Saliency-Aware Video Object Segmentation

By Wenguan Wang, Jianbing Shen, Ruigang Yang, Fatih Murat Porikli. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018

442 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/9dd4c6ac61ba7b23c8c46e0b3f2e3989526b66a0

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

Nested Network With Two-Stream Pyramid for Salient Object Detection in Optical Remote Sensing Images (2019, background): “SALIENT object detection aims at locating the most attractive and visually distinctive objects or regions from an image, which has been used in image/video segmentation [1], image retargeting [2], image foreground annotation [3], thumbnail creation [4], image quality assessment [5], and video summar”
Stereo Video Object Segmentation Using Stereoscopic Foreground Trajectories (2019, background): “Video segmentation [21], [24], [37] can be classified into supervised or unsupervised approaches.”
Video Object Segmentation with Episodic Graph Memory Networks (2020, methodology): “eos. This task has been widely studied over several decades which also called unsupervised video object segmentation [19,22,35, 71]. Traditional methods usually leverage motion[18,29] or saliency cues[12,54] to obtain a heuristic representation for inferring the primary objects. Recent methods were ”
Salient Object Detection in the Deep Learning Era: An In-Depth Survey (2019, unknown): “In computer vision, sampled applications of SOD include image understanding [1], [2], image cap-tioning [3]–[5], object detection [6], [7], un-supervised video object segmentation [8], [9], semantic segmentation [10]– [12], person re-identiﬁcation [13], [14], etc .”
Pyramid Dilated Deeper ConvLSTM for Video Salient Object Detection (2018, background): “, eye fixation prediction [41, 39] and salient object detection [49, 47].”
Revisiting Video Saliency Prediction in the Deep Learning Era (2021, background): “…to as dynamic ﬁxation prediction or video saliency detection , is essential for understanding human attention behaviors and has various practical real-word applications (e.g., video captioning [3], compression [4], question answering [5], object segmentation [6], action recognition [7], etc.).”
InstaBoost: Boosting Instance Segmentation via Probability Map Guided Copy-Pasting (2019, methodology): “Combining instance detection and semantic segmentation, instance segmentation [13, 23, 31, 42, 28, 41, 44, 34] is a much harder problem.”
BBS-Net: RGB-D Salient Object Detection with a Bifurcated Backbone Strategy Network (2020, background): “ in an image [2], [3]. Over the last decade, SOD has attracted signiﬁcant attention due to its widespread applications in object recognition [4], content-based image retrieval [5], image segmentation [6], image editing [7], video analysis [8], [9], and visual tracking [10], [11]. Traditional SOD alg”
Deep Visual Attention Prediction (2017, background): “utational models. Since then, many followup works [5] have been proposed in this direction. In recent decades, there is a new wave in saliency detection [32], [3], [33], [34], [36], [37], [38], [39], [56], [49] that concentrated on uniformly highlighting the most salient object regions in an image, ”
Video Salient Object Detection via Fully Convolutional Networks (2017, background): “proposed, showing inspired performance and good potentials in many computer vision applications [18], [47], [59], [68], [69].”
Review of Visual Saliency Detection With Comprehensive Information (2018, background): “In [100] and [101], the spatial edge and motion boundary were incorporated”
A Survey on Deep Learning Technique for Video Segmentation (2021, background): “, visual attention mechanism [1], motion boundaries [2], etc.”
Every Pixel Counts ++: Joint Learning of Geometry and Motion with 3D Holistic Understanding (2018, methodology): “For unsupervised video segmentation, saliency estimation based on 2D optical flow is often used to discover and track the objects [75], [76], and long trajectories [77] of the moving objects based on optical flow need to be considered.”