Deep visual tracking: Review and experimental comparison

By Peixia Li, Dong Wang, Lijun Wang, Huchuan Lu. Pattern Recognition, 2018

492 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/26e2ca763087be09e3799ad294302aa91077942d

How researchers see this paper

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

In Aerospace Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

Deep Learning for Visual Tracking: A Comprehensive Survey (2019, methodology): “Although the methods in this survey are categorized into the exploitation of off-the-shelf deep features and deep features for visual tracking (similar to the FENs and EENs in [53]), detailed characteristics of these methods such as pre-trained or backbone networks, exploited layer(s), training data”
Transformer Tracking (2021, background): “Many efforts have been done in recent years [23, 28], however, designing a high-accuracy and real-time tracker is still a challenging task.”
LaSOT: A High-Quality Benchmark for Large-Scale Single Object Tracking (2018, background): “In this section, we mainly focus on the tracking benchmarks that are relevant to our work, and refer the readers to surveys [32, 47, 54, 30] for tracking algorithms.”
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].”
Backbone is All Your Need: A Simplified Architecture for Visual Object Tracking (2022, background): “Visual Object Tracking (VOT) [11,52,7,29] aims to localize the specified target in a video, which is a fundamental yet challenging task in computer vision.”
Visual Tracking via Adaptive Spatially-Regularized Correlation Filters (2019, background): “Visual tracking [36, 25, 24] is a fundamental computer vision problem and has many realistic applications including video surveillance, behavior analysis, to name a few.”
Using labeled data to evaluate change detectors in a multivariate streaming environment (2009, unknown): “In the ﬁeld of river ice semantic segmentation, accurate segmentation re-sults can provide crucial information for river monitoring [4,5] , disaster forecasting [6] , and transportation management, especially for rivers with large latitude spans.”