Contrast-based image attention analysis by using fuzzy growing

By Yufei Ma, HongJiang Zhang. MULTIMEDIA '03, 2003

1,074 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/8b183b5c2a58ae8e1dac196831f0725513153d93

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

Deep networks for saliency detection via local estimation and global search (2015, methodology): “Local methods [13, 25, 19, 39] compute center-surround differences in a local context for color, texture and edge orientation channels to capture the region-( [13].”
Frequency-tuned salient region detection (2009, methodology): “Also, individual feature maps are created separately and then combined to obtain the final saliency map [15, 22, 13, 7], or a feature combined saliency map is directly obtained [22, 1].”
Saliency Detection via Absorbing Markov Chain (2013, neutral): “We compare our method with fifteen state-of-the-art saliency detection algorithms: the IT [16], MZ [20], LC [37], GB [14], SR [15], AC [1], FT [2], SER [31], CA [27], RC [8], CB [17], SVO [7], SF [25], LR [29] and GS [33] methods.”
A unified approach to salient object detection via low rank matrix recovery (2012, methodology): “which has motivated various models and methods that combine local, regional and global contrast-based features [17, 23, 27, 18, 8, 4, 16].”
Salient Object Detection: A Benchmark (2015, methodology): “Ma and Zhang [51] proposed an alternative local contrast method using a fuzzy growth model.”
Learning to Detect A Salient Object (2007, methodology): “Contrast is the most commonly used local feature for attention detection [10, 15, 16] because the contrast operator simulates the human visual receptive ﬁelds.”
Saliency detection using maximum symmetric surround (2010, methodology): “The saliency maps generated by several methods suffer from low resolution [7, 1, 14, 9, 11].”
Saliency filters: Contrast based filtering for salient region detection (2012, methodology): “We compare to spectral residual saliency (SR [16]), fuzzy growing (MZ [22]), spatiotemporal cues (LC [29]), visual attention measure (IT [18]), graph-based saliency (GB [15]), salient region detection (AC [1]), context-aware saliency (CA [12]), frequency-tuned saliency (FT [2]) and global-contrast s”
Salient object detection by composition (2011, methodology): “We propose to detect salient objects by directly measuring the saliency of an image window in the original image and adopt the well established sliding window based object detection paradigm.”
What is an object? (2010, background): “the entire image or the surrounding area [23, 25].”
A generic framework of user attention model and its application in video summarization (2005, methodology): “Compared to the original user attention model in [4 ], the static attention model is replaced by our la test work [ 3 ],”
Visual attention detection in video sequences using spatiotemporal cues (2006, methodology): “Similar to the evaluation strategy in [15], each assessor was asked to give a vote on how satisfactory he or she thinks the detected attended region is for each testing sequence.”
Global contrast based salient region detection (2011, methodology): “We have extensively evaluated our methods on publicly available benchmark data sets, and compared our methods with (eight) state-of-the-art saliency methods [17, 21, 32, 14, 15, 1, 2, 12] as well as with manually produced ground truth annotations1.”
Global Contrast Based Salient Region Detection (2015, methodology): “The proposed method is simple, fast, and produces high quality results on benchmark datasets.”
Salient Object Detection: A Discriminative Regional Feature Integration Approach (2013, background): “ience, psychology, neural systems, and computer vision for a long time. It is originally deﬁned as a task of predicting the eye-ﬁxations on images [2]. Recently it is extended to identifying a region [3], [4] containing the salient object, known as salient object detection or salient region detectio”
Center-surround divergence of feature statistics for salient object detection (2011, methodology): “Ma and Zhang have proposed a contrast-based method that uses fuzzy growing to extract regions from their saliency map [16].”
Context-aware saliency detection (2010, background): “Many visual attention approaches have been proposed for detecting a few key locations with maximum local saliency and employ biologically motivated low-level features [16], [15], [22], [35], [6], [13], [20].”
Fusing generic objectness and visual saliency for salient object detection (2011, background): “Specifically, in most saliency detection methods, an edge pixel is often assigned a stronger saliency value since it is more distinct with respect to the whole image.”