Filters








824 Hits in 5.2 sec

Perceptually Guided Photo Retargeting

Yingjie Xia, Luming Zhang, Richang Hong, Liqiang Nie, Yan Yan, Ling Shao
2017 IEEE Transactions on Cybernetics  
We propose perceptually guided photo retargeting, which shrinks a photo by simulating a human's process of sequentially perceiving visually/semantically important regions in a photo.  ...  photo esthetics than conventional saliency maps.  ...  Based on the theory of visual perception [11] , there are usually strong correlation among the nonsalient regions in a photo.  ... 
doi:10.1109/tcyb.2016.2520959 pmid:27116756 fatcat:pja7bxn3pbbolb7j7koi42fl2a

Biologically Inspired Media Quality Modeling

Luming Zhang, Meng Wang, Liqiang Nie, Richang Hong, Yingjie Xia, Roger Zimmermann
2015 Proceedings of the 23rd ACM international conference on Multimedia - MM '15  
These selected graphlets are linked into a so-called biological viewing path (BVP) to simulate human visual perception.  ...  Then, an active learning algorithm is utilized to select graphlets that are both visually and semantically salient.  ...  s saliency model [28] , graph-based visual saliency by Harel et al. [26] , image signature by Hou et al. [27] , information-theory-based saliency model by Burce et al.  ... 
doi:10.1145/2733373.2806255 dblp:conf/mm/ZhangWNHXZ15 fatcat:sifho5j2jbd77oxc7mdqnsynzi

Perception-Guided Multimodal Feature Fusion for Photo Aesthetics Assessment

Luming Zhang, Yue Gao, Chao Zhang, Hanwang Zhang, Qi Tian, Roger Zimmermann
2014 Proceedings of the ACM International Conference on Multimedia - MM '14  
Conventional approaches suffer from the following three drawbacks: 1) the deemphasized role of semantic content that is many times more important than low-level visual features in photo aesthetics; 2)  ...  The top-ranked graphlets are the discerned visually/semantically prominent graphlets in a photo. They are sequentially linked into a path that simulates the process of humans actively viewing.  ...  Tian was also supported for this work in part by ARO grant W911NF-12-1-0057, Faculty Research Award by NEC Laboratories of America, and in part by the National Science Foundation of China (NSFC) under  ... 
doi:10.1145/2647868.2654903 dblp:conf/mm/ZhangGZZTZ14 fatcat:yn5pd7thabbjti4l34iaov23fm

An End-to-End Neural Network for Image Cropping by Learning Composition from Aesthetic Photos [article]

Peng Lu, Hao Zhang, Xujun Peng, Xiaofu Jin
2019 arXiv   pre-print
visual/aesthetic perception.  ...  As one of the fundamental techniques for image editing, image cropping discards unrelevant contents and remains the pleasing portions of the image to enhance the overall composition and achieve better  ...  the saliency map can be defined through its top right corner (x s tr , y s tr ) and bottom left corner (x s bl , y s bl ) by using a Gaussian-like window: (x s tr , y s tr ) = (c x + γσ x , c y + γσ y  ... 
arXiv:1907.01432v3 fatcat:eoltys3js5gsjlss4oj73oudrq

Towards Robustness against Unsuspicious Adversarial Examples [article]

Liang Tong, Minzhe Guo, Atul Prakash, Yevgeniy Vorobeychik
2020 arXiv   pre-print
While most attacks aim to ensure that these are imperceptible, physical perturbation attacks typically aim for being unsuspicious, even if perceptible.  ...  However, there is no universal notion of what it means for adversarial examples to be unsuspicious. We propose an approach for modeling suspiciousness by leveraging cognitive salience.  ...  RS against ∞ dual-perturbation attacks under different numbers of noisecorrupted copies at prediction time.K VISUALIZATION OF LOSS GRADIENT Tr ain Clock Cat Bir d Dog Tr uck Air plane Tr uck Elephant  ... 
arXiv:2005.04272v2 fatcat:x6o5kvpupneaheoerfuavge3dy

Military Object Real-Time Detection Technology Combined with Visual Salience and Psychology

Xia Hua, Xinqing Wang, Dong Wang, Jie Huang, Xiaodong Hu
2018 Electronics  
The main theory of Gestalt visual psychology is then used as the constraint condition to integrate the candidate salient regions and to obtain the object figure with overall perception.  ...  This paper presents a method of military object detection through the combination of human visual salience and visual psychology, so as to achieve rapid and accurate detection of military objects on the  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/electronics7100216 fatcat:wrlixsxyzngvhmdfg6xfr36p4a

Linking language to the visual world: Neural correlates of comprehending verbal reference to objects through pointing and visual cues

David Peeters, Tineke M. Snijders, Peter Hagoort, Aslı Özyürek
2017 Neuropsychologia  
In each picture, one of the objects was singled out, either through the speaker's index-finger pointing gesture or through a visual cue that made the object perceptually more salient in the absence of  ...  Moreover, a match (compared to a mismatch) between speech and the object made salient through a visual cue led to enhanced activation in the mentalizing system, arguably reflecting an attempt to converge  ...  Gunter for valuable comments on an earlier version of this paper.  ... 
doi:10.1016/j.neuropsychologia.2016.12.004 pmid:27939189 fatcat:ipctcilwffcfhjoladgcwwdiqq

