Saliency-aware geodesic video object segmentation

By Wenguan Wang, Jianbing Shen, Fatih Murat Porikli. Computer Vision and Pattern Recognition, 2015

538 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/a4fd90ef2ff0f673faa1c89ea318341443939799

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

1. Luc Van Gool
2. Ming-Hsuan Yang
3. Ling Shao
4. Wenguan Wang
5. Dacheng Tao
6. Jianbing Shen
7. Yi Yang
8. Xiaogang Wang

Citations in the corpus

• Stereo Video Object Segmentation Using Stereoscopic Foreground Trajectories (2019, methodology): “3) Saliency Detection Analysis: Methods in [31] and [35] both facilitate a superpixel-level saliency detection to assist”
• Zero-Shot Video Object Segmentation via Attentive Graph Neural Networks (2019, methodology): “To automatically separate primary objects from the background, conventional methods typically use handcrafted features ( e.g ., color, optical flow) [43, 12, 59, 20] and certain heuristic assumptions related to the foreground ( i.e ., lo-cal motion differences [43], background priors [67]).”
• A Survey of Deep Learning-Based Object Detection (2019, background): “provide benchmarks for video salient object detection, and existing good algorithms [230] [231] [224] [232] [227] [233] [234] [235] [236] [237] [238][239][240][241] devote in this domain.”
• Predicting the Driver's Focus of Attention: The DR(eye)VE Project (2017, background): “The gap in performance with respect to bottom-up unsupervised approaches [61], [62] is higher, and is motivated by the strong relation between saliency maps and the driving context, that calls for a task-oriented training procedure.”
• One-Shot Video Object Segmentation (2016, methodology): “We also add the unsupervised techniques: FST [36], SAL [46], KEY [24], MSG [5], TRC [13], CVOS [48], and NLC [10].”
• Saliency-Aware Video Object Segmentation (2018, methodology): “This paper builds upon and extends our recent work in [20] with a more in depth discussion of the algorithm and expanded evaluations.”
• Learning Video Object Segmentation From Unlabeled Videos (2020, methodology): “As there is no indication for objects to be segmented, conventional ZVOS methods resorted to certain heuristics, such as saliency [59, 62, 61, 7], object proposals[19, 37, 24], and discriminative motion patterns[31, 10, 33].”
• Learning Video Object Segmentation with Visual Memory (2017, methodology): “An alternative to using trajectories is formulating the segmentation problem as a foreground-background classification task [25, 31, 45].”
• A Benchmark Dataset and Evaluation Methodology for Video Object Segmentation (2016, methodology): “Dynamic background (DB) scenes, e.g. flowing water, represent a major difficulty to the class of unsupervised methods, such as NLC and SAL, which adopt distinctive motion saliency as the underlying assumption to predict the object location.”
• Pyramid Dilated Deeper ConvLSTM for Video Salient Object Detection (2018, methodology): “ARP*[20] LVO[34] FSEG[19] LMP[33] SFL*[5] FST*[30] SAGE*[42] Ours Ours+”
• Image Segmentation Using Deep Learning: A Survey (2020, background): “saliency-aware models for geodesic video segmentation [124], Dual Image Segmentation (DIS) [125], FoveaNet [126] (perspective-aware scene parsing), Ladder DenseNet [127], Bilateral Segmentation Network (BiSe-”
• Revisiting Video Saliency: A Large-Scale Benchmark and a New Model (2018, background): “There are some salient object detection models [40, 1, 11, 61, 58, 60, 4, 62, 21] that attempt to uniformly highlight salient object regions in images or videos.”
• Consistent Video Saliency Using Local Gradient Flow Optimization and Global Refinement (2015, methodology): “There are a few methods [7], [8], [11], [14], [20], [37], [50] designed for video saliency till now and most of them simply add the motion feature to image saliency models (e.g., [7], [8], and [37]) to cope with the extra temporal dimension.”
• Shifting More Attention to Video Salient Object Detection (2019, methodology): “…7 VSOD datasets [35,40,43,52,56,59,75], we present a comprehensive evaluation of 17 state-of-the-art models [8, 11,35,41,44,52,53,62,67,68,70,74–76, 81, 87, 92 Our two contributions represent a complete benchmark suite with the necessary tools for a complementary evaluation, bring a more…”
• MASK-RL: Multiagent Video Object Segmentation Framework Through Reinforcement Learning (2020, methodology): “…as follows: unsupervised methods compute background/foreground binary masks based on the input video frames alone [10], [23], [26], [30], [43]; semisupervised methods need some “clues” (usually on the first frames) on the location of moving objects [33], [38], [44], [45]; supervised…”
• Instance Embedding Transfer to Unsupervised Video Object Segmentation (2018, methodology): “Classic work in video segmentation produced results using optical flow and shallow appearance models [12, 22, 24, 31, 33, 42] while more recent methods typically pretrain the network Figure 1.”
• Review of Visual Saliency Detection With Comprehensive Information (2018, methodology): “SG [100], STBP [102], SGSP [104]), and a deep learning based method (VFCN [107]) are used for comparison.”
• Salient Object Detection With Pyramid Attention and Salient Edges (2019, background): “It can be widely applied for improving a variety of vision tasks, such as object proposal generation [2], object segmentation [42, 44], photo cropping [45, 41], and video object tracking [13], among others.”
• DMM-Net: Differentiable Mask-Matching Network for Video Object Segmentation (2019, background): “Methods under the unsupervised category [5, 12, 42, 34] typically exploit the dense optical flow and appearance feature to group the pixels within the spatio-temporal neighborhood.”