Q. Wang, L. Zhang, and K. Kpalma, Fast filtering-based temporal saliency detection using Minimum Barrier Distance, 2017 IEEE International Conference on Multimedia & Expo Workshops, ICME Workshops, pp.232-237, 2017.
URL : https://hal.archives-ouvertes.fr/hal-01637078

W. Qiong, L. Zhang, and K. Kpalma, The 1st Large-scale Video Object Segmentation Challenge Workshop in conjunction with ECCV2018

Ç. Aytekin, H. Possegger, T. Mauthner, S. Kiranyaz, H. Bischof et al., Spatiotemporal Saliency Estimation by Spectral Foreground Detection, IEEE Trans. Multimedia, vol.20, pp.82-95, 2018.

S. Baker, J. P. Scharstein, S. Lewis, M. J. Roth, R. Black et al., A Database and Evaluation Methodology for Optical Flow, International Journal of Computer Vision, vol.92, pp.1-31, 2011.

S. Bhattacharya, K. Venkatesh, S. Subramanian, and . Gupta, Visual Saliency Detection Using Spatiotemporal Decomposition, IEEE Trans. Image Processing, vol.27, pp.1665-1675, 2018.

L. Xiu, C. Bi, and . Pun, Fast copy-move forgery detection using local bidirectional coherency error refinement, Pattern Recognition, vol.81, pp.161-175, 2018.

A. Borji, M. Cheng, H. Jiang, and J. Li, Salient Object Detection: A Benchmark, IEEE Trans. Image Processing, vol.24, pp.5706-5722, 2015.

A. Borji, M. Cheng, H. Jiang, and J. Li, Salient Object Detection: A Survey, 2014.

T. Brox and J. Malik, Large Displacement Optical Flow: Descriptor Matching in Variational Motion Estimation, IEEE Trans. Pattern Anal. Mach. Intell, vol.33, issue.3, pp.500-513, 2011.

T. Brox and J. Malik, Object Segmentation by Long Term Analysis of Point Trajectories, Computer Vision -ECCV 2010 -11th European Conference on Computer Vision, pp.282-295, 2010.

K. Sergi-caelles, J. Maninis, L. Pont-tuset, D. Leal-taixé, L. Cremers et al., One-Shot Video Object Segmentation, 2017 IEEE Conference on Computer Vision and Pattern Recognition, pp.5320-5329, 2017.

A. Sergi-caelles, K. Montes, Y. Maninis, L. Chen, F. Van-gool et al., The 2018 DAVIS Challenge on Video Object Segmentation, 2018.

J. Sergi-caelles, F. Pont-tuset, A. Perazzi, K. Montes, L. Maninis et al., The 2019 DAVIS Challenge on VOS: Unsupervised Multi-Object Segmentation, 2019.

I. Cassagne, N. Riche, M. Decombas, M. Mancas, B. Gosselin et al., Video saliency based on rarity prediction: Hyperaptor". In: 23rd European Signal Processing Conference, pp.1521-1525, 2015.

C. Chen, S. Li, H. Qin, Z. Pan, and G. Yang, Bilevel Feature Learning for Video Saliency Detection, IEEE Trans. Multimedia, vol.20, pp.3324-3336, 2018.

C. Chen, S. Li, Y. Wang, H. Qin, and A. Hao, Video Saliency Detection via Spatial-Temporal Fusion and Low-Rank Coherency Diffusion, IEEE Trans. Image Processing, vol.26, pp.3156-3170, 2017.

C. Chen, Y. Li, S. Li, H. Qin, and A. Hao, A Novel Bottom-Up Saliency Detection Method for Video With Dynamic Background, IEEE Signal Process. Lett, vol.25, pp.154-158, 2018.

L. Chen, G. Papandreou, I. Kokkinos, K. Murphy, and A. L. Yuille, DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs, IEEE Trans. Pattern Anal. Mach. Intell, vol.40, pp.834-848, 2018.

Y. Chen, W. Zou, Y. Tang, X. Li, C. Xu et al., SCOM: Spatiotemporal Constrained Optimization for Salient Object Detection, IEEE Trans. Image Processing, vol.27, pp.3345-3357, 2018.

