Filters








13 Hits in 2.7 sec

Cosaliency

David E. Jacobs, Dan B. Goldman, Eli Shechtman
2010 Proceedings of the 23nd annual ACM symposium on User interface software and technology - UIST '10  
a) Input image pairs (b) Cosaliency (c) Processed Cosaliency (d) Collection-aware crops An overview of our algorithm and its results for two pairs of images.  ...  From this data, we train a model for image saliency in the context of other images that we call cosaliency.  ...  This problem is doubly true when comparing multiple images simultaneously.  ... 
doi:10.1145/1866029.1866066 dblp:conf/uist/JacobsGS10 fatcat:cikvg2776vhszgtqklsc5qtspi

Airport Detection-Based Cosaliency on Remote Sensing Images

Zhen Hua, Zhenzhu Bian, Jinjiang Li, Silvestar Šesnić
2021 Mathematical Problems in Engineering  
This paper proposes a contour extraction model based on cosaliency detection for remote sensing image airport detection and improves the traditional line segmentation detection (LSD) algorithm to make  ...  We compared the model proposed in this article with four commonly used methods.  ...  (iv) Design a cosaliency detection module to compare and fuse the clues in a single image and between multiple images to obtain a predicted cosaliency map.  ... 
doi:10.1155/2021/8956396 fatcat:2jbo2j6vhbddvjzsxtmuyapgu4

Cosaliency Detection Based on Intrasaliency Prior Transfer and Deep Intersaliency Mining

Dingwen Zhang, Junwei Han, Jungong Han, Ling Shao
2016 IEEE Transactions on Neural Networks and Learning Systems  
As an interesting and emerging topic, cosaliency detection aims at simultaneously extracting common salient objects in multiple related images.  ...  of multiple related images.  ...  From the bottom two histograms in Fig. 7 , we can observe that the obtained intersaliency (β = 1) achieves better performance than the intrasaliency (β = 0) does, especially when looking at the AP score  ... 
doi:10.1109/tnnls.2015.2495161 pmid:26571541 fatcat:wlx7n6x3qrfijcgnb3ppomgyga

Co-Saliency Detection with Co-Attention Fully Convolutional Network [article]

Guangshuai Gao, Wenting Zhao, Qingjie Liu, Yunhong Wang
2020 arXiv   pre-print
Co-saliency detection aims to detect common salient objects from a group of relevant images.  ...  Among the various interesting questions that have been brought, one is "where do people look when comparing images?" Jacobs et al.  ...  Especially, from Fig. 5 , we can see in cases where the common objects in relevant images have similar texture or appearance with the background, compared methods tend to perform unsatisfactorily.  ... 
arXiv:2008.08909v1 fatcat:ykgayihxrvcp5hac3gv545h7li

From co-saliency to co-segmentation: An efficient and fully unsupervised energy minimization model

Kai-Yueh Chang, Tyng-Luh Liu, Shang-Hong Lai
2011 CVPR 2011  
We address two key issues of co-segmentation over multiple images. The first is whether a pure unsupervised algorithm can satisfactorily solve this problem.  ...  Specifically, instead of relying on the user inputs, our approach introduces a cosaliency prior as the hint about possible foreground locations, and uses it to construct the MRF data terms.  ...  Roughly speaking, it is related to the areas that most people may focus on when seeing a view.  ... 
doi:10.1109/cvpr.2011.5995415 dblp:conf/cvpr/ChangLL11 fatcat:fipghtltqnealbnm2dtrb6edcy

A Review of Co-saliency Detection Technique: Fundamentals, Applications, and Challenges [article]

Dingwen Zhang, Huazhu Fu, Junwei Han, Ali Borji, Xuelong Li
2017 arXiv   pre-print
As a novel branch of visual saliency, co-saliency detection refers to the discovery of common and salient foregrounds from two or more relevant images, and can be widely used in many computer vision tasks  ...  The existing co-saliency detection algorithms mainly consist of three components: extracting effective features to represent the image regions, exploring the informative cues or factors to characterize  ...  Thus, compared with image co-saliency, video co-saliency needs to additionally consider information cues such as intra-video temporal saliency [94] , inter-video co-saliency [44] , and intra-video cosaliency  ... 
arXiv:1604.07090v5 fatcat:j7zqwqaowndrbcuoazzizkuqr4

