Target-Aware Deep Tracking

By Xin Li, Chao Ma, Baoyuan Wu, Zhenyu He, Ming-Hsuan Yang. Computer Vision and Pattern Recognition, 2019

378 citations recorded by the source corpus.

Existing deep trackers mainly use convolutional neural networks pre-trained for the generic object recognition task for representations. Despite demonstrated successes for numerous vision tasks, the contributions of using pre-trained deep features for visual tracking are not as significant as that for object recognition. The key issue is that in visual tracking the targets of interest can be arbitrary object class with arbitrary forms. As such, pre-trained deep features are less effective in modeling these targets of arbitrary forms for distinguishing them from the background. In this paper, we propose a novel scheme to learn target-aware features, which can better recognize the targets undergoing significant appearance variations than pre-trained deep features. To this end, we develop a regression loss and a ranking loss to guide the generation of target-active and scale-sensitive features. We identify the importance of each convolutional filter according to the back-propagated gradients and select the target-aware features based on activations for representing the targets. The target-aware features are integrated with a Siamese matching network for visual tracking. Extensive experimental results show that the proposed algorithm performs favorably against the state-of-the-art methods in terms of accuracy and speed.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/503bafe063e410050c174fcc741e39b3b1e0eb22

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

Invisible Backdoor Attack with Sample-Specific Triggers (2020, background): “Deep neural networks (DNNs) have been widely and successfully adopted in many areas [11, 25, 49, 19].”
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].”
Deep Learning for Visual Tracking: A Comprehensive Survey (2019, methodology): “00GHz CPU, GTX Titan GPU Matlab MatConvNet 33 CM TADT [161] Siamese matching network Conv4-1, Conv4-3 Still images ImageNet DAF Intel I7 3.”
Know Your Surroundings: Exploiting Scene Information for Object Tracking (2020, background): “Most current approaches [3,8,31,34,25,16,37] tackle the problem by learning an appearance model of the target in the initial frame.”
Deep Template-based Object Instance Detection (2021, background): “Many of these tracking approaches propose to use an in-network cross-correlation operation (sometimes denoted as ?d) between a template and an image in feature space [40, 5, 23].”
The Seventh Visual Object Tracking VOT2019 Challenge Results (2019, neutral): “edu The TADT [61] tracker learns target-aware features for robust visual tracking.”
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”
Siamese Box Adaptive Network for Visual Tracking (2020, neutral): “including SiamRPN++ [20], ECO [6], DiMP [2], C-COT [8], ATOM [5], DaSiamRPN [52], TADT [23], C-RPN [10], GradNet [22].”
Exact Adversarial Attack to Image Captioning via Structured Output Learning With Latent Variables (2019, background): “, image classification [15, 33, 32, 31], object detection [9], or object tracking [38, 19]), of which the loss functions are factorized to independent (i.”