D Sensors

B. I. Barbosa, M. Cristani, A. Del Bue, L. Bazzani, V. Murino
European Conference on Computer Vision (ECCV) Workshops, 2012

Online Bayesian Non-Parametrics for Social Group Detection

M. Zanotto, L. Bazzani, M. Cristani, V. Murino
British Machine Vision Conference (BMVC), 2012
PDF

Analyzing Groups: A Social Signaling Perspective

L. Bazzani, M. Cristani, G. Paggetti, D. Tosato, G. Menegaz, and V. Murino
Video Analytics for Business Intelligence, 2012

Multiple-Shot Person Re-Identification by Chromatic and Epitomic Analyses

L. Bazzani, M. Cristani, A. Perina, and V. Murino
Pattern Recognition Letters (PRL), 2012
PDF

Learning Attentional Policies for Object Tracking and Recognition in Video with Deep Networks

L. Bazzani, N. de Freitas, H. Larochelle, V. Murino, J-A Ting
The 30th International Conference on Machine Learning (ICML), 2011

Custom Pictorial Structures for Re-Identification

D. S. Cheng, M. Cristani, M. Stoppa, L. Bazzani, V. Murino
British Machine Vision Conference (BMVC), 2011

Social Interaction Discovery by Statistical Analysis of F-Formations

M. Cristani, L. Bazzani, G. Pagetti, A. Fossati, D. Tosato, A. Del Bue, G. Menegaz, V. Murino
British Machine Vision Conference (BMVC), 2011

Towards Computational Proxemics: Inferring Social Relations from Interpersonal Distances

M. Cristani, G. Pagetti, A. Vinciarelli, L. Bazzani, G. Menegaz, V. Murino
International Conference on Social Computing (SocialCom), 2011
PDF

Multiple-Shot Person Re-Identification by HPE Signature

L. Bazzani, M. Cristani, A. Perina, M. Farenzena, V. Murino
International Conference on Pattern Recognition (ICPR), 2010
PDF

Person Re-Identification by Symmetry-Driven Accumulation of Local Features

M. Farenzena, L. Bazzani, A. Perina, M. Cristani, V. Murino
Conference on Computer Vision and Pattern Recognition (CVPR), 2010

Collaborative Particle Filters for Group Tracking

L. Bazzani, M. Cristani, V. Murino
International Conference on Image Processing (ICIP), 2010
PDF

🦄 Personal Projects

Music Album: Accepted Insanity

As long-time keyboardist, I am currently composing and producing original synthwave music. This album explores the insanity that sorrounds us but we are somehow programmed to accept.

Personal Hybrid Training Planner

As a runner and passionate about strength training, I created a personalized planner that leverages AI to build highly personalized, multi-week training plans tailored to your specific requirements.