Tracking-Learning-Detection

By Zdenek Kalal. 2012

3,271 citations recorded by the source corpus.

Subfields: Artificial Intelligence, 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 Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Objects as Points (2019, background): “Object detection powers many vision tasks like instance segmentation [7, 21, 32], pose estimation [3, 15, 39], tracking [24,27], and action recognition [5].”
Learning Multi-domain Convolutional Neural Networks for Visual Tracking (2015, background): “These tracking algorithms typically learn classiﬁers based on multiple instance learning [2], P-N learning [24], online boosting [14, 15], structured output SVMs [17], etc.”
Fully-Convolutional Siamese Networks for Object Tracking (2016, methodology): “This owes in large part to the demonstrated ability of methods like TLD [2], Struck [3] and KCF [4].”
Watch and learn: Semi-supervised learning of object detectors from videos (2015, background): “Sparse labeling implies that unlike other approaches [26], we do not assume exhaustively annotated input, and thus cannot sample negatives from the vicinity of labeled positives.”
Towards Weakly-Supervised Action Localization (2016, methodology): “However, we show for the ﬁrst time that extracting highly robust human tubes is possible by leveraging a recent state-of-the-art object detection approach [13], a large annotated dataset of humans in a variety of poses [14] and state-of-the-art tracking-by-detection [15,16].”
Transferring Rich Feature Hierarchies for Robust Visual Tracking (2015, methodology): “These trackers include Struck [12], SCM [38], TLD [17], ASLA [16], DLT [30] and TGPR [7].”
Learning to Track for Spatio-Temporal Action Localization (2015, neutral): “Our approach also relies on tracking, but is more robust to appearance and pose changes by using a tracking-by-detection approach [12, 21], in combination with a class-speciﬁc detector.”
Human Action Recognition With Video Data: Research and Evaluation Challenges (2014, background): “[57], [58], [88], [124], Gaussian mixture models [31], [82], [109], [122], and random forests [143] are some of the paradigms explored.”
Context-Aware Correlation Filter Tracking (2017, methodology): “Lastly, we include TLD [13] and the classic context tracker CXT [7] for reference.”
Learning to Track: Online Multi-object Tracking by Decision Making (2015, methodology): “After computing the optical flow of all the sampled points, we use the ForwardBackward (FB) error defined in [16] to measure how stable the predict is.”
The Visual Object Tracking VOT2016 Challenge Results (2016, background): “of both trackers Tracking Learning Detection (TLD) [75] tracker and Kernelized Correlation Filters (KCF) tracker [47], and selects the best patch by measuring the correlation correspondence with the stored object model sample patches.”
Distractor-aware Siamese Networks for Visual Object Tracking (2018, methodology): “Compared with PTAV [6], MUSTer [9] and TLD [10] which are qualiﬁed to perform long-term tracking, the proposed DaSiamRPN outperforms these trackers by relative 45.8%, 87.5% Fig.”
MarkIt: privacy markers for protecting visual secrets (2014, background): “In many cases users may want to protect three dimensional objects.”
Using labeled data to evaluate change detectors in a multivariate streaming environment (2009, neutral): “FPS is frame per second, which represents the speed of segmentation.”
Transfer Learning Based Visual Tracking with Gaussian Processes Regression (2014, methodology): “For fair comparison, we only compare the proposed TGPR tracker with the eight RGB competitors, including Struck [8], VTD [17], CT [41], TLD [15], MIL [2], SemiB [7] and the other 2 RGB baseline algorithms provided by the benchmark providers, RGBdet [30] and OF [30].”