Predicting Eye Fixations With Higher-Level Visual Features

Ming Liang, Xiaolin Hu
2015 IEEE Transactions on Image Processing  
Most computational studies define saliency as outliers of distributions of low-level features, and propose saliency as an important factor for predicting eye fixations.  ...  Saliency map and object map are the two contrasting hypotheses for the mechanisms utilized by the visual system to guide eye fixations when humans are freely viewing natural images.  ...  The local coordinater i is then converted to r i by padding zeros in r i , which correspond to the KK unused visual words.  ... 
doi:10.1109/tip.2015.2395713 pmid:25622314 fatcat:ynfasvxyaffl5dpsfb6wf5cm6q

Disentangled High Quality Salient Object Detection [article]

Lv Tang, Bo Li, Shouhong Ding, Mofei Song
2021 arXiv   pre-print
Extensive experiments on high-resolution saliency datasets as well as some widely used saliency benchmarks show that the proposed method achieves superior performance compared to the state-of-the-art methods  ...  HRRN is a regression task, which aims at accurately refining the saliency value of pixels in the uncertain region to preserve a clear object boundary at high-resolution with limited GPU memory.  ...  Receptive fields of F 1 5 and F 1 6 are relatively bigger, we only use GCNs with k = 7, 11 and k = 7.  ... 
arXiv:2108.03551v2 fatcat:dy6la4az4balxesndkpleseb2a

Salient Object Detection Techniques in Computer Vision—A Survey

Ashish Kumar Gupta, Ayan Seal, Mukesh Prasad, Pritee Khanna
2020 Entropy  
Detection and localization of regions of images that attract immediate human visual attention is currently an intensive area of research in computer vision.  ...  A large number of salient object detection (SOD) methods have been devised to effectively mimic the capability of the human visual system to detect the salient regions in images.  ...  Such theories preliminarily formed the base for development of the early saliency models.  ... 
doi:10.3390/e22101174 pmid:33286942 pmcid:PMC7597345 fatcat:3p5d2nal4vhxbi2via3g7oicga

Salient Object Detection via Structured Matrix Decomposition

Houwen Peng, Bing Li, Haibin Ling, Weiming Hu, Weihua Xiong, Stephen J. Maybank
2017 IEEE Transactions on Pattern Analysis and Machine Intelligence  
methods in terms of seven performance metrics.  ...  decomposition model with two structural regularizations: (1) a tree-structured sparsity-inducing regularization that captures the image structure and enforces patches from the same object to have similar saliency  ...  Visual comparisons of saliency maps of the best methods.  ... 
doi:10.1109/tpami.2016.2562626 pmid:28113696 fatcat:4rnbcixgxvahdi3qh7rfeibsgm

Data augmentation and image understanding [article]

Alex Hernandez-Garcia
2020 arXiv   pre-print
This work focuses on learning representations that are more aligned with visual perception and the biological vision.  ...  In turn, machine vision has also been an active area of research, currently dominated by the use of artificial neural networks.  ...  Hence, our results provide some new insights in the understanding of visual perception of natural images, showing that the global salience of an image is rather affected by the semantics of the content  ... 
arXiv:2012.14185v1 fatcat:qcip4vstzvbxzo4qevek5marrm

States of mind: Emotions, body feelings, and thoughts share distributed neural networks

Suzanne Oosterwijk, Kristen A. Lindquist, Eric Anderson, Rebecca Dautoff, Yoshiya Moriguchi, Lisa Feldman Barrett
2012 NeuroImage  
activity within large-scale distributed brain networks using fMRI.  ...  contribution of those networks.  ...  (e.g., Young et al., 2011) , episodic memory and prospection (e.g., Addis et al., 2007) , semantic processing (e.g., Binder et al., 2009) , and even context-sensitive visual perception (Bar et al.  ... 
doi:10.1016/j.neuroimage.2012.05.079 pmid:22677148 pmcid:PMC3453527 fatcat:ta3jm45kxvbkdhxtxfpnykomay

Object recognition is enabled by an experience-dependent appraisal of visual features in the brain's value system

Vladimir V. Kozunov, Timothy O. West, Anastasia Y. Nikolaeva, Tatiana A. Stroganova, Karl J. Friston
2020 NeuroImage  
ill-posed inverse problem of perception, can be available before category-specific processing in visual cortex.  ...  Using magnetoencephalography, we analyzed distributed patterns of neuronal activity - evoked by Mooney figures - before and after they were recognized as meaningful objects.  ...  projection screen located 1.7m in front of the participants with a Panasonic PT-D7700E-K DLP projector to provide an 8 Â 8 visual angle.  ... 
doi:10.1016/j.neuroimage.2020.117143 pmid:32650054 pmcid:PMC7762843 fatcat:f645f2svgzhr5fam4nq3to2wee

A predictive processing model of episodic memory and time perception [article]

Zafeirios Fountas, Anastasia Sylaidi, Kyriacos Nikiforou, Anil Seth, Murray Shanahan, Warrick Roseboom
2020 bioRxiv   pre-print
The complexity of interactions among stimulation, attention, and memory that characterise time experience is likely the reason that a single overarching theory of time perception has been difficult to  ...  In the present study we propose a framework that reconciles these interactions within a single model, built using the principles of the predictive processing approach to perception.  ...  Acknowledgements This work was supported by the European Union Future and Emerging Technologies grant (GA:641100) TIMESTORM-Mind and Time: Investigation of the Temporal Traits of Human-Machine Convergence  ... 
doi:10.1101/2020.02.17.953133 fatcat:2c4bxom725f7xbveirg4fzzl54
« Previous Showing results 1 — 15 out of 824 results