You are here
- Phone: 0461314511
- FBK Povo
My research belongs to the area of computer vision and machine learning and is centered on methods and systems for video understanding and 3d scene analysis. I have worked extensively on object tracking, audio-visual tracking, head pose estimation and group detection for behavior analysis. My current focus is on representation learning for video.
2020.07: News featured on FBK Magazine.
2020.06: Receiving the AWS Machine Learning Research Award.
2020.06: We ranked 3rd place in the CVPR'20 EPIC Kitchens Action Recognition challenge.
2020.02: Gate-Shift Networks (GSM) accepted at CVPR'20 main program.
2020.02: We are organizing a Workshop on Image and Video Question Answering.
2019.12: GSM is state of the art in action recognition.
2019.12: Journal Paper accepted at IEEE Transactions on Image Processing.
2019.11: I gave an invited talk at ICCV'19 Egocentric Perception, Interaction and Computing workshop in Seoul, Korea.
2019.11: Let's welcome Alex, new PhD student on the topic of video question answering.
2019.07: Paper accepted at ICCV'19 main program.
2019.07: I gave a seminar Learning to Recognize Actions in Video at Siena Artificial Intelligence Lab.
2019.06: Swathikiran defended his PhD thesis and graduated with cum laude mark.
2019.06: I gave a seminar on our work on action recognition at FBK Spring of AI seminar series.
2019.04: Paper accepted at ICIP'19 main program.
2019.02: Long Short-Term Attention (LSTA) accepted at CVPR'19 main program.
2019.02: Paper accepted at ICASSP'19 main program.
2019.01: Journal Paper accepted at ACM MultiMedia.
2019.01: Journal Paper accepted at Intelligenza Artificiale special issue on selected papers of AI*IA 2018 conference.
O. Lanz; R. Brunelli,Multimodal Technologies for Perception,Heidelberg,Springer,vol.4625/2008,2007, pp. 287-296, (Classification of Events, Activities and Relatinships, Evaluation and Workshop - CLEAR,Baltimore, MD, USA,from 5/8/2007 to 5/9/2007)
O. Lanz,Approximate Bayesian Multibody Tracking,in «IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE»,vol. 28,n. 9,2006, pp. 1436 -1449
Roberto Brunelli; Alessio Brutti; Paul Chippendale; Oswald Lanz; Maurizio Omologo; Piergiorgio Svaizer; Francesco Tobia,A Generative Approach to Audio-Visual Person Tracking,Multimodal Technologies for Perception,Springer,vol.4122/2007,2006, (First International Evaluation Workshop on Classification of Events, Activities and Relationships - CLEAR'06,Southampton, UK,from 04/10/2006 to 04/12/2006)
O. Lanz; F. Tobia; R. Brunelli,Multi-view Appearance Model for Visual People Tracking,Atti della Seconda Conferenza Italiana sui Sistemi Intelligenti - CISI,2006, (Seconda Conferenza Italiana sui Sistemi Intelligenti - CISI 2006,Ancona, Italy,09/27/2006 - 09/29/2006)
O. Lanz; R. Brunelli,Dynamic Head Location and Pose from Video,IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems 2006,n. 4042078,2006, pp. 47-52, (IEEE Conference on Multisensor Fusion and Integration - MFI,Heidelberg (Germany),da 09/03/2006 a 09/06/2006)
O. Lanz; R. Manduchi,Hybrid Joint-Separable Multibody Tracking,vol.1,2005, pp. 413-420, (IEEE Conference on Computer Vision and Pattern Recognition - CVPR,San Diego (CA),from 06/20/2005 to 06/26/2005)
O. Lanz,Probabilistic Multi-Person Tracking for Ambient Intelligence,Monitoring human activities with visual sensors is still a challenge, especially when multiple targets are involved. Occlusions, if not properly handled, are a major source of failure. Indoor environments with complex topology require the use of sensor networks whose effective management is by itself a difficult problem. Situated in the context of Ambient Intelligence, this thesis is concerned with both algorithmic and architectural aspects of distributed monitoring systems. The algorithmic approach pursued is that of non–parametric Bayesian filtering, a probabilistic state estimation framework whose multi target formulation allows physically–based modeling of the occlusion process within an appearance based, background independent observation model. While unaffordable in its plain, joint formulation, a novel, efficient, probabilistically sound solution is proposed and its robustness experimentally verified. Its MonteCarlo implementation provides a suitable framework for tackling dynamic resource allocation within a distributed modular architecture. Representation size of probabilistic estimates is adapted to conveyed uncertainty, while active environment sampling aims at minimizing uncertainty. Independent sensor agencies are synergically reconfigured by a supervisor process with global environment knowledge. The proposed system is then adaptive to its own performance, environment and sensing and computing infrastructure, providing a scalable solution to the problem of visual monitoring of crowded, topologically complex environments,2005
O. Lanz,A Joint-Separable Filter for Multitarget Tracking,Tracking multiple targets with visual sensors is a challenging problem, especially when efficiency is an issue. Occlusions, if not properly handled, are a major source of failure. Solutions supporting principled occlusion reasoning have been proposed but are yet unpractical for online applications. This article presents a new solution which effectively manages the trade-off between reliable modeling and computational efficiency. The Hybrid Joint-Separable (HJS) filter is derived from a joint Bayesian formulation of the problem, and shown to be efficient while optimal in terms of efficient belief representation. Computational efficiency is achieved by employing a forward MRF approximation to joint dynamics and an incremental algorithm for posterior update with an appearance likelihood that implements a physically-based model of the occlusion process. Its real time MonteCarlo implementation achieves accurate tracking during partial occlusions, while in case of complete occlusion tracking hypotheses are bound to estimated occlusion volumes. Experiments show that the proposed algorithm is very robust and able to resolve even long term complete occlusions between targets with identical appearance,2005
O. Lanz,Dynamic Resource Allocation for Probabilistic Tracking in Complex Scenes,Monitoring human activities in large environments is a challenging problem. Such scenarios impose the use of sensor networks and decentralized processing to achieve scalability in terms of spatial environment and task complexity. This article addresses both algorithmic and architectural aspects of distributed tracking systems. The algorithmic approach pursued is that of sequential Bayesian filtering, whose standard formulation is rewritten in a form suitable for distribution within a three-layered modular architecture. Its non-parametric MonteCarlo implementation provides a suitable framework for tackling dynamic resource allocation: representation size of probabilistic estimates is adapted to conveyed uncertainty, while active environment sampling aims at minimizing uncertainty. Independent tracking agencies with competence on a subset of targets are instantiated and continuously reconfigured by a supervisor process with global environment knowledge. The proposed system is then adaptive to its sensing and computing infrastructure, own performance and environment, providing a scalable solution to the problem of visual monitoring of populated, topologically complex environments,2005
O. Lanz,Automatic Lens Distortion Estimation for an Active Camera,2004, pp. 575-580, (International Conference on Computer Vision and Graphics - ICCVG,Warsaw (Poland),da 09/22/2004 a 09/24/2004)