J. Cheng, Y. Tsai, S. Wang, and M. Yang, SegFlow: Joint Learning for Video Object Segmentation and Optical Flow, IEEE International Conference on Computer Vision, pp.686-695, 2017.

R. Cong, J. Lei, H. Fu, M. Cheng, W. Lin et al., Review of Visual Saliency Detection with Comprehensive Information, 2018.

M. Decombas, N. Riche, F. Dufaux, B. Pesquet-popescu, M. Mancas et al., Spatio-temporal saliency based on rare model, IEEE International Conference on Image Processing, ICIP 2013, pp.3451-3455, 2013.
URL : https://hal.archives-ouvertes.fr/hal-01436250

A. Dosovitskiy, P. Fischer, E. Ilg, P. Häusser, C. Hazirbas et al., FlowNet: Learning Optical Flow with Convolutional Networks, 2015 IEEE International Conference on Computer Vision, ICCV 2015, pp.2758-2766, 2015.

L. Duan, T. Xi, S. Cui, H. Qi, and A. C. Bovik, A spatiotemporal weighted dissimilarity-based method for video saliency detection, Sig. Proc.: Image Comm, vol.38, pp.45-56, 2015.

E. Salehe-erfanian-ebadi and . Izquierdo, Foreground Segmentation with Tree-Structured Sparse RPCA, IEEE Trans. Pattern Anal. Mach. Intell, vol.40, pp.2273-2280, 2018.

A. Faktor and M. Irani, Video Segmentation by Non-Local Consensus voting, British Machine Vision Conference, 2014.

D. Fan, W. Wang, M. Cheng, and J. Shen, Shifting more attention to video salient object detection, 2019 IEEE Conference on Computer Vision and Pattern Recognition, pp.8554-8564, 2019.

Y. Fang, Z. Wang, W. Lin, and Z. Fang, Video Saliency Incorporating Spatiotemporal Cues and Uncertainty Weighting, IEEE Trans. Image Processing, vol.23, pp.3910-3921, 2014.

K. Fukuchi, K. Miyazato, A. Kimura, S. Takagi, and J. Yamato, Saliency-based video segmentation with graph cuts and sequentially updated priors, Proceedings of the 2009 IEEE International Conference on Multimedia and Expo, pp.638-641, 2009.

F. Guo, W. Wang, J. Shen, L. Shao, J. Yang et al., Video Saliency Detection Using Object Proposals, IEEE Trans. Cybernetics, vol.48, pp.3159-3170, 2018.

J. Han, D. Zhang, G. Cheng, N. Liu, and D. Xu, Advanced Deep-Learning Techniques for Salient and Category-Specific Object Detection: A Survey, IEEE Signal Process. Mag, vol.35, pp.84-100, 2018.

K. He, G. Gkioxari, P. Dollár, and R. B. Girshick, Mask R-CNN, IEEE International Conference on Computer Vision, pp.2980-2988, 2017.

K. He, J. Sun, and X. Tang, Guided Image Filtering, Computer Vision -ECCV 2010, 11th European Conference on Computer Vision, Heraklion, pp.1-14, 2010.

K. He, X. Zhang, S. Ren, and J. Sun, Deep Residual Learning for Image Recognition, 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016, pp.770-778, 2016.

Y. Hu, R. Song, and Y. Li, Efficient Coarse-to-Fine Patch Match for Large Displacement Optical Flow, 2016 IEEE Conference on Computer Vision and Pattern Recognition, pp.5704-5712, 2016.

E. Ilg, N. Mayer, T. Saikia, M. Keuper, A. Dosovitskiy et al., FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks, 2017 IEEE Conference on Computer Vision and Pattern Recognition, pp.1647-1655, 2017.

S. Ioffe and C. Szegedy, Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift, Proceedings of the 32nd International Conference on Machine Learning, pp.448-456, 2015.

B. Jiang, L. Zhang, H. Lu, C. Yang, and M. Yang, Saliency Detection via Absorbing Markov Chain, 2013 IEEE International Conference on Computer Vision, ICCV 2013, pp.1665-1672, 2013.

R. Kannan, G. Ghinea, and S. Swaminathan, Discovering salient objects from videos using spatiotemporal salient region detection, Sig. Proc.: Image Comm, vol.36, pp.154-178, 2015.

