NDLI: Adaptive convolutional layer selection based on historical retrospect for visual tracking

Content Provider	IET Digital Library
Author	Tang, Fuhui Lu, Xiankai Zhang, Xiaoyu Luo, Lingkun Hu, Shiqiang Zhang, Huanlong
Abstract	Visual tracking has recently gained a great advance with the use of the convolutional neural network (CNN). Usually, existing CNN-based trackers exploit the features from a single layer or a certain combination of multiple layers. However, these features only characterise an object from an invariable aspect and cannot adapt to scene variation, which limits the performance of such trackers. To overcome this limitation, the authors study the problem from a new perspective and propose a novel convolutional layer selection method. To obtain robust appearance representation, they investigate the advantages of features extracted from different convolutional layers. To determine the correctness of the tracking prediction and updated model, they design a verification mechanism based on historical retrospect, which can estimate the deviation for each layer by bidirectionally locating the target. Meanwhile, the deviation works as the layer-wise selection criteria. Extensive evaluations on the OTB-2013, visual object tracking (VOT)-2016 and VOT-2017 benchmarks demonstrate that the proposed tracker performs favourably against several state-of-the-art trackers.
Starting Page	345
Ending Page	353
Page Count	9
ISSN	17519632
Volume Number	13
e-ISSN	17519640
Issue Number	Issue 3, Apr (2019)
Alternate Webpage(s)	https://digital-library.theiet.org/content/journals/iet-cvi/13/3
Alternate Webpage(s)	https://digital-library.theiet.org/content/journals/10.1049/iet-cvi.2018.5194
Journal	IET Computer Vision
Publisher Date	2018-12-13
Access Restriction	Open
Rights Holder	© The Institution of Engineering and Technology
Subject Keyword	Adaptive Convolutional Layer Selection Cellular Neural Nets CNN-based Trackers Computer Vision And Image Processing Technique Convolutional Layer Selection Method Convolutional Neural Network Different Convolutional Layer Feature Extraction Great Advance Historical Retrospect Image Recognition Image Representation Image Sequence Invariable Aspect Knowledge Engineering Technique Layer-wise Selection Criteria Learning in AI Multiple Layer Neural Computing Technique Object Detection Object Tracking Robust Appearance Representation Scene Variation Single Layer Target Tracking Tracker Performs Tracking Prediction Video Signal Processing Visual Object Tracking Visual Tracking
Content Type	Text
Resource Type	Article
Subject	Computer Vision and Pattern Recognition Software

Sl.	Authority	Responsibilities	Communication Details
1	Ministry of Education (GoI), Department of Higher Education	Sanctioning Authority	https://www.education.gov.in/ict-initiatives
2	Indian Institute of Technology Kharagpur	Host Institute of the Project: The host institute of the project is responsible for providing infrastructure support and hosting the project	https://www.iitkgp.ac.in
3	National Digital Library of India Office, Indian Institute of Technology Kharagpur	The administrative and infrastructural headquarters of the project	Dr. B. Sutradhar bsutra@ndl.gov.in
4	Project PI / Joint PI	Principal Investigator and Joint Principal Investigators of the project	Dr. B. Sutradhar bsutra@ndl.gov.in Prof. Saswat Chakrabarti will be added soon
5	Website/Portal (Helpdesk)	Queries regarding NDLI and its services	support@ndl.gov.in
6	Contents and Copyright Issues	Queries related to content curation and copyright issues	content@ndl.gov.in
7	National Digital Library of India Club (NDLI Club)	Queries related to NDLI Club formation, support, user awareness program, seminar/symposium, collaboration, social media, promotion, and outreach	clubsupport@ndl.gov.in
8	Digital Preservation Centre (DPC)	Assistance with digitizing and archiving copyright-free printed books	dpc@ndl.gov.in
9	IDR Setup or Support	Queries related to establishment and support of Institutional Digital Repository (IDR) and IDR workshops	idr@ndl.gov.in

Occlusion-robust object tracking based on the confidence of online selected hierarchical features

Survey on hardware implementations of visual object trackers

Embedding holistic appearance information in part-based adaptive appearance model for robust visual tracking

Correlation filter-based visual tracking via adaptive weighted CNN features fusion

Classifying Global Scene Context for On-line Multiple Tracker Selection

ACT: an ACTNet for visual tracking

Robust long-term correlation tracking with multiple models

Data driven visual tracking via representation learning and online multi-class LPBoost learning

Object detection using convolutional networks with adaptively adjusting receptive field of convolutional filter

Adaptive convolutional layer selection based on historical retrospect for visual tracking

Similar Documents

Occlusion-robust object tracking based on the confidence of online selected hierarchical features

Survey on hardware implementations of visual object trackers

Embedding holistic appearance information in part-based adaptive appearance model for robust visual tracking

Correlation filter-based visual tracking via adaptive weighted CNN features fusion

Classifying Global Scene Context for On-line Multiple Tracker Selection

ACT: an ACTNet for visual tracking

Robust long-term correlation tracking with multiple models

Data driven visual tracking via representation learning and online multi-class LPBoost learning

Object detection using convolutional networks with adaptively adjusting receptive field of convolutional filter

Adaptive convolutional layer selection based on historical retrospect for visual tracking