Visual tracking via adaptive structural local sparse appearance model

By Xu Jia, Huchuan Lu, Ming-Hsuan Yang. 2012

1,325 citations recorded by the source corpus.

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

Transferring Rich Feature Hierarchies for Robust Visual Tracking (2015, neutral): “These trackers include Struck [12], SCM [38], TLD [17], ASLA [16], DLT [30] and TGPR [7].”
CoTracker: It is Better to Track Together (2023, background): “However, this approximation is crude as points are often strongly correlated ( e.g ., when they belong to the same object).”
A Scale Adaptive Kernel Correlation Filter Tracker with Feature Integration (2014, methodology): “Success plots of OPE − deformation (19) SAMF [0.624] KCF [0.534] SCM [0.448] DFT [0.439] CN [0.438] Struck [0.393] TLD [0.378] VTD [0.377] LSK [0.377] ASLA [0.372] (c) 0 10 20 30 40 50 0 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9 Location error threshold”
Object Tracking Benchmark (2015, methodology): “On the other hand, stochastic search algorithms such as particle ﬁlters [28, 44] have been widely used since they are relatively insensitive to local minima and computationally efﬁcient [47, 40, 30].”
Track and Segment: An Iterative Unsupervised Approach for Video Object Proposals (2016, methodology): “We first evaluate the quality of our spatio-temporal box proposals against tracking algorithms on the Visual Tracker SCM [59] Struck [20] TLD [26] ASLA [25] CXT [12] VTD [30] VTS [31] TGPR [17] RPT [34] [52] [35] We compare our unsupervised video object box proposals to state-of-the-art supervised t”
Accurate Scale Estimation for Robust Visual Tracking (2014, methodology): “Ours ASLA SCM Struck LSHT Figure 1: A comparison of our method with the state-of-the-art trackers ASLA [14], SCM [20], Struck [9] and LSHT [10] in challenging situations, namely partial occlusions, out-of-plane rotations and illumination variations.”
Beyond Correlation Filters: Learning Continuous Convolution Operators for Visual Tracking (2016, methodology): “We validate our Continuous Convolution Operator Tracker (C-COT) in a comprehensive comparison with 20 state-of-the-art methods: ASLA [25], TLD [26], Struck [21], LSHT [22], EDFT [14], DFT [41], CFLB [18], ACT [13], TGPR [19], KCF [24], DSST [9], SAMF [31], MEEM [47], DAT [40], LCT [36], HCF [35], St”
Understanding and Diagnosing Visual Tracking Systems (2015, methodology): “For example, in the classical mean-shift tracker [7], the observation model must be paired with a probabilistic map as output; in some part-based methods, such as [1, 17], the observation model must be designed in such a way to take the part information into consideration; and in the latest deep lea”
Long-term correlation tracking (2015, methodology): “Struck [9], CT [29], and ASLA [13]); and (iii) tracking by multiple online classifiers (TLD [14], SCM [30], MEEM [27], and TGPR [8]).”
Adaptive Decontamination of the Training Set: A Unified Formulation for Discriminative Visual Tracking (2016, methodology): “We perform a comprehensive comparison with 17 recent state-of-the-art trackers: EDFT [7], LSHT [12], DFT [24], ASLA [15], TLD [16], Struck [11], CFLB [8], ACT [6], TGPR [9], KCF [13], DSST [2], SAMF [19], DAT [23], MEEM [29], LCT [22], HCF [21] and SRDCF [5].”
Sparse coding based visual tracking: Review and experimental comparison (2013, methodology): “For AMSC, we select BRD [21], OLSR [41], and SLSA [42].”
MUlti-Store Tracker (MUSTer): A cognitive psychology inspired approach to object tracking (2015, background): “29 popular approaches whose results are available in OOTB, such as Struck [14], TLD [23], SCM [52], VTD [26], VTS [27], and ASLA [22].”
Convolutional Features for Correlation Filter Based Visual Tracking (2015, background): “These scores Overlap threshold 0 0.2 0.4 0.6 0.8 1 O v e rl a p P re c is io n [ % ] 0 20 40 60 80 Success plot of scale variation (28) DeepSRDCF [63.6] DeepDCF [60.0] SRDCF [59.3] DSST [55.2] SAMF [52.0] MEEM [50.7] ASLA [49.7] Struck [43.1] KCF [42.8] TGPR [42.4] Overlap threshold 0 0.2 0.4 0.6 0.”
Learning a Deep Compact Image Representation for Visual Tracking (2013, methodology): “As of now, there is very little relevant work, with the possible exception of [11] which tries to improve the pooling step in the sparse coding literature to address this issue.”
Visual Tracking with Fully Convolutional Networks (2015, methodology): “Based on the discrimination rule, when distracters are detected using (9), SNet is further updated using the tracking results in the first frame and the current frame by minimizing min βW S 2 F + x,y ˆ M 1 S (x, y) − M 1 (x, y) 2 + 1 − Φ t (x, y) ˆ M t S (x, y) − M t (x, y) 2 , (10) where W S denote”
Reliable Patch Trackers: Robust visual tracking by exploiting reliable patches (2015, background): “Despite having achieved promising progress over the past decade, it remains very challenging for designing an all-situation-handled tracker that can handle various critical situations, such as illumination changes, geometric deformations, fast motions, partial occlusion, and background clutters,…”