A. Khoreva, B. Benenson, E. Ilg, T. Brox, and B. Schiele, Lucid Data Dreaming for Video Object Segmentation, The 2018 DAVIS Challenge on Video Object Segmentation -CVPR Workshops, 2018.

H. Kim, Y. Kim, J. Sim, and C. Kim, Spatiotemporal Saliency Detection for Video Sequences Based on Random Walk With Restart, IEEE Trans. Image Processing, vol.24, pp.2552-2564, 2015.

T. Le, K. Nguyen, M. Nguyen-phan, T. Ton, and T. Nguyen, Instance Re-Identification Flow for Video Object Segmentation, p.2017

T. Le and A. Sugimoto, Deeply Supervised 3D Recurrent FCN for Salient Object Detection in Videos, British Machine Vision Conference, 2017.

T. Le and A. Sugimoto, Semantic Instance Meets Salient Object: Study on Video Semantic Salient Instance Segmentation, IEEE Winter Conference on Applications of Computer Vision, 2019.

T. Le and A. Sugimoto, SpatioTemporal utilization of deep features for video saliency detection, 2017 IEEE International Conference on Multimedia & Expo Workshops, ICME Workshops, pp.465-470, 2017.

T. Le and A. Sugimoto, Video Salient Object Detection Using Spatiotemporal Deep Features, IEEE Trans. Image Processing, vol.27, pp.5002-5015, 2018.

G. Lee, Y. Tai, and J. Kim, Deep Saliency with Encoded Low Level Distance Map and High Level Features, 2016 IEEE Conference on Computer Vision and Pattern Recognition, pp.660-668, 2016.

F. Li, T. Kim, A. Humayun, D. Tsai, and J. M. Rehg, Video Segmentation by Tracking Many Figure-Ground Segments, IEEE International Conference on Computer Vision, ICCV 2013, pp.2192-2199, 2013.

G. Li and Y. Yu, Deep Contrast Learning for Salient Object Detection, 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016, pp.478-487, 2016.

G. Li and Y. Yu, Visual Saliency Detection Based on Multiscale Deep CNN Features, IEEE Trans. Image Processing, vol.25, pp.5012-5024, 2016.

J. Li, C. Xia, and X. Chen, A Benchmark Dataset and SaliencyGuided Stacked Autoencoders for Video-Based Salient Object Detection, IEEE Trans. Image Processing, vol.27, pp.349-364, 2018.

J. Li, A. Zheng, X. Chen, and B. Zhou, Primary Video Object Segmentation via Complementary CNNs and Neighborhood Reversible Flow, IEEE International Conference on Computer Vision, pp.1426-1434, 2017.

X. Li, Y. Qi, Z. Wang, K. Chen, Z. Liu et al., Video Object Segmentation with Reidentification, The 2017 DAVIS Challenge on Video Object Segmentation -CVPR Workshops, 2017.

N. Liu and J. Han, DHSNet: Deep Hierarchical Saliency Network for Salient Object Detection, 2016 IEEE Conference on Computer Vision and Pattern Recognition, pp.678-686, 2016.

T. Liu, Z. Yuan, J. Sun, J. Wang, N. Zheng et al., Learning to Detect a Salient Object, IEEE Trans. Pattern Anal. Mach. Intell, vol.33, pp.353-367, 2011.

Z. Liu, J. Li, L. Ye, G. Sun, and L. Shen, Saliency Detection for Unconstrained Videos Using Superpixel-Level Graph and Spatiotemporal Propagation, IEEE Trans. Circuits Syst. Video Techn. 27, vol.12, pp.2527-2542, 2017.

J. Luiten, P. Voigtlaender, and B. Leibe, PReMVOS: Proposalgeneration, Refinement and Merging for the DAVIS Challenge on Video Object Segmentation, The 2018 DAVIS Challenge on Video Object Segmentation -CVPR Workshops, 2018.

Y. Luo, J. Yuan, and J. Lu, Finding spatio-temporal salient paths for video objects discovery, J. Visual Communication and Image Representation, vol.38, pp.45-54, 2016.

