Search Results for author: Madhu Kiran

Found 11 papers, 4 papers with code

Dynamic Template Selection Through Change Detection for Adaptive Siamese Tracking

no code implementations7 Mar 2022 Madhu Kiran, Le Thanh Nguyen-Meidine, Rajat Sahay, Rafael Menelau Oliveira E Cruz, Louis-Antoine Blais-Morin, Eric Granger

Results indicate that integrating our proposed method into state-of-art adaptive Siamese trackers can increase the potential benefits of a template update strategy, and significantly improve performance.

Change Detection Incremental Learning +2

Generative Target Update for Adaptive Siamese Tracking

no code implementations21 Feb 2022 Madhu Kiran, Le Thanh Nguyen-Meidine, Rajat Sahay, Rafael Menelau Oliveira E Cruz, Louis-Antoine Blais-Morin, Eric Granger

This paper proposes a model adaptation method for Siamese trackers that uses a generative model to produce a synthetic template from the object search regions of several previous frames, rather than directly using the tracker output.

Change Detection

Incremental Multi-Target Domain Adaptation for Object Detection with Efficient Domain Transfer

1 code implementation13 Apr 2021 Le Thanh Nguyen-Meidine, Madhu Kiran, Marco Pedersoli, Jose Dolz, Louis-Antoine Blais-Morin, Eric Granger

Recent advances in unsupervised domain adaptation have significantly improved the recognition accuracy of CNNs by alleviating the domain shift between (labeled) source and (unlabeled) target data distributions.

Incremental Learning Knowledge Distillation +4

Holistic Guidance for Occluded Person Re-Identification

no code implementations13 Apr 2021 Madhu Kiran, R Gnana Praveen, Le Thanh Nguyen-Meidine, Soufiane Belharbi, Louis-Antoine Blais-Morin, Eric Granger

Hence, our proposed student-teacher framework is trained to address the occlusion problem by matching the distributions of between- and within-class distances (DCDs) of occluded samples with that of holistic (non-occluded) samples, thereby using the latter as a soft labeled reference to learn well separated DCDs.

Denoising Person Re-Identification +1

Knowledge Distillation Methods for Efficient Unsupervised Adaptation Across Multiple Domains

no code implementations18 Jan 2021 Le Thanh Nguyen-Meidine, Atif Belal, Madhu Kiran, Jose Dolz, Louis-Antoine Blais-Morin, Eric Granger

Our proposed approach is compared against state-of-the-art methods for compression and STDA of CNNs on the Office31 and ImageClef-DA image classification datasets.

Knowledge Distillation Person Re-Identification +1

A Flow-Guided Mutual Attention Network for Video-Based Person Re-Identification

no code implementations9 Aug 2020 Madhu Kiran, Amran Bhuiyan, Louis-Antoine Blais-Morin, Mehrsan Javan, Ismail Ben Ayed, Eric Granger

Our Mutual Attention network relies on the joint spatial attention between image and optical flow features maps to activate a common set of salient features across them.

Optical Flow Estimation Video-Based Person Re-Identification

Joint Progressive Knowledge Distillation and Unsupervised Domain Adaptation

2 code implementations16 May 2020 Le Thanh Nguyen-Meidine, Eric Granger, Madhu Kiran, Jose Dolz, Louis-Antoine Blais-Morin

In both datasets, results indicate that our method can achieve the highest level of accuracy while requiring a comparable or lower time complexity.

Knowledge Distillation Person Re-Identification +1

On the Interaction Between Deep Detectors and Siamese Trackers in Video Surveillance

no code implementations31 Oct 2019 Madhu Kiran, Vivek Tiwari, Le Thanh Nguyen-Meidine, Eric Granger

However, bounding boxes provided by a state-of-the-art detector are noisy, due to changes in appearance, background and occlusion, which can cause the tracker to drift.

Change Detection Visual Object Tracking

Progressive Gradient Pruning for Classification, Detection and DomainAdaptation

1 code implementation20 Jun 2019 Le Thanh Nguyen-Meidine, Eric Granger, Madhu Kiran, Louis-Antoine Blais-Morin, Marco Pedersoli

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 remains an issue, especially for ap-plications on platforms with limited resources and requir-ing real-time processing.

Classification General Classification +1

A Comparison of CNN-based Face and Head Detectors for Real-Time Video Surveillance Applications

no code implementations10 Sep 2018 Le Thanh Nguyen-Meidine, Eric Granger, Madhu Kiran, Louis-Antoine Blais-Morin

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 backgrounds.

Head Detection

Cannot find the paper you are looking for? You can Submit a new open access paper.