Accurate Scale Estimation for Robust Visual Tracking

By Martin Danelljan, Gustav Häger, Fahad Shahbaz Khan, Michael Felsberg. 2014

2,059 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

Learning feed-forward one-shot learners (2016, methodology): “An elementary tracker based on learnet compares favourably against recent tracking systems, which make use of different features and online model update strategies: DAT [17], DSST [2], MEEM [22], MUSTer [6] and SO-DLT [21].”
Few-Shot Class-Incremental Learning by Sampling Multi-Phase Tasks (2022, background): “W ITH the rapid development of supervised learning, current learning systems have achieved or even sur-passed human-level performances in many tasks [1], [2], [3], [4], [5], [6].”
Learning Multi-domain Convolutional Neural Networks for Visual Tracking (2015, methodology): “For example, DSST [6] learns separate ﬁl-ters for translation and scaling, and MUSTer [21] employs short-term and long-term memory stores inspired by a psychological memory model.”
Fully-Convolutional Siamese Networks for Object Tracking (2016, methodology): “In addition to the trackers reported by [11], in Figure 3 we also compare against seven more recent state-of-the-art trackers presented in the major computer vision conferences and that can run at frame-rate speed: Staple [33], LCT [34], CCT [35], SCT4 [36], DLSSVM NU [37], DSST [38] and KCFDP [39].”
Hierarchical Deep Temporal Models for Group Activity Recognition (2016, methodology): “For tracking subjects in a scene, we used the tracker by Danelljan et al. [61], implemented in the Dlib library [62].”
Meta-Tracker: Fast and Robust Online Adaptation for Visual Object Trackers (2018, background): “Many hard cases have been tackled by using context information [55, 38], short and long-term memory [35, 23], and scale-estimation [10], just to name a few.”
Need for Speed: A Benchmark for Higher Frame Rate Object Tracking (2017, methodology): “We generally categorized these trackers based on their learning strategy and utilized feature in three classes including CF trackers with hand-crafted features (BACF [15], SRDCF [9], Staple [1], DSST [7], KCF [14], LCT [25], SAMF [22] and CFLB [17]), CF trackers with deep features (HCF [24] and HDT ”
Discriminative Scale Space Tracking (2016, methodology): “We propose the Discriminative Scale Space Tracker (DSST), which is based on learning a separate 1-dimensional scale correlation ﬁlter.”
Learning Dynamic Memory Networks for Object Tracking (2018, methodology): “We compare our method MemTrack with 9 recent real-time trackers (≥ 15 fps), including CFNet [30], LMCF [32], ACFN [5], RFL [36], SiamFC [4], SiamFC U [30], Staple [3], DSST [7], and KCF [15] on both OTB-2013 and OTB-2015.”
LaSOT: A High-Quality Benchmark for Large-Scale Single Object Tracking (2018, background): “, ECO HC [7], DSST [8], CN [11], CSK [19], KCF [20], fDSST [9], SAMF [33], SCT4 [6], STC [57] and Staple [3]) or deep features (e.”
Long-term correlation tracking (2015, methodology): “Unlike [5], we propose to uniformly resize all patches with size P ×Q again and use HOG features to construct the scale feature pyramid.”
Video Relationship Reasoning Using Gated Spatio-Temporal Energy Graph (2019, methodology): “Next, the method described in [5] is used to relate frame-level into a chunk-level object proposals.”
Understanding and Diagnosing Visual Tracking Systems (2015, methodology): “Recent benchmarking studies show that the top-performing trackers are usually discriminative trackers [9, 15] or hybrid ones [43] mainly because purely generative trackers cannot handle complicated background well, making it easy to drift away from the target.”
TrackingNet: A Large-Scale Dataset and Benchmark for Object Tracking in the Wild (2018, methodology): “Since the inception of CF trackers with single-channel features [23, 24], they have been extended with kernels [25], multi-channel features [27] and scale adaptation [28].”
End-to-End Representation Learning for Correlation Filter Based Tracking (2017, methodology): “We also include the recent SAMF [18] and DSST [6] for reference.”
ECO: Efficient Convolution Operators for Tracking (2016, methodology): “The recent advancement in DCF based tracking performance is driven by the use of multi-dimensional features [13, 15], robust scale estimation [7, 11], non-linear kernels [20], long-term memory components [28], sophisticated learning models [3, 10] and reducing boundary effects [9, 16].”
LaSOT: A High-quality Large-scale Single Object Tracking Benchmark (2020, methodology): “The methods of [16, 55] introduce a scale embedding to handle scale variation.”
Unsupervised Deep Tracking (2019, methodology): “We evaluate the proposed UDT and UDT+ trackers with state-of-the-art real-time trackers including ACT [4], ACFN [6], CFNet [49], SiamFC [1], SCT [5], CSR-DCF [32], DSST [8], and KCF [16] using precision and success plots metrics.”
MUlti-Store Tracker (MUSTer): A cognitive psychology inspired approach to object tracking (2015, methodology): “And on top of these, we include recent correlation filter-based trackers CN [7], KCF [16], DSST [6], which is the best performing tracker in [24], and further include very recent state-of-the-art trackers MEEM [50], MTMVTLAD [36] and the LGT [47] based on coupled-layer visual model.”