Support vector tracking

By Shai Avidan. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004

988 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/351dc239ba9f94fb344773bc7fb8697212e7e9ba

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

On-road vehicle detection: a review (2006, background): “Several efforts have been reported in [88] and more recently in [89].”
Visual tracking with online Multiple Instance Learning (2009, background): “the design of appearance models is whether to model only the object [5, 21], or both the object and the background [18, 14, 19, 4, 3, 24, 7].”
Real-time part-based visual tracking via adaptive correlation filters (2015, background): “Different from generative trackers, discriminative approaches cast tracking as a classification problem that distinguishes the tracked targets from the backgrounds [2, 29, 42, 56].”
Efficient mean-shift tracking via a new similarity measure (2005, methodology): “Learning-based approaches apply pattern recognition algorithms to learn the objects either in the eigenspace or in the kernel space, and then search for targets in image sequences [4, 1, 33].”
MUlti-Store Tracker (MUSTer): A cognitive psychology inspired approach to object tracking (2015, result): “In contrast to the generative approaches used in [42] and [37], discriminative methods [2, 3, 4, 14, 17, 20] have been proposed that consider both foreground and background information.”
Fast multiple object tracking via a hierarchical particle filter (2005, methodology): “Appearance-based approaches apply recognition algorithms to learn the objects either in some basis such as the eigenspace formed from observations or in kernel space [4, 1, 35].”
Siam R-CNN: Visual Tracking by Re-Detection (2019, methodology): “Tracking by re-detection has a long history, reaching back to the seminal work of Avidan [1] and Grabner et al. [21].”
Real-Time Tracking via On-line Boosting (2006, methodology): “In addition, to the on-line adaption problem, recently many techniques have addressed the idea of using information about the background in order to increase the robustness of tracking [1, 19, 2, 26, 6].”
Learning deep features for multiple object tracking by using a multi-task learning strategy (2014, background): “Model-free object tracking approaches can be divided into two categories: generative [8, 9, 10, 11, 12] and discriminative [13, 14, 15, 16, 17].”
Semi-supervised On-Line Boosting for Robust Tracking (2008, background): “…illumination variations, partial occlusions of the object, cluttered scenes, etc. Recently tracking has been formulated as a classiﬁcation problem, i.e. , the task of tracking is to optimally separate in each frame the object from the background ( e.g. , Avidan [1] used support vector machines).”
Struck: Structured output tracking with kernels (2011, neutral): “This popularity is due in part to the great deal of progress made recently in object detection, with many of the ideas being directly transferable to tracking [2].”
Deformable Model Fitting by Regularized Landmark Mean-Shift (2010, background): “As such, future work will involve investigations into the use of different feature detectors (see Avidan 2004; Cootes and Taylor 1992; Cristinacce and Cootes 2006, for example), more sophisticated shape models (see Gu and Fig.”
Visual Tracking: an Experimental Survey (2013, neutral): “A common way of updating is to substitute the old template with the last seen template, improved with partial updating [103], [104], with leaking [61], or with occasional target rebooting from scratch [105].”
Face tracking and recognition with visual constraints in real-world videos (2008, background): “Direct use of object detectors in discriminative tracking has been proposed more recently, c.f., [ 2 , 14].”
Graph mode-based contextual kernels for robust SVM tracking (2011, background): “Finally, this contextual kernel is embedded into SVMs for robust tracking.”
Self-Paced Learning for Long-Term Tracking (2013, methodology): “To do so in a principled and efficient manner, we use the formalism of self-paced learning and online solvers for SVMs.”
Context tracker: Exploring supporters and distracters in unconstrained environments (2011, background): “Since visual tracking is a semi-supervised problem where the incoming data is unknown, online appearance modeling [26, 3, 12, 28] is preferable to an offline one [1, 2].”