Improved Robust Video Saliency Detection Based on Long-Term Spatial-Temporal Information

被引：96

作者：

Chen, Chenglizhao ^{[1
]}

Wang, Guotao ^{[1
]}

Peng, Chong ^{[1
]}

Zhang, Xiaowei ^{[1
]}

Qin, Hong ^{[2
]}

机构：

[1] Qingdao Univ, Coll Comp Sci & Technol, Qingdao 266071, Peoples R China

[2] SUNY Stony Brook, Dept Comp Sci, Stony Brook, NY 11794 USA

来源：

IEEE TRANSACTIONS ON IMAGE PROCESSING | 2020年 / 29卷

基金：

中国国家自然科学基金; 美国国家科学基金会;

关键词：

Saliency detection; Deep learning; Quality assessment; Trajectory; Computational modeling; Color; Training; Video saliency detection; spatial-temporal saliency consistency; low-level saliency clues; long-term information revealing; OBJECT DETECTION; SEGMENTATION; OPTIMIZATION;

D O I：

10.1109/TIP.2019.2934350

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper proposes to utilize supervised deep convolutional neural networks to take full advantage of the long-term spatial-temporal information in order to improve the video saliency detection performance. The conventional methods, which use the temporally neighbored frames solely, could easily encounter transient failure cases when the spatial-temporal saliency clues are less-trustworthy for a long period. To tackle the aforementioned limitation, we plan to identify those beyond-scope frames with trustworthy long-term saliency clues first and then align it with the current problem domain for an improved video saliency detection.

引用

页码：1090 / 1100

页数：11

共 67 条

[1] SLIC Superpixels Compared to State-of-the-Art Superpixel Methods [J].

Achanta, Radhakrishna ;

Shaji, Appu ;

Smith, Kevin ;

Lucchi, Aurelien ;

Fua, Pascal ;

Suesstrunk, Sabine .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2012, 34 (11) :2274-2281

[2] Salient Object Detection: A Benchmark [J].

Borji, Ali ;

Cheng, Ming-Ming ;

Jiang, Huaizu ;

Li, Jia .

IEEE TRANSACTIONS ON IMAGE PROCESSING, 2015, 24 (12) :5706-5722

[3] Structure-Aware Adaptive Diffusion for Video Saliency Detection [J].

Chen, Chenglizhao ;

Wang, Guotao ;

Peng, Chong .

IEEE ACCESS, 2019, 7 :79770-79782

[4] Bilevel Feature Learning for Video Saliency Detection [J].

Chen, Chenglizhao ;

Li, Shuai ;

Qin, Hong ;

Pan, Zhenkuan ;

Yang, Guowei .

IEEE TRANSACTIONS ON MULTIMEDIA, 2018, 20 (12) :3324-3336

[5] A Novel Bottom-Up Saliency Detection Method for Video With Dynamic Background [J].

Chen, Chenglizhao ;

Li, Yunxiao ;

Li, Shuai ;

Qin, Hong ;

Hao, Aimin .

IEEE SIGNAL PROCESSING LETTERS, 2018, 25 (02) :154-158

[6] Video Saliency Detection via Spatial-Temporal Fusion and Low-Rank Coherency Diffusion [J].

Chen, Chenglizhao ;

Li, Shuai ;

Wang, Yongguang ;

Qin, Hong ;

Hao, Aimin .

IEEE TRANSACTIONS ON IMAGE PROCESSING, 2017, 26 (07) :3156-3170

[7] Robust salient motion detection in non-stationary videos via novel integrated strategies of spatio-temporal coherency clues and low-rank analysis [J].

Chen, Chenglizhao ;

Li, Shuai ;

Qin, Hong ;

Hao, Aimin .

PATTERN RECOGNITION, 2016, 52 :410-432

[8] Real-time and robust object tracking in video via low-rank coherency analysis in feature space [J].

Chen, Chenglizhao ;

Li, Shuai ;

Qin, Hong ;

Hao, Aimin .

PATTERN RECOGNITION, 2015, 48 (09) :2885-2905

[9] Structure-Sensitive Saliency Detection via Multilevel Rank Analysis in Intrinsic Feature Space [J].

Chen, Chenglizhao ;

Li, Shuai ;

Qin, Hong ;

Hao, Aimin .

IEEE TRANSACTIONS ON IMAGE PROCESSING, 2015, 24 (08) :2303-2316

[10] SCOM: Spatiotemporal Constrained Optimization for Salient Object Detection [J].

Chen, Yuhuan ;

Zou, Wenbin ;

Tang, Yi ;

Li, Xia ;

Xu, Chen ;

Komodakis, Nikos .

IEEE TRANSACTIONS ON IMAGE PROCESSING, 2018, 27 (07) :3345-3357

← 1 2 3 4 5 6 7 →