Search Results - "Pernici, Federico"

Object Tracking by Oversampling Local Features by Pernici, Federico, Del Bimbo, Alberto

“…In this paper, we present the ALIEN tracking method that exploits oversampling of local invariant representations to build a robust object/context…”
Get full text

Continuous localization and mapping of a pan–tilt–zoom camera for wide area tracking by Lisanti, Giuseppe, Masi, Iacopo, Pernici, Federico, Del Bimbo, Alberto

“…Pan–tilt–zoom (PTZ) cameras are well suited for object identification and recognition in far-field scenes. However, the effective use of PTZ cameras is…”
Get full text

Self-supervised on-line cumulative learning from video streams by Pernici, Federico, Bruni, Matteo, Del Bimbo, Alberto

“…We present a novel online self-supervised method for face identity learning from video streams. The method exploits deep face feature descriptors together with…”
Get full text

Regular Polytope Networks by Pernici, Federico, Bruni, Matteo, Baecchi, Claudio, Bimbo, Alberto Del

“…Neural networks are widely used as a model for classification in a large variety of tasks. Typically, a learnable transformation (i.e., the classifier) is…”
Get full text

CoReS: Compatible Representations via Stationarity by Biondi, Niccolo, Pernici, Federico, Bruni, Matteo, Bimbo, Alberto Del

“…Compatible features enable the direct comparison of old and new learned features allowing to use them interchangeably over time. In visual search systems, this…”
Get full text

Temporal Binary Representation for Event-Based Action Recognition by Innocenti, Simone Undri, Becattini, Federico, Pernici, Federico, Del Bimbo, Alberto

“…In this paper we present an event aggregation strategy to convert the output of an event camera into frames processable by traditional Computer Vision…”
Get full text

Class-incremental Learning with Pre-allocated Fixed Classifiers by Pernici, Federico, Bruni, Matteo, Baecchi, Claudio, Turchini, Francesco, Del Bimbo, Alberto

“…In class-incremental learning, a learning agent faces a stream of data with the goal of learning new classes while not forgetting previous ones. Neural…”
Get full text

Memory Based Online Learning of Deep Representations from Video Streams by Pernici, Federico, Bartoli, Federico, Bruni, Matteo, Del Bimbo, Alberto

“…We present a novel online unsupervised method for face identity learning from video streams. The method exploits deep face descriptors together with a memory…”
Get full text

Non-myopic information theoretic sensor management of a single pan–tilt–zoom camera for multiple object detection and tracking by Salvagnini, Pietro, Pernici, Federico, Cristani, Marco, Lisanti, Giuseppe, Del Bimbo, Alberto, Murino, Vittorio

“…•Detailed derivation of an information theoretic framework for real PTZ management.•Introduction and implementation of a non-myopic strategy.•Large…”
Get full text

Metric 3D reconstruction and texture acquisition of surfaces of revolution from a single uncalibrated view by Colombo, C., Del Bimbo, A., Pernici, F.

“…Image analysis and computer vision can be effectively employed to recover the three-dimensional structure of imaged objects, together with their surface…”
Get full text

Towards on-line saccade planning for high-resolution image sensing by Bimbo, Alberto Del, Pernici, Federico

“…This paper considers the problem of designing an active observer to plan a sequence of decisions regarding what target to look at, through a foveal-sensing…”
Get full text

Backward-Compatible Aligned Representations via an Orthogonal Transformation Layer by Ricci, Simone, Biondi, Niccolò, Pernici, Federico, Del Bimbo, Alberto

“…Visual retrieval systems face significant challenges when updating models with improved representations due to misalignment between the old and new…”
Get full text

Stationary Representations: Optimally Approximating Compatibility and Implications for Improved Model Replacements by Biondi, Niccolo, Pernici, Federico, Ricci, Simone, Del Bimbo, Alberto

“…Learning compatible representations enables the interchangeable use of semantic features as models are updated over time. This is particularly relevant in…”
Get full text

Stationary Representations: Optimally Approximating Compatibility and Implications for Improved Model Replacements by Biondi, Niccolò, Pernici, Federico, Ricci, Simone, Del Bimbo, Alberto

“…Learning compatible representations enables the interchangeable use of semantic features as models are updated over time. This is particularly relevant in…”
Get full text

Information theoretic sensor management for multi-target tracking with a single pan-tilt-zoom camera by Salvagnini, Pietro, Pernici, Federico, Cristani, Marco, Lisanti, Giuseppe, Masi, Iacopo, Del Bimbo, Alberto, Murino, Vittorio

“…Automatic multiple target tracking with pan-tilt-zoom (PTZ) cameras is a hard task, with few approaches in the literature, most of them proposing simplistic…”
Get full text

Maximally Compact and Separated Features with Regular Polytope Networks by Pernici, Federico, Bruni, Matteo, Baecchi, Claudio, Del Bimbo, Alberto

“…Convolutional Neural Networks (CNNs) trained with the Softmax loss are widely used classification models for several vision tasks. Typically, a learnable…”
Get full text

Class-incremental Learning with Pre-allocated Fixed Classifiers by Pernici, Federico, Bruni, Matteo, Baecchi, Claudio, Turchini, Francesco, Del Bimbo, Alberto

“…In class-incremental learning, a learning agent faces a stream of data with the goal of learning new classes while not forgetting previous ones. Neural…”
Get full text

Fine-Grained Adversarial Semi-supervised Learning by Mugnai, Daniele, Pernici, Federico, Turchini, Francesco, Del Bimbo, Alberto

“…ACM Transactions on Multimedia Computing, Communications, and Applications 2021 In this paper we exploit Semi-Supervised Learning (SSL) to increase the amount…”
Get full text

CoReS: Compatible Representations via Stationarity by Biondi, Niccolo, Pernici, Federico, Bruni, Matteo, Del Bimbo, Alberto

“…Compatible features enable the direct comparison of old and new learned features allowing to use them interchangeably over time. In visual search systems, this…”
Get full text

CL2R: Compatible Lifelong Learning Representations by Biondi, Niccolo, Pernici, Federico, Bruni, Matteo, Mugnai, Daniele, Del Bimbo, Alberto

“…In this paper, we propose a method to partially mimic natural intelligence for the problem of lifelong learning representations that are compatible. We take…”
Get full text