Search Results - "Bazzani, Loris"

Symmetry-driven accumulation of local features for human characterization and re-identification by Bazzani, Loris, Cristani, Marco, Murino, Vittorio

“…This work proposes a method to characterize the appearance of individuals exploiting body visual cues. The method is based on a symmetry-driven…”
Get full text

Joint Individual-Group Modeling for Tracking by Bazzani, Loris, Zanotto, Matteo, Cristani, Marco, Murino, Vittorio

“…We present a novel probabilistic framework that jointly models individuals and groups for tracking. Managing groups is challenging, primarily because of their…”
Get full text

Multiple-Shot Person Re-identification by HPE Signature by Bazzani, Loris, Cristani, Marco, Perina, Alessandro, Farenzena, Michela, Murino, Vittorio

“…In this paper, we propose a novel appearance-based method for person re-identification, that condenses a set of frames of the same individual into a highly…”
Get full text

Approximate Log-Hilbert-Schmidt Distances between Covariance Operators for Image Classification by Ha Quang Minh, San Biagio, Marco, Bazzani, Loris, Murino, Vittorio

“…This paper presents a novel framework for visual object recognition using infinite-dimensional covariance operators of input features, in the paradigm of…”
Get full text

Weighted bag of visual words for object recognition by San Biagio, Marco, Bazzani, Loris, Cristani, Marco, Murino, Vittorio

“…Bag of Visual words (BoV) is one of the most successful strategy for object recognition, used to represent an image as a vector of counts using a learned…”
Get full text

Image Search With Text Feedback by Visiolinguistic Attention Learning by Chen, Yanbei, Gong, Shaogang, Bazzani, Loris

“…Image search with text feedback has promising impacts in various real-world applications, such as e-commerce and internet search. Given a reference image and…”
Get full text

Learning where to attend with deep architectures for image tracking by Denil, Misha, Bazzani, Loris, Larochelle, Hugo, de Freitas, Nando

“…We discuss an attentional model for simultaneous object tracking and recognition that is driven by gaze data. Motivated by theories of perception, the model…”
Get more information

Multiple-shot person re-identification by chromatic and epitomic analyses by Bazzani, Loris, Cristani, Marco, Perina, Alessandro, Murino, Vittorio

“…► We propose a novel appearance-based method for person re-identification. ► It condenses a set of frames of the same individual into a informative signature…”
Get full text

Revamping Cross-Modal Recipe Retrieval with Hierarchical Transformers and Self-supervised Learning by Salvador, Amaia, Gundogdu, Erhan, Bazzani, Loris, Donoser, Michael

“…Cross-modal recipe retrieval has recently gained substantial attention due to the importance of food in people's lives, as well as the availability of vast…”
Get full text

Learning Attribute-driven Disentangled Representations for Interactive Fashion Retrieval by Hou, Yuxin, Vig, Eleonora, Donoser, Michael, Bazzani, Loris

“…Interactive retrieval for online fashion shopping provides the ability to change image retrieval results according to the user feedback. One common problem in…”
Get full text

Image and Video Understanding in Big Data by Murino, Vittorio, Gong, Shaogang, Loy, Chen Change, Bazzani, Loris

Get full text

Towards Computational Proxemics: Inferring Social Relations from Interpersonal Distances by Cristani, M., Paggetti, G., Vinciarelli, A., Bazzani, L., Menegaz, G., Murino, V.

“…This paper proposes a study corroborated by preliminary experiments on the inference of social relations based on the analysis of interpersonal distances,…”
Get full text

Decentralized particle filter for joint individual-group tracking by Bazzani, L., Cristani, M., Murino, V.

“…In this paper, we address the task of tracking groups of people in surveillance scenarios. This is a major challenge in computer vision, since groups are…”
Get full text

Self-taught object localization with deep networks by Bazzani, Loris, Bergamo, Alessandra, Anguelov, Dragomir, Torresani, Lorenzo

“…This paper introduces self-taught object localization, a novel approach that leverages deep convolutional networks trained for whole-image recognition to…”
Get full text

Person re-identification with a PTZ camera: An introductory study by Salvagnini, Pietro, Bazzani, Loris, Cristani, Marco, Murino, Vittorio

“…We present an introductory study that paves the way for a new kind of person re-identification, by exploiting a single Pan-Tilt-Zoom (PTZ) camera. PTZ devices…”
Get full text

Collaborative particle filters for group tracking by Bazzani, Loris, Cristani, Marco, Murino, Vittorio

“…Tracking groups of people is a highly informative task in surveillance, and it represents a still open and little explored issue. In this paper, we propose a…”
Get full text

Localized Triplet Loss for Fine-grained Fashion Image Retrieval by D'Innocente, Antonio, Garg, Nikhil, Zhang, Yuan, Bazzani, Loris, Donoser, Michael

“…Fashion retrieval methods aim at learning a clothing-specific embedding space where images are ranked based on their global visual similarity with a given…”
Get full text

Learning Visual Hierarchies with Hyperbolic Embeddings by Wang, Ziwei, Ramasinghe, Sameera, Xu, Chenchen, Monteil, Julien, Bazzani, Loris, Ajanthan, Thalaiyasingam

“…Structuring latent representations in a hierarchical manner enables models to learn patterns at multiple levels of abstraction. However, most prevalent image…”
Get full text

LatteCLIP: Unsupervised CLIP Fine-Tuning via LMM-Synthetic Texts by Cao, Anh-Quan, Jaritz, Maximilian, Guillaumin, Matthieu, de Charette, Raoul, Bazzani, Loris

“…Large-scale vision-language pre-trained (VLP) models (e.g., CLIP) are renowned for their versatility, as they can be applied to diverse applications in a…”
Get full text

iEdit: Localised Text-guided Image Editing with Weak Supervision by Bodur, Rumeysa, Gundogdu, Erhan, Bhattarai, Binod, Kim, Tae-Kyun, Donoser, Michael, Bazzani, Loris

“…Diffusion models (DMs) can generate realistic images with text guidance using large-scale datasets. However, they demonstrate limited controllability on the…”
Get full text