Learning Dynamic Siamese Network for Visual Object Tracking

By Qing Guo, Wei Feng, Ce Zhou, Rui Huang, Liang Wan, Song Wang. IEEE International Conference on Computer Vision, 2017

757 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/7574b7e5a75fdd338c27af5aeb77ab79460c4437

How researchers see this paper

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

In Aerospace Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

LaSOT: A High-Quality Benchmark for Large-Scale Single Object Tracking (2018, background): “, MDNet [42], TRACA [5], CFNet [50], SiamFC [4], StructSiam [59], DSiam [16], SINT [49] and VITAL [48]), correlation filter trackers with hand-crafted features (e.”
Target-Aware Deep Tracking (2019, methodology): “The proposed algorithm is compared with the state-of-the-art trackers, including the correlation ﬁlters based trackers, such as SRDCF [9], Staple [1], MCPF [48], CCOT [10], ECO [7], BACF [17], DRT [38], STRCF [22], and MCCT-H [43]; the non-real-time deep trackers such as MDNet [29], CREST [35], LSAR”
Deep Learning for Visual Tracking: A Comprehensive Survey (2019, methodology): “The main contributions of the SNN-based methods are: i) exploiting multi-stage Siamese framework to stimulate hard negative sampling [157], ii) adopting sampling heuristic such as fixed foregroundto-background ratio [157] or sampling strategies such as random sampling [111] or flow-guided sampling [”
AutoTrack: Towards High-Performance Visual Tracking for UAV With Automatic Spatio-Temporal Regularization (2020, methodology): “Compared to deep trackers including ASRCF [31], TADT [51], SiameseFC [15], DSiam [56], MCCT [13], ADNet [16], CFNet [52], DeepSTRCF [14], UDT+ [53], HCF [18], C-COT [17], ECO [20], IBCCF [54], MCPF [19] and CREST [35], AutoTrack with a single CPU exhibits the”
Know Your Surroundings: Exploiting Scene Information for Object Tracking (2020, background): “ECO DSiam StructSiam SiamFC VITAL MDNet SiamRPN++ ATOM DiMP-50 Ours [9] [18] [52] [2] [40] [36] [30] [8] [3]”
Learning Dynamic Memory Networks for Object Tracking (2018, background): “[13] propose a dynamic Siamese network with two general transformations for target appearance variation and background suppression.”
Distractor-aware Siamese Networks for Visual Object Tracking (2018, methodology): “CFNet [33] and DSiam [7] can online update the tracking model via a running average template and a fast transformation learning module, respectively.”
TrackingNet: A Large-Scale Dataset and Benchmark for Object Tracking in the Wild (2018, methodology): “Such trackers are usually trained oﬄine on a large-scale dataset using either deep regression [35] or a CNN matching function [14, 15, 36].”
The Sixth Visual Object Tracking VOT2018 Challenge Results (2018, methodology): “%) applied Siamese networks (ALAL A.2, DensSiam A.23, DSiam A.30, LWDNTm A.41, LWDNTthi A.42, MBSiam A.48, SA Siam P A.59, SA Siam R A.60, SiamFC A.34, SiamRPN A.35, SiamVGG A.63, STST A.66, UpdateNet A.1), 3 trackers (4”
Siam R-CNN: Visual Tracking by Re-Detection (2019, result): “8 shows results on the LaSOT test set [18] (280 videos, 2448 frames average length) compared to nine SOTA methods [5, 16, 37, 50, 60, 4, 78, 22, 15].”
Unsupervised Deep Tracking (2019, methodology): “Trackers SiamFC DCFNet CFNet UDT DSiam EAST HP SA-Siam SiamPRN RASNet SACF Siam-tri RT-MDNet MemTrack StructSiam UDT+ [1] [54] [49] [14] [17] [13] [15] [27] [55] [59] [12] [19] [58] [60]”
Deformable Siamese Attention Networks for Visual Object Tracking (2020, background): “Recent work attempted to enhance the target representation by integrating the features of previous targets [41, 14], but the discriminative context information from the background is ignored.”
ATOM: Accurate Tracking by Overlap Maximization (2018, methodology): “Our tracker outperforms MDNet with relative gains of 14% and STRCF SINT ECO DSiam StructSiam SiamFC VITAL MDNet DaSiam- ATOM [19] [34] [4] [10] [41] [2] [32] [26] RPN[42]”
Transformer Meets Tracker: Exploiting Temporal Context for Robust Visual Tracking (2021, background): “The recent improvements upon Siamese trackers include attention mechanism [54], reinforcement learning [22, 51], target-aware model fine-tuning [30], unsupervised training [50, 52], sophisticated backbone networks [27, 61], cascaded frameworks [14, 49], and model update mechanisms [16, 17, 58, 60].”
SiamCAR: Siamese Fully Convolutional Classification and Regression for Visual Tracking (2019, methodology): “By modifying the Siamese branches with two online transformations, DSiam [31] proposes to learn a dynamic Siamese network, which achieves an improved accuracy with acceptable speed loss.”
Deeper and Wider Siamese Networks for Real-Time Visual Tracking (2019, methodology): “A large amount of follow-up work [7, 12, 13, 20, 40] have been proposed, and they fall into two camps.”
GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wild (2018, methodology): “In this work, we consider siamese tracker SiamFC [46] and its variants CFNet [63], DCFNet [75], DSiam [72], SASiam [76], and SiamDW [78]; recurrent tracker Mem-”
Graph Attention Tracking (2020, positive): “Following this similarity-learning work, many researchers try to enhance the Siamese model for feature representation but still leverage the cross-correlation for information embedding [11, 12, 30, 9].”