SalientShape: group saliency in image collections

By Ming-Ming Cheng, Niloy J. Mitra, Xiaolei Huang, Shimin Hu. The Visual Computer, 2013

300 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/e0b44a3cf11ca93b31a0339ea7011d5b77997a85

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

Weakly-Supervised Salient Object Detection via Scribble Annotations (2020, methodology): “Then, we evaluate our method on six widely-used benchmarks: (1) DUTS testing dataset [34]; (2) ECSSD [44]; (3) DUT [45]; (4) PASCAL-S [18]; (5) HKU-IS [17] and (6) THUR [2].”
Recurrent Attentional Networks for Saliency Detection (2016, unknown): “THUR15K [8] has 6,232 images which belong to five object classes of “butterfly”, “coffee mug”, “dog jump”, “giraffe”, and “plane”.”
Stacked Cross Refinement Network for Edge-Aware Salient Object Detection (2019, methodology): “We evaluate the proposed approach on six traditional benchmark datasets: ECSSD [33], PASCAL-S [21], DUTS [28], HKU-IS [19], DUT-OMRON [34] and THUR 15 K [6].”
A Stagewise Refinement Model for Detecting Salient Objects in Images (2017, methodology): “THUR15K has 6,232 images from five categories including ‘butterfly’, ‘coffee mug’, ‘dog jump’, ‘giraffe’ and ‘plane’.”
Structure-Measure: A New Way to Evaluate Foreground Maps (2017, background): “ evaluating and comparing various computer vision algorithm for applications such as object detection [6,8,24,40], saliency prediction [5,20,42], image segmentation [41], contentbased image retrieval [12,15,22], semantic segmentation [21,45,46] and image collection browsing [10,14,29]. As a speciﬁc ”
Learning to Detect Salient Objects with Image-Level Supervision (2017, methodology): “We evaluate our Weakly Supervised Saliency (WSS) method on the test set of DUTS and 5 public data sets: SED [2], ECSSD [52], THUR [5], PASCAL-S [30] and HKU-IS [26].”
Deep Saliency with Encoded Low Level Distance Map and High Level Features (2016, methodology): “These benchmarks include ECSSD [29], Judd [14], THUR15K [6], DUTOMRON [30], PASCAL-S [18], and FT [1].”
Label Decoupling Framework for Salient Object Detection (2020, methodology): “To evaluate the proposed method, six popular benchmark datasets are adopted, including ECSSD [36] with 1000 images, PASCAL-S [19] with 850 images, HKU-IS [17] with 4447 images, DUT-OMRON [37] with 5168 images, DUTS [25] with 15572 images and THUR15K [5] with 6232 images.”
Advanced Deep-Learning Techniques for Salient and Category-Specific Object Detection: A Survey (2018, methodology): “The THUR15K data set [85] contains 6,232 images coming from five object classes, i.”
Deep Level Sets for Salient Object Detection (2017, unknown): “The THUR [9] has 6232 images collected from Flickr with 5 topics:”Butterfly”, ”Coffee Mug”, ”Dog Jump”, ”Giraffe” and ”Plane”.”
Salient Objects in Clutter: Bringing Salient Object Detection to the Foreground (2018, background): “butes (Attr) and category labels are provided. Please refer to the supplemental material for more illustrations of our dataset. Our work is motivated by two observations. First, existing SOD datasets [2, 5,10,11,23,26,29,32,43,44] are awed either in the data collection procedure or quality of the da”
STC: A Simple to Complex Framework for Weakly-Supervised Semantic Segmentation (2015, methodology): “In order to ensure that the images are simple ones, we adopt a method similar to that proposed in [40], [41] to filter the crawled images.”
Detect Globally, Refine Locally: A Novel Approach to Saliency Detection (2018, methodology): “We evaluate the proposed framework on five popular datasets: ECSSD [31], DUTOMRON [32], THUR15K [5], HKU-IS [17], and DUTS [27].”
Uncertainty-aware Joint Salient Object and Camouflaged Object Detection (2021, methodology): “Dataset: For salient object detection, we train our model using the augmented DUTS training dataset [44], and testing on six other testing dataset, including the DUTS testing dataset, ECSSD [49], DUT [50], HKU-IS [27], THUR [4] and SOC testing dataset [8].”