Omni-Scale Feature Learning for Person Re-Identification
- Kaiyang Zhou, Yongxin Yang, A. Cavallaro, T. Xiang
- Computer ScienceIEEE International Conference on Computer Vision
- 2 May 2019
A novel deep ReID CNN is designed, termed Omni-Scale Network (OSNet), for omni-scale feature learning by designing a residual block composed of multiple convolutional feature streams, each detecting features at a certain scale.
Online Multi-target Tracking with Strong and Weak Detections
- Ricardo Sánchez-Matilla, F. Poiesi, A. Cavallaro
- Computer ScienceECCV Workshops
- 8 October 2016
An online multi-target tracker that exploits both high- and low-confidence target detections in a Probability Hypothesis Density Particle Filter framework and performs data association just after the prediction stage thus avoiding the need for computationally expensive labeling procedures such as clustering.
Automatic Analysis of Facial Affect: A Survey of Registration, Representation, and Recognition
- E. Sariyanidi, H. Gunes, A. Cavallaro
- Computer ScienceIEEE Transactions on Pattern Analysis and Machine…
- 1 June 2015
This paper provides a comprehensive analysis of facial representations by uncovering their advantages and limitations, and elaborate on the type of information they encode and how they deal with the key challenges of illumination variations, registration errors, head-pose variations, occlusions, and identity bias.
Video Tracking - Theory and Practice
- Emilio Maggio, A. Cavallaro
- Computer Science
- 21 February 2011
The design methodologies discussed throughout the book provide guidelines for developers in the industry working on vision-based applications, and help researchers and practitioners develop techniques and solutions based on the potential of video tracking applications.
Cast shadow segmentation using invariant color features
- E. Salvador, A. Cavallaro, T. Ebrahimi
- Computer ScienceComputer Vision and Image Understanding
- 1 August 2004
Mobile sensor data anonymization
- M. Malekzadeh, R. Clegg, A. Cavallaro, H. Haddadi
- Computer ScienceInternational Conference on Internet-of-Things…
- 26 October 2018
This work forms the anonymization problem using an information-theoretic approach and proposes a new multi-objective loss function for training deep autoencoders that helps minimizing user-identity information as well as data distortion to preserve the application-specific utility.
Protecting Sensory Data against Sensitive Inferences
- M. Malekzadeh, R. Clegg, A. Cavallaro, H. Haddadi
- Computer ScienceP2DS@EuroSys
- 21 February 2018
A feature learning architecture for mobile devices that provides flexible and negotiable privacy-preserving sensor data transmission by appropriately transforming raw sensor data and validated the proposed architecture in an activity recognition application using two real-world datasets.
Hybrid particle filter and mean shift tracker with adaptive transition model
- Emilio Maggio, A. Cavallaro
- EngineeringProceedings. (ICASSP '05). IEEE International…
- 18 March 2005
A tracking algorithm based on a combination of particle filter and mean shift, and enhanced with a new adaptive state transition model that predicts the state based on adaptive variances is proposed.
Efficient Multitarget Visual Tracking Using Random Finite Sets
- Emilio Maggio, M. Taj, A. Cavallaro
- Computer ScienceIEEE transactions on circuits and systems for…
- 1 August 2008
The proposed filtering framework for multitarget tracking that is based on the probability hypothesis density filter and data association using graph matching and a novel particle resampling strategy improves the accuracy of the tracker, especially in cluttered scenes.
Learning Generalisable Omni-Scale Representations for Person Re-Identification
- Kaiyang Zhou, Yongxin Yang, A. Cavallaro, T. Xiang
- Computer ScienceIEEE Transactions on Pattern Analysis and Machine…
- 15 October 2019
Novel CNN architectures to address the challenges of effective person re-identification and generalisable feature learning are developed, including a re-ID CNN termed omni-scale network (OSNet) to learn features that not only capture different spatial scales but also encapsulate a synergistic combination of multiple scales.
...
...