Z. Luo, A. Kumar-mishra, A. Achkar, J. A. Eichel, S. Li et al., Non-local Deep Features for Salient Object Detection, 2017 IEEE Conference on Computer Vision and Pattern Recognition, pp.6593-6601, 2017.

M. Habib-mahmood, Y. Diez, J. Salvi, and X. Lladó, A collection of challenging motion segmentation benchmark datasets, Pattern Recognition, vol.61, pp.1-14, 2017.

K. Maninis, S. Caelles, Y. Chen, J. Pont-tuset, L. Lealtaixé et al., Video Object Segmentation Without Temporal Information, 2017.

N. Mayer, E. Ilg, P. Häusser, P. Fischer, D. Cremers et al., A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation, 2016 IEEE Conference on Computer Vision and Pattern Recognition, pp.4040-4048, 2016.

F. Milletari, N. Navab, and S. Ahmadi, V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation, Fourth International Conference on 3D Vision, vol.3, pp.565-571, 2016.

R. Mottaghi, X. Chen, X. Liu, N. Cho, S. Lee et al., The Role of Context for Object Detection and Semantic Segmentation in the Wild, 2014 IEEE Conference on Computer Vision and Pattern Recognition, pp.891-898, 2014.

P. Ochs, J. Malik, and T. Brox, Segmentation of Moving Objects by Long Term Video Analysis, IEEE Trans. Pattern Anal. Mach. Intell, vol.36, issue.6, pp.1187-1200, 2014.

A. Papazoglou and V. Ferrari, Fast Object Segmentation in Unconstrained Video, IEEE International Conference on Computer Vision, ICCV 2013, pp.1777-1784, 2013.

H. Peng, B. Li, W. Xiong, W. Hu, and R. Ji, RGBD Salient Object Detection: A Benchmark and Algorithms, Computer Vision -ECCV 2014 -13th European Conference, pp.92-109, 2014.

F. Perazzi, A. Khoreva, R. Benenson, B. Schiele, and A. Sorkine-hornung, Learning Video Object Segmentation from Static Images, 2017 IEEE Conference on Computer Vision and Pattern Recognition, pp.3491-3500, 2017.

F. Perazzi, J. Pont-tuset, B. Mcwilliams, J. Luc, M. H. Van-gool et al., A Benchmark Dataset and Evaluation Methodology for Video Object Segmentation, 2016 IEEE Conference on Computer Vision and Pattern Recognition, pp.724-732, 2016.

J. Pont-tuset, F. Perazzi, S. Caelles, P. Arbeláez, A. Sorkine-hornung et al., The 2017 DAVIS Challenge on Video Object Segmentation, 2017.

E. Rahtu, J. Kannala, M. Salo, and J. Heikkilä, Segmenting Salient Objects from Images and Videos, Computer Vision -ECCV 2010 -11th European Conference on Computer Vision, pp.366-379, 2010.

H. Ramadan and H. Tairi, Pattern mining-based video saliency detection: Application to moving object segmentation, Computers & Electrical Engineering, vol.70, pp.567-579, 2018.

A. Rosenfeld and J. L. Pfaltz, Distance functions on digital pictures, Pattern Recognition, vol.1, pp.33-61, 1968.

K. Simonyan and A. Zisserman, Very Deep Convolutional Networks for Large-Scale Image Recognition, 2014.

H. Song, W. Wang, S. Zhao, J. Shen, and K. Lam, Pyramid Dilated Deeper ConvLSTM for Video Salient Object Detection, Computer Vision -ECCV 2018 -15th European Conference, pp.744-760, 2018.

J. Sun, D. Yu, Y. Li, and C. Wang, Mask Propagation Network for Video Object Segmentation, The 2018 DAVIS Challenge on Video Object Segmentation -CVPR Workshops, 2018.

Y. Tang, W. Zou, Z. Jin, Y. Chen, Y. Hua et al., Weakly Supervised Salient Object Detection with Spatiotemporal Cascade Neural Networks, IEEE Trans. Circuits Syst. Video Techn, 2018.

