Robust Fragments-based Tracking using the Integral Histogram

By Amit Adam, Ehud Rivlin, Ilan Shimshoni. Computer Vision and Pattern Recognition, 2006

1,552 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/15cd7d675e499d6e53014916d7cf4a1714341f6a

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

Robust Visual Tracking via Structured Multi-Task Sparse Learning (2012, methodology): “…(Black and Jepson 1998), mean shift tracker (Comaniciu et al. 2003), appearance model based tracker (Jepson et al. 2003), context-aware tracker (Yang et al. 2009), fragment-based tracker (Frag) (Adam et al. 2006), incremental tracker (IVT) (Ross et al. 2008), and VTD tracker (Kwon and Lee 2010).”
Learning a Deep Compact Image Representation for Visual Tracking (2013, methodology): “The resulting tracker would be similar to previous patch (or fragment) based methods [1, 11] which have been shown to be robust against partial occlusion.”
Robust visual tracking via multi-task sparse learning (2012, methodology): “Other methods (IVT, L 1 , L ∞1 , OAB, MIL, and Frag) fail to track the object reliably.”
UvA-DARE (Digital Academic Repository) Siamese Instance Search for Tracking (2016, methodology): “FRT [1] uses the earth mover’s distance matching.”
Tracking the Untrackable: Learning to Track Multiple Cues with Long-Term Dependencies (2017, result): “Recently, Xiang et al. [69] have shown that learning a representation would improve the similarity score of a tracking framework and outperform previous works by a large margin.”
Correlation filters with limited boundaries (2014, methodology): “MOSSE KMOSSE MILTrack STRUCK OAB(1) SemiBoost FragTrack Our method [5] [13] [3] [11] [9] [10] [1] FaceOcc1 {1.”
Struck: Structured Output Tracking with Kernels (2016, positive): “Table 1 shows the results obtained by our tracking framework for various budget sizes B, along with published results from existing state-of-the-art approaches [2]–[4], [42], [43], and example frames can be seen in Figure 2.”
Siamese Instance Search for Tracking (2016, methodology): “FRT [1] uses the earth mover’s distance matching.”
Struck: Structured output tracking with kernels (2011, neutral): “This is combined with an intersection kernel: k(x, ¯ x) = 1 D D i=1 min(x i , ¯ x i ).”
Reliable Patch Trackers: Robust visual tracking by exploiting reliable patches (2015, background): “Adam et al. [1] proposed to represent the object by the grid of fragments, where the target position is voted from these fragments.”
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].”
Context tracker: Exploring supporters and distracters in unconstrained environments (2011, methodology): “For example, FragTracker [1] and MILTracker [3] use exhaustive search in a small area.”
Visual Tracking With Weighted Adaptive Local Sparse Appearance Model via Spatio-Temporal Context Learning (2018, background): “Generally, the representations for constructing generative appearance models include GMMs [39], color histograms [40], subspace representation [19], and sparse representation [22], [23],”
Sparse coding based visual tracking: Review and experimental comparison (2013, methodology): “In addition, we also select ﬁve baseline trackers, Frag [60], IVT [4], MIL [13], OAB [11] and CT [55] for comparison.”
Visual tracking via adaptive structural local sparse appearance model (2012, methodology): “The proposed approach is compared with six state-of-the-art tracking methods including incremental visual tracking (IVT) method [18], fragment-based (FragTrack) tracking method [1], l1 tracker (l1) [16], multiple instance learning (MIL) tracker [3], visual tracking decomposition (VTD) method [10] an”
Learning Spatially Regularized Correlation Filters for Visual Tracking (2015, methodology): “We provide a comparison of our tracker with 24 state-of-the-art methods from the literature: MIL [2], IVT [28], CT [36], TLD [22], DFT [29], EDFT [12], ASLA [21], L1APG [3], CSK [19], SCM [37], LOT [26], CPF [27], CXT [11], Frag [1], Struck [16], LSHT [17], LSST [32], ACT [10], KCF [20], CFLB [14], ”
PROST: Parallel robust online simple tracking (2010, background): “Sylvester[16] 1344 3D-motion, varying illumination Faceocc1 [ 1 ] 886 moving camera, occlusions Faceocc2 [3] 812 occlusions, heavy appearance change”