Consistent Video Saliency Using Local Gradient Flow Optimization and Global Refinement

By Wenguan Wang, Jianbing Shen, Ling Shao. IEEE Transactions on Image Processing, 2015

392 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Sensory Systems

View Paper: https://www.semanticscholar.org/paper/065ec79836040f89df3c850a3b065de9222a8871

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

In Sensory Systems

Citations in the corpus

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.”
Spatiotemporal Knowledge Distillation for Efficient Estimation of Aerial Video Saliency (2019, methodology): “The heuristic saliency models [24]–[29] generally use hand-crafted features and design heuristic rules to perform visual saliency estimation in a bottom-up or top-down man-”
Stereo Video Object Segmentation Using Stereoscopic Foreground Trajectories (2019, background): “Video segmentation [21], [24], [37] can be classified into supervised or unsupervised approaches.”
Learning Unsupervised Video Object Segmentation Through Visual Attention (2019, methodology): “Quantitative results: As shown in Table 7, our model (without CRF binaryzation) outperforms previous VSOD models [64, 45, 80, 48, 79, 77, 16, 49] with human read-able attention maps.”
Revisiting Video Saliency: A Large-Scale Benchmark and a New Model (2018, neutral): “, salient objects in videos [59]).”
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].”
Video Salient Object Detection via Fully Convolutional Networks (2017, methodology): “performing alternatives: saliency via deep feature (MD) [33], saliency via absorbing markov chain (MC) [67], space-time saliency for time-mapping (TIMP) [19], gradient-flow filed based saliency (GAFL) [3], geodesic distance based video saliency (SAGE) [17], and saliency via random walk with restart ”
Deep Visual Attention Prediction (2017, background): “object segmentation [7], [32], [36], video understanding [2],”
Saliency-Aware Video Object Segmentation (2018, neutral): “In [50], gradient ﬂow ﬁeld is proposed for detecting salient object regions in video sequences with global optimization.”
Shifting More Attention to Video Salient Object Detection (2019, methodology): “Second, with the established DAVSOD dataset and previous 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…”
Review of Visual Saliency Detection With Comprehensive Information (2018, methodology): “For example, the moving woman is highlighted homogeneously with clean background interference through the CVS method [98].”
Pyramid Dilated Deeper ConvLSTM for Video Salient Object Detection (2018, methodology): “Quantitative comparison against 18 saliency methods using PR curve on DAVIS [31], FBMS [2] and ViSal [43] datasets.”
Revisiting Video Saliency Prediction in the Deep Learning Era (2021, background): “Other datasets are either limited in terms of variety and scale of video stimuli [34], [36], or collected for special purposes (e.g., salient objects in videos [39], [40]).”