P. Tokmakov, K. Alahari, and C. Schmid, Learning Motion Patterns in Videos, 2017 IEEE Conference on Computer Vision and Pattern Recognition, pp.531-539, 2017.
URL : https://hal.archives-ouvertes.fr/hal-01427480

P. Tokmakov, K. Alahari, and C. Schmid, Learning Video Object Segmentation with Visual Memory, pp.4491-4500, 2017.
URL : https://hal.archives-ouvertes.fr/hal-01511145

S. Tripathi, Y. Hwang, S. J. Belongie, and T. Q. Nguyen, Improving streaming video segmentation with early and mid-level visual processing, IEEE Winter Conference on Applications of Computer Vision, pp.477-484, 2014.

W. Tu, S. He, Q. Yang, and S. Chien, Real-Time Salient Object Detection with a Minimum Spanning Tree, 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016, pp.2334-2342, 2016.

Z. Tu, A. Abel, L. Zhang, B. Luo, and A. Hussain, A New Spatio-Temporal Saliency-Based Video Object Segmentation, Cognitive Computation, vol.8, pp.629-647, 2016.

Z. Tu, Z. Guo, W. Xie, M. Yan, C. Remco et al., Fusing disparate object signatures for salient object detection in video, Pattern Recognition, vol.72, pp.285-299, 2017.

P. Voigtlaender and B. Leibe, Online Adaptation of Convolutional Neural Networks for Video Object Segmentation, British Machine Vision Conference 2017, 2017.

L. Wang, H. Lu, X. Ruan, and M. Yang, Deep networks for saliency detection via local estimation and global search, IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015, pp.3183-3192, 2015.

L. Wang, H. Lu, Y. Wang, M. Feng, D. Wang et al., Learning to Detect Salient Objects with Image-Level Supervision, 2017 IEEE Conference on Computer Vision and Pattern Recognition, pp.3796-3805, 2017.

L. Wang, L. Wang, H. Lu, P. Zhang, and X. Ruan, Saliency Detection with Recurrent Fully Convolutional Networks, Computer Vision -ECCV 2016 -14th European Conference, pp.825-841, 2016.

W. Wang, J. Shen, and F. Porikli, Saliency-aware geodesic video object segmentation, IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015, pp.3395-3402, 2015.

W. Wang, J. Shen, and L. Shao, Consistent Video Saliency Using Local Gradient Flow Optimization and Global Refinement, IEEE Trans. Image Processing, vol.24, pp.4185-4196, 2015.

W. Wang, J. Shen, and L. Shao, Video Salient Object Detection via Fully Convolutional Networks, IEEE Trans. Image Processing, vol.27, pp.38-49, 2018.

W. Wang, J. Shen, R. Yang, and F. Porikli, SaliencyAware Video Object Segmentation, IEEE Trans. Pattern Anal. Mach. Intell, vol.40, pp.20-33, 2018.

X. Wei, L. Song, R. Xie, and W. Zhang, Two-stream recurrent convolutional neural networks for video saliency estimation, 2017 IEEE International Symposium on Broadband Multimedia Systems and Broadcasting, pp.1-5, 2017.

T. Xi, W. Zhao, H. Wang, and W. Lin, Salient Object Detection With Spatiotemporal Background Priors for Video, IEEE Trans. Image Processing, vol.26, pp.3425-3436, 2017.

H. Xiao, J. Feng, G. Lin, Y. Liu, and M. Zhang, MoNet: Deep Motion Exploitation for Video Object Segmentation, 2018 IEEE Conference on Computer Vision and Pattern Recognition, pp.1140-1148, 2018.

C. Li, Video Object Segmentation with Joint Re-identification and Attention-Aware Mask Propagation, The 2018 DAVIS Challenge on Video Object Segmentation -CVPR Workshops, 2018.

N. Xu, L. Yang, Y. Fan, D. Yue, Y. Liang et al., YouTube-VOS: A Large-Scale Video Object Segmentation Benchmark, 2018.

S. Xu, L. Bao, and P. Zhou, Class-Agnostic Video Object Segmentation without Semantic Re-Identification, The 2018 DAVIS Challenge on Video Object Segmentation -CVPR Workshops, 2018.

F. Yan, Autonomous vehicle routing problem solution based on artificial potential field with parallel ant colony optimization (ACO) algorithm, Pattern Recognition Letters, vol.116, pp.195-199, 2018.

