Adaptive feature fusion for visual object tracking

Shaochuan Zhao

doi:10.1016/j.patcog.2020.107679

2021-03-01

PRE

DOI：10.1016/j.patcog.2020.107679

原文链接

原文求助

摘要

En 中文

Recent advanced trackers, consisting of discriminative classification component and dedicated bounding box estimation, have achieved improved performance in the visual tracking community. The most essential factor for the development is the utilization of different Convolutional Neural Networks (CNNs), which significantly improves the model capacity via offline trained deep feature representations. Though powerful deep structures emphasize more semantic appearance through high dimensional latent variables, how to achieve effective feature adaptation in the online tracking stage has not been sufficiently considered yet. To this end, we argue the necessity of exploring hierarchical and complementary appearance descriptors from different convolutional layers to achieve online tracking adaptation. Therefore, in this paper, we propose an adaptive feature fusion mechanism, which can balance the detection granularities from shallow to deep convolutional layers. To be specific, the correlation between template and instance is employed to generate adaptive weights to achieve advanced saliency and discrimination. In addition, considering temporal appearance variation, the projection matrix for the multi-channel inputs is jointly updated with the correlation classifier to further enhance the robustness. The experimental results on four recent benchmarks, i.e., OTB-2015, VOT2018, LaSOT and TrackingNet, demonstrate the effectiveness and robustness of the proposed method, with superior performance compared to the state-of-the-art approaches. (C) 2020 Elsevier Ltd. All rights reserved.

Keyword:

Visual tracking

Deep neural network

Feature fusion

Online adaptation

AI总结

对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。

期刊

Pattern Recognition

IF:

7.6

论文数:

1.3W

被引数:

4.5W

机构

Jiangnan University

学者数:

3.9W

论文数: 2.7W

被引数: 4.7W

引用论文

Learning Adaptive Discriminative Correlation Filters via Temporal Consistency Preserving Spatial Feature Selection for Robust Visual Object Tracking

IEEE TRANSACTIONS ON IMAGE PROCESSING

IF13.7

2019-11-01

310

OAAI

Xu, Tianyang; Feng, Zhen-Hua; Wu, Xiao-Jun; Kittler, Josef

ImageNet Large Scale Visual Recognition Challenge ImageNet大规模视觉识别挑战

INTERNATIONAL JOURNAL OF COMPUTER VISION

IF9.3

2015-04-11

2.7W

PREAI

Russakovsky, Olga; Deng, Jia; Su, Hao; Krause, Jonathan; Satheesh, Sanjeev; Ma, Sean; Huang, Zhiheng; Karpathy, Andrej; Khosla, Aditya; Bernstein, Michael; Berg, Alexander C.; Fei-Fei, Li

Targeted mutation of zebrafish fga models human congenital afibrinogenemia

Blood

IF0

2014-04-03

OAAI

Richard J. Fish; Corinne Di Sanza; Marguerite Neerman-Arbez

Multi attention module for visual tracking

PATTERN RECOGNITION

IF7.6

2019-03-01

PREAI

Chen, Boyu; Li, Peixia; Sun, Chong; Wang, Dong; Yang, Gang; Lu, Huchuan