Staple: Complementary Learners for Real-Time Tracking

Bertinetto, Luca; Valmadre, Jack; Golodetz, Stuart; Mikšík, Ondřej; Torr, Philip H. S.

doi:10.1109/cvpr.2016.156

Cited by 1,515 publications

(1,166 citation statements)

References 39 publications

Supporting

Mentioning

1,164

Contrasting

Unclassified

Order By: Relevance

“…Therefore, in this paper we compare against 27 trackers which are outlined in Table 2. SRDCF (Danelljan et al 2015), KCF (Henriques et al 2015), LCT (Ma et al 2015), STAPLE (Bertinetto et al 2016a) and DSST (Danelljan et al 2014) are all discriminative trackers based on DCFs. They all performed well in the VOT 2015 (Kristan et al 2015) challenge and DSST was the winner of VOT 2014 (Kristan et al 2014).…”

Section: Model Free Trackingmentioning

confidence: 99%

A Comprehensive Performance Evaluation of Deformable Face Tracking “In-the-Wild”

et al. 2017

View full text Add to dashboard Cite

Recently, technologies such as face detection, facial landmark localisation and face recognition and verification have matured enough to provide effective and efficient solutions for imagery captured under arbitrary conditions (referred to as "in-the-wild"). This is partially attributed to the fact that comprehensive "in-the-wild" benchmarks have been developed for face detection, landmark localisation and recognition/verification. A very important technology that has not been thoroughly evaluated yet is deformable face tracking "in-the-wild". Until now, the performance has mainly been assessed qualitatively by visually assessing the result of a deformable face tracking technology on short videos. In this paper, we perform the first, to the best of our knowledge, thorough evaluation of state-of-theart deformable face tracking pipelines using the recently introduced 300 VW benchmark. We evaluate many different architectures focusing mainly on the task of on-line deformable face tracking. In particular, we compare the following general strategies: (a) generic face detection plus generic facial landmark localisation, (b) generic model free tracking plus generic facial landmark localisation, as well as (c) hybrid approaches using state-of-the-art face detection, model free tracking and facial landmark localisation technologies. Our evaluation reveals future avenues for further research on the topic.

show abstract

Section: Model Free Trackingmentioning

confidence: 99%

A Comprehensive Performance Evaluation of Deformable Face Tracking “In-the-Wild”

et al. 2017

View full text Add to dashboard Cite

show abstract

“…The main attributes of all the experimental sequences can refer to [69]. The proposed SFragT tracker is compared with other state-of-the-art trackers, including DFT [70], LOT [6], CT [11], Struck [18], KCF [22], and Staple [36], which achieve good results on the benchmark. Note that, particularly, KCF and Staple are basically the top trackers at present.…”

Section: Experimental Setup and Evaluation Metricsmentioning

confidence: 99%

“…The HOG feature descriptor [34] is a popular feature descriptor used in visual tracking tasks. Various state-of-the-art object tracking algorithms, such as Struck [18], KCF [22], SDRCF [35], and Staple [36], employ HOG as the feature descriptor. However, HOG is primarily used to describe the edges of an object, which is not robust to the rotation and deformation of objects.…”

Section: Recent Object-representative Developmentsmentioning

confidence: 99%

Structured fragment-based object tracking using discrimination, uniqueness, and validity selection

Zheng

Xin

et al. 2017

Multimedia Systems

View full text Add to dashboard Cite

Local features have widely been used in visual tracking to improve robustness in the presence of partial occlusion, deformation, and rotation. In this paper, a local fragment-based object tracking algorithm is proposed. Unlike many existing fragment-based algorithms using all the fragments and allocating the weight to each fragment according to similarity, the proposed algorithm only selects discriminative, unique, and valid fragments for tracking. First, discrimination and uniqueness metric are defined for each local fragment, and an automatic pre-selection mechanism is proposed for all these fragments. Second, a Harris-SIFT filter is used to select the current valid fragments and exclude the occluded or highly deformed fragments. By selecting the discriminative, unique, and valid fragments, these fragments are used to construct a structured description for the object. Finally, the object tracking is performed using the selected fragments combining the displacement and similarity, as well as spatial constraint of the selected fragments. The object template can be updated by fusing feature similarity and structural consistency. The experimental results on a recent OTB 2013 tracking benchmark data set demonstrate that the proposed algorithm can achieve reliable tracking results even in the presence of significant appearance changes, partial occlusion, and similar disturbances.

show abstract

“…For training the correlation filter, this method used only grayscale samples. To improve the method, according to the results of recent studies multidimensional features such as histogram of Gaussian (HOG) features can be used [10][11][12][13]. Although the correlation filter provides efficient computation, all the circular shifts should be learned during the process.…”

Section: Mathematical Problems In Engineeringmentioning

confidence: 99%

Visual Tracking Based on Complementary Learners with Distractor Handling

Wibowo

Lee

Kim

et al. 2017

Mathematical Problems in Engineering

View full text Add to dashboard Cite

The representation of the object is an important factor in building a robust visual object tracking algorithm. To resolve this problem, complementary learners that use color histogram-and correlation filter-based representation to represent the target object can be used since they each have advantages that can be exploited to compensate the other's drawback in visual tracking. Further, a tracking algorithm can fail because of the distractor, even when complementary learners have been implemented for the target object representation. In this study, we show that, in order to handle the distractor, first the distractor must be detected by learning the responses from the color-histogram-and correlation-filter-based representation. Then, to determine the target location, we can decide whether the responses from each representation should be merged or only the response from the correlation filter should be used. This decision depends on the result obtained from the distractor detection process. Experiments were performed on the widely used VOT2014 and VOT2015 benchmark datasets. It was verified that our proposed method performs favorably as compared with several state-of-the-art visual tracking algorithms.

show abstract

Staple: Complementary Learners for Real-Time Tracking

Cited by 1,515 publications

References 39 publications

A Comprehensive Performance Evaluation of Deformable Face Tracking “In-the-Wild”

A Comprehensive Performance Evaluation of Deformable Face Tracking “In-the-Wild”

Structured fragment-based object tracking using discrimination, uniqueness, and validity selection

Visual Tracking Based on Complementary Learners with Distractor Handling

Contact Info

Product

Resources

About