Q. Yan, L. Xu, J. Shi, and J. Jia, Hierarchical Saliency Detection, 2013 IEEE Conference on Computer Vision and Pattern Recognition, pp.1155-1162, 2013.

B. Yang, X. Zhang, L. Chen, and Z. Gao, Spatiotemporal salient object detection based on distance transform and energy optimization, Neurocomputing, vol.266, pp.165-175, 2017.

C. Yang, L. Zhang, H. Lu, X. Ruan, and M. Yang, Saliency Detection via Graph-Based Manifold Ranking, 2013 IEEE Conference on Computer Vision and Pattern Recognition, pp.3166-3173, 2013.

Y. Zhai and M. Shah, Visual attention detection in video sequences using spatiotemporal cues, Proceedings of the 14th ACM International Conference on Multimedia, pp.815-824, 2006.

J. Zhang, S. Sclaroff, Z. L. Lin, X. Shen, B. L. Price et al., Minimum Barrier Salient Object Detection at 80 FPS, 2015 IEEE International Conference on Computer Vision, ICCV 2015, pp.1404-1412, 2015.

R. Zhao, W. Ouyang, H. Li, and X. Wang, Saliency detection by multi-context deep learning, IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015, pp.1265-1274, 2015.

X. Zhou, Z. Liu, C. Gong, and W. Liu, Improving Video Saliency Detection via Localized Estimation and Spatiotemporal Refinement, IEEE Trans. Multimedia, vol.20, pp.2993-3007, 2018.

X. Zhou, Z. Liu, K. Li, and G. Sun, Video saliency detection via bagging-based prediction and spatiotemporal propagation, J. Visual Communication and Image Representation, vol.51, pp.131-143, 2018.

, 3 A comparison of video SOD, video semantic salient object segmentation and video object instance segmentation

, Some examples of saliency maps generated by the proposed VBGF, p.24

, Some examples of saliency maps generated by VBGFd, p.25

, Some examples of segmentation maps generated by SWVOS, p.26

.. .. Examples,

, Some examples are given for each dataset

, Methods classification based on low-level cues

, Methods classification based on fusion ways

, Minimum barrier distance transform with the Raster Scan, (c) Final result

, Minimum barrier distance transform with the minimum spanning tree, (c) Boundary index (the boundary is divided into three groups according to their color values), (d) Boundary dissimilarity map

, Result without update processing, (c) Result with update processing

]. .. , State-of-the-art saliency maps, p.42

, Color optical flow map of the input frame, (c) Optical flow gradient magnitude, (d) Superpixel segmentation, (e) Gradient magnitude of (d), (f) Spatio-temporal gradient field by fusing (c) and (e) in a non-linear way

, Color optical flow map of the input frame, (c) Static edge probability map, (d) Superpixel segmentation, (e) Motion boundary of (b) , (f) Spatio-temporal edge probability map by combining (c), (d) and (e), (g) Final result

, 46 2.10 RWR15 [39]. (a) Input frame, (b) Saliency map generated by the random walk simulation without employing temporal information as restarting distributions, (c) Saliency map generated by the random walk simulation with employing temporal information as restarting distributions

, Contrast-based saliency, (c) Pos region (salient) are denoted by blue color, Neg region (non salient) are denoted by red color and Unk region (undeterministic) are denoted by white color

]. .. , State-of-the-art saliency maps, p.48

, Better viewed in color) P-R curves of proSSM, proTSM and proSTSM over the Fukuchi dataset and FBMS dataset. proSSM: proposed spatial saliency map; proTSM: proposed temporal saliency map; proSTSM: proposed spatio-temporal saliency map, The proposed block-diagram. SD: Spatial saliency detection; SSM: Spatial saliency map; TD: Temporal saliency detection; TSM: Temporal saliency map; STSM: Spatio-temporal saliency

, Quantitative comparisons between our method (VBGF) and six video SOD models over the Fukuchi dataset. (a) show the P-R curves, (b) shows the F-measure scores ? and (c) shows MAE scores ?. Some state-of-the-art methods, p.66

