51 citations · 91 across the 12 of their papers we have counts for
12 papers
Knowledge Distillation for Multi-Target Domain Adaptation in Real-Time Person Re-Identification
Félix Remigereau, Djebril Mekhazni, Sajjad Abdoli +3
Despite the recent success of deep learning architectures, person re-identification (ReID) remains a challenging problem in real-word applications. Several unsupervised single-targ…
Dynamic Template Selection Through Change Detection for Adaptive Siamese Tracking
Madhu Kiran, Le Thanh Nguyen-Meidine, Rajat Sahay +3
Deep Siamese trackers have recently gained much attention in recent years since they can track visual objects at high speeds. Additionally, adaptive tracking methods, where target…
Generative Target Update for Adaptive Siamese Tracking
Madhu Kiran, Le Thanh Nguyen-Meidine, Rajat Sahay +3
Siamese trackers perform similarity matching with templates (i.e., target models) to recursively localize objects within a search region. Several strategies have been proposed in t…
Holistic Guidance for Occluded Person Re-Identification
Madhu Kiran, R Gnana Praveen, Le Thanh Nguyen-Meidine +3
In real-world video surveillance applications, person re-identification (ReID) suffers from the effects of occlusions and detection errors. Despite recent advances, occlusions cont…
Incremental Multi-Target Domain Adaptation for Object Detection with Efficient Domain Transfer
Le Thanh Nguyen-Meidine, Madhu Kiran, Marco Pedersoli +3
Recent advances in unsupervised domain adaptation have significantly improved the recognition accuracy of CNNs by alleviating the domain shift between (labeled) source and (unlabel…
Knowledge Distillation Methods for Efficient Unsupervised Adaptation Across Multiple Domains
Le Thanh Nguyen-Meidine, Atif Belal, Madhu Kiran +3
Beyond the complexity of CNNs that require training on large annotated datasets, the domain shift between design and operational data has limited the adoption of CNNs in many real-…
Unsupervised Multi-Target Domain Adaptation Through Knowledge Distillation
Le Thanh Nguyen-Meidine, Atif Belal, Madhu Kiran +3
Unsupervised domain adaptation (UDA) seeks to alleviate the problem of domain shift between the distribution of unlabeled data from the target domain w.r.t. labeled data from the s…
Joint Progressive Knowledge Distillation and Unsupervised Domain Adaptation
Le Thanh Nguyen-Meidine, Eric Granger, Madhu Kiran +2
Currently, the divergence in distributions of design and operational data, and large computational complexity are limiting factors in the adoption of CNNs in real-world application…
On the Interaction Between Deep Detectors and Siamese Trackers in Video Surveillance
Madhu Kiran, Vivek Tiwari, Le Thanh Nguyen-Meidine +1
Visual object tracking is an important function in many real-time video surveillance applications, such as localization and spatio-temporal recognition of persons. In real-world ap…
Exploiting Prunability for Person Re-Identification
Hugo Masson, Amran Bhuiyan, Le Thanh Nguyen-Meidine +4
Recent years have witnessed a substantial increase in the deep learning (DL)architectures proposed for visual recognition tasks like person re-identification,where individuals must…
Progressive Gradient Pruning for Classification, Detection and DomainAdaptation
Le Thanh Nguyen-Meidine, Eric Granger, Madhu Kiran +2
Although deep neural networks (NNs) have achievedstate-of-the-art accuracy in many visual recognition tasks,the growing computational complexity and energy con-sumption of networks…
A Comparison of CNN-based Face and Head Detectors for Real-Time Video Surveillance Applications
Le Thanh Nguyen-Meidine, Eric Granger, Madhu Kiran +1
Detecting faces and heads appearing in video feeds are challenging tasks in real-world video surveillance applications due to variations in appearance, occlusions and complex backg…