Saliency Detection for Unconstrained Videos Using Superpixel-Level Graph and Spatiotemporal Propagation

Li, Zhi; Li, Junhao; Ye, Linwei; Sun, Guangling; Shen, Liquan

doi:10.1109/tcsvt.2016.2595324

Cited by 170 publications

(95 citation statements)

References 65 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As shown in Table 1, our proposed method is compared with 11 existing static-image salient object detection models including Amulet [48], UCF [49], SRM [40], DSS [13], MSR [22], NLDF [29], R3Net [7], C2SNet [26], RAS [5], DGRL [41], PiCANet [27], and 6 state-of-the-art video SOD algorithms including GAFL [43], SAGE [42], SGSP [28], FCNS [44], FGRNE [23], PDB [33]. Our proposed method is implemented by adopting MGA-tmc module at the positions of MGA-{0-4}, and MGA-m module at the position of MGA-5.…”

Section: Comparison With the State-of-the-artmentioning

confidence: 99%

Motion Guided Attention for Video Salient Object Detection

Chen²,

Li³

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

186

115

View full text Add to dashboard Cite

Video salient object detection aims at discovering the most visually distinctive objects in a video. How to effectively take object motion into consideration during video salient object detection is a critical issue. Existing stateof-the-art methods either do not explicitly model and harvest motion cues or ignore spatial contexts within optical flow images. In this paper, we develop a multi-task motion guided video salient object detection network, which learns to accomplish two sub-tasks using two sub-networks, one sub-network for salient object detection in still images and the other for motion saliency detection in optical flow images. We further introduce a series of novel motion guided attention modules, which utilize the motion saliency subnetwork to attend and enhance the sub-network for still images. These two sub-networks learn to adapt to each other by end-to-end training. Experimental results demonstrate that the proposed method significantly outperforms existing state-of-the-art algorithms on a wide range of benchmarks. We hope our simple and effective approach will serve as a solid baseline and help ease future research in video salient object detection. Code and models will be made available.

show abstract

Section: Comparison With the State-of-the-artmentioning

confidence: 99%

Motion Guided Attention for Video Salient Object Detection

Chen²,

Li³

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

186

115

View full text Add to dashboard Cite

show abstract

“…The proposed method is evaluated on both DAVIS and FBMS datasets and the results are compared against seven recent state-of-the-art saliency detection methods: deeply supervised salient object detection (DSS) [24], minimum barrier (MB) [71], multi-task deep neural network (MT) [41], local gradient flow optimization (GF) [63], superpixel-level graph (SGSP) [47], geodesic distance based video saliency (SAGE) [66] and fully convolutional networks (FCN) [64]. The first three are still-image saliency detection methods while the last four methods operate on video sequences to predict saliency maps.…”

Section: Performance Comparisonmentioning

confidence: 99%

Salient object detection in video using deep non-local neural networks

Shokri

Harati

Taba

2020

Journal of Visual Communication and Image Representation

View full text Add to dashboard Cite

Detection of salient objects in image and video is of great importance in many computer vision applications. In spite of the fact that the state of the art in saliency detection for still images has been changed substantially over the last few years, there have been few improvements in video saliency detection. This paper investigates the use of recently introduced non-local neural networks in video salient object detection. Non-local neural networks are applied to capture global dependencies and hence determine the salient objects. The effect of non-local operations is studied separately on static and dynamic saliency detection in order to exploit both appearance and motion features. A novel deep non-local neural network architecture is introduced for video salient object detection and tested on two well-known datasets DAVIS and FBMS. The experimental results show that the proposed algorithm outperforms state-of-the-art video saliency detection methods.

show abstract

“…However, they might loss some important high-level features such as semantic information in video sequences. What's more, some existing methods attempt to use linear or nonlinear combination rules to fuse spatial and temporal information simply [8], [13], [14], [16], which may ignore the intrinsic relationship due to the fixed weights used for the combination of spatial and temporal information.…”

Section: Arxiv:180704514v1 [Cscv] 12 Jul 2018mentioning

confidence: 99%

“…Besides, we make use of one 3D pooling layer, two 3D deconvolutional layers for the last three groups, and all strides of the 3D unpooling layer are set as 1×2×2 Table 1. The basic information of four public datasets: DAVIS [22], SegTrackV2 [21], VOT2016 [18], USVD [13].…”

Section: The Deconv3dnet For Saliency Learningmentioning

confidence: 99%

See 1 more Smart Citation

Video Saliency Detection by 3D Convolutional Neural Networks

Ding

Fang

2018

Communications in Computer and Information Science

View full text Add to dashboard Cite

Different from salient object detection methods for still images, a key challenging for video saliency detection is how to extract and combine spatial and temporal features. In this paper, we present a novel and effective approach for salient object detection for video sequences based on 3D convolutional neural networks. First, we design a 3D convolutional network (Conv3DNet) with the input as three video frame to learn the spatiotemporal features for video sequences. Then, we design a 3D deconvolutional network (Deconv3DNet) to combine the spatiotemporal features to predict the final saliency map for video sequences. Experimental results show that the proposed saliency detection model performs better in video saliency prediction compared with the state-of-the-art video saliency detection methods.

show abstract

Saliency Detection for Unconstrained Videos Using Superpixel-Level Graph and Spatiotemporal Propagation

Cited by 170 publications

References 65 publications

Motion Guided Attention for Video Salient Object Detection

Motion Guided Attention for Video Salient Object Detection

Salient object detection in video using deep non-local neural networks

Video Saliency Detection by 3D Convolutional Neural Networks

Contact Info

Product

Resources

About