, Quantitative comparisons between our method (VBGF) and five video SOD models over the FBMS dataset. (a) show the P-R curves, (b) shows the F-measure scores ? and (c) shows the MAE scores ?. Some state-of-the-art methods, p.68

, (a)-(f) are 6 different video sequences. Some state-of-the-art methods, Comparison of the saliency maps

, (g)-(k) are 5 different video sequences. Some state-of-the-art methods, Comparison of the saliency maps

, Methods classification according to the deep representations generation 78

. .. Osvos, Multi-tasks models: (a) WSS, (b) SegFlow and (c), p.80

. .. Scnn, Single-task models: (a) SFCN and (b), p.81

. .. Lvo, Single-task models: (a) NRF, (b) DHSNet and LMP, p.83

. .. Encoder-decoder-network, Better viewed in color) Performances on the VOS-E dataset: (a) Fmeasure?, Precision?, Recall?, (b) MAE?, (c) P-R curve. ? means the higher the better and ? means the lower the better, vol.84

. F-measure?, . Precision?, . Recall?, and .. .. Mae?,-(c)-p-r-curve, Better viewed in color) Performances on the VOS-N dataset: (a) Fmeasure?, Precision?, Recall?, (b) MAE?, (c) P-R curve, Better viewed in color) Performances on the FBMS dataset: (a)

, Better viewed in color) Performances on the DAVIS-2016-val dataset: (a) F-measure?, Precision?, Recall?, (b) MAE?, (c) P-R curve, p.94

, Better viewed in color) Performances on the DAVIS-2017-val dataset: (a) F-measure?, Precision?, Recall?, (b) MAE?, (c) P-R curve, p.95

, 13 (Better viewed in color) MAE performance?, vol.3

, 14 (Better viewed in color) Precision performance?

, 15 (Better viewed in color) Recall performance?

. .. , 16 (Better viewed in color) F-measure performance?, vol.3, p.99

, Examples of saliency maps for cases of failure

, SD: Spatial saliency detection; SSM: Spatial saliency map; TD: Temporal saliency detection; TSM: Temporal saliency map; STSM: Spatio-temporal saliency map

, An overview of OSVOS: the designed network is firstly trained to learn the generic objects, and then fine-tuned to learn the target object. (b) The designed network

, The first row shows the result without updating, the second row gives the online selected training example and the third shows the result with updating

, The proposed block-diagram SWVOS

, One example of the warping confidence computation. The target object is denoted in red box in (a)

, The target object is denoted in red box in (a)

. .. Datasets, 29 2.1 A table comparing the our method (VBGF) and six video SOD models in MAE ? and F-measure ? scores over 4 video sequences chosen from the Fukuchi dataset. The Bold number indicates the best result, Comparison between various test

, Average run time (per frame) of our proposed method (VBGF) and the compared models

. .. , Comparison of the existing survey/benchmark for SOD, p.76

T. Backbone and . Datasets, x" indicates that the method is not based on any backbone or the method is off-the-shelf deep features based)

, Area of each method in the Fig 3.14. (The best score is in bold), p.97

, Area of each method in the Fig 3.15. (The best score is in bold), p.98

, Area of each method in the Fig 3.16. (The best score is in bold), p.99

, Average run time in seconds (per frame) of the compared models. (The best score is in bold)

, Comparison of the proposed VBGFd componets' performance on dataset VOS, VOS-E, VOS-N. proSSM: proposed spatial saliency map; proTSM: proposed temporal saliency map; proSTSM: proposed spatio-temporal saliency map. The Bold number indicates the best result in each line, p.103

, Performance benchmarking of VBGFd, and VBGF, and 13 state-of-theart models on the dataset VOS-E. The best three scores in each column are marked in red, green and blue

. .. , 105 3.10 Performance benchmarking of VBGFd, and VBGF, and 13 state-of-theart models on the dataset VOS. The best three scores in each column are marked in red, green and blue, Performance benchmarking of VBGFd, and VBGF, and 13 state-of-theart models on the dataset VOS-N

, Average run time (per frame) of each component in the proposed models, vol.106

, Performance comparison between the proposed method (SWVOS) and existing models over the YouTube-VOS-test dataset. The best score is in bold

, Performance benchmarking in the YouTube-VOS Challenge, p.117