Efficient Salient Region Detection with Soft Image Abstraction

Cheng, Ming–Ming; Warrell, Jonathan; Lin, Wen-Yan; Zheng, Shuai; Vineet, Vibhav; Crook, Nigel T.

doi:10.1109/iccv.2013.193

Cited by 459 publications

(320 citation statements)

References 49 publications

(111 reference statements)

Supporting

Mentioning

314

Contrasting

Unclassified

Order By: Relevance

“…2 Visual comparison of saliency maps on benchmark I [7]. (a) Original images, (b) IT [8], (c) SR [9], (d) FT [7], (e) GB [10], (f) AC [11], (g) MZ [12], (h) GC [13], (i) SF [14], (j) CUD, (k) Ground truth. Fig.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Salient Region Detection Based on Color Uniqueness and Color Spatial Distribution

Zhang

Wang

et al. 2014

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYIn this study, we address the problem of salient region detection. Recently, saliency detection with contrast based approaches has shown to give promising results. However, different individual features exhibit different performance. In this paper, we show that the combination of color uniqueness and color spatial distribution is an effective way to detect saliency. A Color Adaptive Thresholding Watershed Fusion Segmentation (CAT-WFS) method is first given to retain boundary information and delete unnecessary details. Based on the segmentation, color uniqueness and color spatial distribution are defined separately. The color uniqueness denotes the color rareness of salient object, while the color spatial distribution represents the color attribute of the background. Aiming at highlighting the salient object and downplaying the background, we combine the two characters to generate the final saliency map. Experimental results demonstrate that the proposed algorithm outperforms existing salient object detection methods.

show abstract

Section: Resultsmentioning

confidence: 99%

“…(a) and (b) are average precision and recall curves by fixed/adaptive thresholding separately. Our method CUD is compared with SR [9], MZ [12], FT [7], LC [16], HC [17], RC [17], CA [4], GB [10], AC [11], IT [8], SF [14], GC [13], and CO [15].…”

Section: Resultsmentioning

confidence: 99%

Salient Region Detection Based on Color Uniqueness and Color Spatial Distribution

Zhang

Wang

et al. 2014

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

show abstract

“…For frames with similar contents, the closer the salient region is to the center of the corresponding frame, the more important the corresponding frame is and the large probability that it is selected as a key frame. Thus, to model gaze, we first obtain the saliency map via the method proposed in [59] and then compute the Euclidean distance of the saliency map centroid to the frame center. Finally, the gaze attention score for each frame is defined as…”

Section: Attention Priormentioning

confidence: 99%

Scalable gastroscopic video summarization via similar-inhibition dictionary selection

Wang

Cong

Cao

et al. 2016

Artificial Intelligence in Medicine

View full text Add to dashboard Cite

“…These saliency approaches built saliency models focusing on high contrast regions between candidate foreground objects and their surrounding backgrounds. More specifically, Cheng et al [28] aimed at two saliency indicators: global appearance contrast and spatially compact distribution. Goferman et al [12] built a content-aware saliency detection model with the consideration of the contrast from both local and global perspectives.…”

Section: B Bottom-up Saliency Detectionmentioning

confidence: 99%

“…As argued by the pioneering perceptual research studies [26], [27], contrast is one of the influential factors in low-level visual saliency. Since the salient regions in the visual field would first pop out through different low-level features from their surroundings, numerous bottomup models [11]- [13], [28]- [30], [44] have been proposed to detect salient regions in images based on different mathematical principles. These saliency approaches built saliency models focusing on high contrast regions between candidate foreground objects and their surrounding backgrounds.…”

Section: B Bottom-up Saliency Detectionmentioning

confidence: 99%

Correspondence Driven Saliency Transfer

Yang

Shen

Shao

et al. 2016

IEEE Trans. on Image Process.

138

View full text Add to dashboard Cite

Abstract-In this paper, we show that large annotated data sets have great potential to provide strong priors for saliency estimation rather than merely serving for benchmark evaluations. To this end, we present a novel image saliency detection method called saliency transfer. Given an input image, we first retrieve a support set of best matches from the large database of saliency annotated images. Then, we assign the transitional saliency scores by warping the support set annotations onto the input image according to computed dense correspondences. To incorporate context, we employ two complementary correspondence strategies: a global matching scheme based on scene-level analysis and a local matching scheme based on patch-level inference. We then introduce two refinement measures to further refine the saliency maps and apply the random-walk-with-restart by exploring the global saliency structure to estimate the affinity between foreground and background assignments. Extensive experimental results on four publicly available benchmark data sets demonstrate that the proposed saliency algorithm consistently outperforms the current state-of-the-art methods.

show abstract

Efficient Salient Region Detection with Soft Image Abstraction

Abstract: Detecting visually salient regions in images is

Cited by 459 publications

References 49 publications

Salient Region Detection Based on Color Uniqueness and Color Spatial Distribution

Salient Region Detection Based on Color Uniqueness and Color Spatial Distribution

Scalable gastroscopic video summarization via similar-inhibition dictionary selection

Correspondence Driven Saliency Transfer

Contact Info

Product

Resources

About