Visual Tracking: an Experimental Survey

By Arnold M. W. Smeulders, Dung Manh Chu. 2013

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Occluded Video Instance Segmentation: A Benchmark (2021, background): “Multi-object tracking and segmentation (MOTS) [70] extends multiobject tracking (MOT) [66] from a bounding box level to a pixel level.”
Fully-Convolutional Siamese Networks for Object Tracking (2016, methodology): “Many of the sequences were originally presented in other datasets (e.g. ALOV [1] and OTB [11]).”
Transferring Rich Feature Hierarchies for Robust Visual Tracking (2015, background): “For a systematic review and comparison, we refer readers to a recent survey and benchmark [26, 33].”
Online Multi-Expert Learning for Visual Tracking (2020, unknown): “There are various kinds of visual tracking algorithms, and a brief review can be found in [1], [23]–[25].”
Fast Online Object Tracking and Segmentation: A Unifying Approach (2018, background): “Given the location of an arbitrary target of interest in the first frame of a video, the aim of visual object tracking is to estimate its position in all the subsequent frames with the best possible accuracy [69, 65, 55].”
Ocean: Object-aware Anchor-free Tracking (2020, background): “s, large deformation and illumination variations [44,49]. Tracking at real-time speeds has a variety of applications, such as surveillance, robotics, autonomous driving and human-computer interaction [16,25,33]. In recent years, Siamese tracker has drawn great attention because of its balanced speed”
Towards More Flexible and Accurate Object Tracking with Natural Language: Algorithms and Benchmark (2021, background): “For more related works on standard visual tracking, please check the following survey papers [33, 35, 41, 48, 65].”
Understanding and Diagnosing Visual Tracking Systems (2015, background): “Other benchmark datasets include the Princeton tracking benchmark [28], NUS-PRO [19] and ALOV++ [27].”
MUlti-Store Tracker (MUSTer): A cognitive psychology inspired approach to object tracking (2015, methodology): “We compare our tracker with 19 popular trackers6 that were evaluated in [43].”
Discriminative Correlation Filter Tracker with Channel and Spatial Reliability (2016, background): “It has received significant attention of the computer vision community which is reflected in the number of papers published on the topic and the existence of multiple performance evaluation benchmarks [42, 28, 29, 26, 27, 32, 37, 35].”
GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wild (2018, unknown): “Datasets that are mostly used for training trackers include ALOV++ [21], NUS_PRO [17], ImageNet-VID [23], YouTube-BB [26], LaSOT [20] and TrackingNet [19].”
In defense of color-based model-free tracking (2015, methodology): “The sequences contained in the VOT datasets have been collected from well-known tracking evaluations, such as the experimental survey on the Amsterdam Library of Ordinary Videos (ALOV) [41], the Online Tracking Benchmark (OTB) [44] , as well as recently (a) Likelihood map L. (b) Regions O and S. (c)”
Learning Adaptive Discriminative Correlation Filters via Temporal Consistency Preserving Spatial Feature Selection for Robust Visual Object Tracking (2018, background): “For a comprehensive review of existing tracking methods the reader can refer to recent surveys [1], [2], [3], [4], [5], [6].”
Multi-task Correlation Particle Filter for Robust Object Tracking (2017, background): “A comprehensive review of the tracking methods is beyond the scope of the paper, and surveys of this field can be found in [38, 36, 31].”
A Benchmark and Simulator for UAV Tracking (2016, background): “There are several recent benchmarks that were created to address specific deficiencies of older benchmarks and introduce new evaluation approaches [24,25,40], but they do not introduce videos with many tracking nuisances addressed in this paper and common to aerial scenarios.”
Multiple Hypothesis Tracking Revisited (2015, methodology): “Online discriminative appearance modeling is a standard method for addressing appearance variation [39].”
Long-term correlation tracking (2015, background): “Visual tracking has been studied extensively with numerous applications [25, 21].”
A Survey on Deep Learning Technique for Video Segmentation (2021, methodology): “To infer the location of a target object over time, current tracking methods usually assume that the target is determined by a bounding box in the first frame [59].”
TrackingNet: A Large-Scale Dataset and Benchmark for Object Tracking in the Wild (2018, unknown): “Object tracking is a common task in computer vision, with a long history spanning decades [1–3].”