Salient object cutout using Google images

Hongyuan Zhu, Jianfei Cai, Jianmin Zheng, Jianxin Wu, Nadia Thalmann
2013 2013 IEEE International Symposium on Circuits and Systems (ISCAS2013)  
Motivated by the recent progress on image co-segmentation and internet image retrieval techniques, in this paper, we propose to use the user input image for segmentation as a query image to Google Images  ...  and then employ the top returned Google images to build up the knowledge about the object-of-interest in the user input image.  ...  Nevertheless, when the number of images is large, user input is time consuming and infeasible.  ... 
doi:10.1109/iscas.2013.6571994 dblp:conf/iscas/ZhuCZWM13 fatcat:jzmrtdtgvfdb7oljk7gc5gwh7m

Co-saliency detection via looking deep and wide

Dingwen Zhang, Junwei Han, Chao Li, Jingdong Wang
2015 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
Cosaliency: Weakly Supervised Learning and High-Level Feature Where people look when comparing images. In UIST, 2010. Learning. IEEE Trans. Geosci.  ...  Self-information increases when multiple related images as shown in Figure 4. In this case, the probability of a OP decreases.  ... 
doi:10.1109/cvpr.2015.7298918 dblp:conf/cvpr/ZhangHLW15 fatcat:szglwxobdbb3tdv4qyeob6v6km

Automatic triage for a photo series

Huiwen Chang, Fisher Yu, Jue Wang, Douglas Ashley, Adam Finkelstein
2016 ACM Transactions on Graphics  
By augmenting this dataset with ground truth human preferences among photos within each series, we establish a benchmark for measuring the effectiveness of algorithmic models of how people select photos  ...  We have also discovered from the user comments that people often look at very different set of features when evaluating photos of different scene categories.  ...  From the user comments received from the user study, it is clear that people use features at all levels for reasoning about the relative quality when comparing similar images.  ... 
doi:10.1145/2897824.2925908 fatcat:bgvkfaivw5fa7lpjvtnxj44kdu

Research on Salient Object Detection using Deep Learning and Segmentation Methods

2019 International journal of recent technology and engineering  
The target detection is critically depends on the feature types implemented. 3 Learning to predict where humans look Judd, [2007] Combines both bottom-up image based saliency cues and top-down  ...  Compared to image co-saliency, it is more reliable due to the utilization of temporal information of video sequence.  ... 
doi:10.35940/ijrte.b1046.0982s1119 fatcat:6ofq53vb7zhx7boq4ndpraphs4

One-Shot Object Affordance Detection in the Wild [article]

Wei Zhai, Hongchen Luo, Jing Zhang, Yang Cao, Dacheng Tao
2021 arXiv   pre-print
., given a support image that depicts the action purpose, all objects in a scene with the common affordance should be detected.  ...  Affordance detection refers to identifying the potential action possibilities of objects in an image, which is a crucial ability for robot perception and manipulation.  ...  We also find when N = 6 does not bring a significant improvement compared to N = 5. It suggests that as N increases, the effectiveness of the model may be reaching a bottleneck.  ... 
arXiv:2108.03658v1 fatcat:kinywe25xzh7vc7g3ajakvst6m

Epigenetica e filosofia e fisica della prassi [article]

Massimo Morigi
2021 figshare.com  
There is much room for radical political people to contest the meanings of the breached boundary. The cyborg appears in myth precisely where the boundary between human and animal is transgressed.  ...  There is much room for radical political people to contest for the meanings of the breached boundary. 1 The cyborg appears in myth precisely where the boundary between human and animal is transgressed.  ...  She has long been interested in heuristic quantum algorithms such as quantum annealing, and looks forward to experimenting with them on emerging quantum computing hardware.  ... 
doi:10.6084/m9.figshare.13726861.v1 fatcat:3ob2wbozdfcdna6axyebp6eeva

Epigenetica, Teoria endosimbiotica, Sintesi evoluzionista moderna, Sintesi evoluzionistica estesa e fantasmagorie transumaniste, Massimo Morigi.pdf

Massimo Morigi
2021 figshare.com  
There is much room for radical political people to contest for the meanings of the breached boundary. 1 The cyborg appears in myth precisely where the boundary between human and animal is transgressed.  ...  In a fiction where no character is "simply" human, human status is highly problematic.  ... 
doi:10.6084/m9.figshare.13514822.v1 fatcat:kpx5gqafhnd43l2wrqmj4g5cc4