Real time robust L1 tracker using accelerated proximal gradient approach

By Chenglong Bao, Yi Wu, Haibin Ling, Hui Ji. 2012 IEEE Conference on Computer Vision and Pattern Recognition, 2012

950 citations recorded by the source corpus.

Subfields: Computational Mechanics, Computer Vision and Pattern Recognition, Electrical and Electronic Engineering

View Paper: https://www.semanticscholar.org/paper/8f96aeeeb897367d82146739b4656328c273ab05

How researchers see this paper

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

In Computational Mechanics

In Computer Vision and Pattern Recognition

In Electrical and Electronic Engineering

Citations in the corpus

Object Tracking Benchmark (2015, background): “Furthermore, Mei and Ling [40] proposed a tracking approach based on sparse representation to handle the corrupted appearance and recently it has been further improved [41, 57, 64, 10, 55, 42].”
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].”
The Sixth Visual Object Tracking VOT2018 Challenge Results (2018, background): “L1APG [4] considers tracking as a sparse approximation problem in a particle filter framework.”
Discriminative Scale Space Tracking (2016, methodology): “The trackers used for our comparison are: MIL [18], IVT [27], CT [17], TLD [28], DFT [6], EDFT [29], ASLA [5], L1APG [14], CSK [1], SCM [30], LOT [31], CPF [32], CXT [33], Frag [34], Struck [3], LSHT [4], LSST [35], KCF [9] and SAMF [23].”
Visual Tracking with Fully Convolutional Networks (2015, background): “Recently, sparse coding has been exploited for tracking [21, 3, 32, 31, 30], where the target is reconstructed by a sparse linear combination of target templates.”
Learning to Track: Online Multi-object Tracking by Decision Making (2015, methodology): “This decision making is related to the goal of single object tracking in the literature [3, 15, 16, 5].”
Visual Tracking With Weighted Adaptive Local Sparse Appearance Model via Spatio-Temporal Context Learning (2018, methodology): “Although demonstrated success of the trackers based local sparse appearance model [23], [25], [50], [51], their performance on the recently tracking benchmark [53] is not favorable.”
Adaptive Color Attributes for Real-Time Visual Tracking (2014, methodology): “CT [27] LSST [24] Frag [1] L1APG [2] LOT [18] ASLA [10] TLD [11] SCM [28] EDFT [6] CSK [9] DFT [20] CXT [5] CPF [19] LSHT [8] Struck [7] CN2 CN Median CLE 78.”
Visual Tracking via Locality Sensitive Histograms (2013, methodology): “The others are the recent tracking methods, including the real time L1 tracker (L1T) [3], the super-pixel tracker (SPT) [24], the real-time compressive tracker (CT) [27], the multiple instance learning tracker (MIL) [2], the structured output tracker (Struck) [8], the visual tracking decomposition m”
LaSOT: A High-Quality Benchmark for Large-Scale Single Object Tracking (2018, methodology): “…techniques ( e.g ., BACF [15], SRDCF [10], CSRDCF [36], Staple CA [40] and STRCF [29]), ensemble trackers ( e.g ., PTAV [13], LCT [38], MEEM [56] and TLD [24]), sparse trackers ( e.g ., L1APG [2] and ASLA [23]), other representatives ( e.g ., CT [58], IVT [44], MIL [1] and Struck [17]).”
Real-time part-based visual tracking via adaptive correlation filters (2015, methodology): “We compared the proposed algorithm with thirteen state-of-the-art visual trackers: Frag[1], TLD [21], IVT [34], DFT [35], ORIA [44], LOT [32], CXT [13], L1apg [5], MTT [53], ASLA [20], MIL [4], Struck [16] and KCF [17].”
Overview of Environment Perception for Intelligent Vehicles (2017, methodology): “A total of 278 frames were used and results are obtained with the tracking by detection method,10 the scene flow-based method [157], an L1-based tracking method [158], and a compressive method [159].”
Online Object Tracking: A Benchmark (2013, background): “Furthermore, Mei and Ling [40] proposed a tracking approach based on sparse representation to handle the corrupted appearance and recently it has been further improved [41, 57, 64, 10, 55, 42].”
Transfer Learning Based Visual Tracking with Gaussian Processes Regression (2014, background): “iii) Some work [9,14], based on the part-based model, focuses on selectively updating the parts of the object to handle the tracking drift caused by heavy occlusion; other work [26,3,45] use occlusion detection strategy to determine whether the template should be updated with the new observation.”
The Visual Object Tracking VOT2015 Challenge Results (2015, methodology): “Submitted by VOT Committee L1APG [4] considers tracking as a sparse approximation problem in a particle filter framework.”
Learning a Deep Compact Image Representation for Visual Tracking (2013, methodology): “However, after the bird turns, L1T and TLD totally fail but CT and MIL can recover to some degree.”