Read by QxMD icon Read

representational learning

Christopher Fassnidge, Claudia Cecconi Marcotti, Elliot Freeman
In some people, visual stimulation evokes auditory sensations. How prevalent and how perceptually real is this? 22% of our neurotypical adult participants responded 'Yes' when asked whether they heard faint sounds accompanying flash stimuli, and showed significantly better ability to discriminate visual 'Morse-code' sequences. This benefit might arise from an ability to recode visual signals as sounds, thus taking advantage of superior temporal acuity of audition. In support of this, those who showed better visual relative to auditory sequence discrimination also had poorer auditory detection in the presence of uninformative visual flashes, though this was independent of awareness of visually-evoked sounds...
January 13, 2017: Consciousness and Cognition
Kristen A Baker, Sarah Laurence, Catherine J Mondloch
Adults and children aged 6years and older easily recognize multiple images of a familiar face, but often perceive two images of an unfamiliar face as belonging to different identities. Here we examined the process by which a newly encountered face becomes familiar, defined as accurate recognition of multiple images that capture natural within-person variability in appearance. In Experiment 1 we examined whether exposure to within-person variability in appearance helps children learn a new face. Children aged 6-13years watched a 10-min video of a woman reading a story; she was filmed on a single day (low variability) or over three days, across which her appearance and filming conditions (e...
January 13, 2017: Cognition
Yuchen Guo, Guiguang Ding, Li Liu, Jungong Han, Ling Shao
Sparse representation and image hashing are powerful tools for data representation and image retrieval respectively. The combinations of these two tools for scalable image retrieval, i.e., Sparse Hashing (SH) methods, have been proposed in recent years and the preliminary results are promising. The core of those methods is a scheme that can efficiently embed the (highdimensional) image features into a low-dimensional Hamming space while preserving the similarity between features. Existing SH methods mostly focus on finding better sparse representations of images in the hash space...
January 16, 2017: IEEE Transactions on Image Processing: a Publication of the IEEE Signal Processing Society
Jorge Garcia, Niki Martinel, Alfredo Gardel, Ignacio Bravo, Gian Luca Foresti, Christian Micheloni
Existing approaches for person re-identification are mainly based on creating distinctive representations or on learning optimal metrics. The achieved results are then provided in form of a list of ranked matching persons. It often happens that the true match is not ranked first but it is in the first positions. This is mostly due to the visual ambiguities shared between the true match and other "similar" persons. At the current state, there is a lack of a study of such visual ambiguities which limit the re-identification performance within the first ranks...
January 16, 2017: IEEE Transactions on Image Processing: a Publication of the IEEE Signal Processing Society
Jin Xie, Fan Zhu, Guoxian Dai, Ling Shao, Yi Fang
Since there are complex geometric variations with 3D shapes, extracting efficient 3D shape features is one of the most challenging tasks in shape matching and retrieval. In this paper, we propose a deep shape descriptor by learning shape distributions at different diffusion time via a progressive shape-distribution-encoder (PSDE). First, we develop a shape distribution representation with the kernel density estimator to characterize the intrinsic geometry structures of 3D shapes. Then, we propose to learn a deep shape feature through an unsupervised PSDE...
January 10, 2017: IEEE Transactions on Image Processing: a Publication of the IEEE Signal Processing Society
Yueying Kao, Ran He, Kaiqi Huang
Human beings often assess the aesthetic quality of an image coupled with the identification of the image's semantic content. This paper addresses the correlation issue between automatic aesthetic quality assessment and semantic recognition. We cast the assessment problem as the main task among a multitask deep model, and argue that semantic recognition task offers the key to address this problem. Based on convolutional neural networks, we employ a single and simple multi-task framework to efficiently utilize the supervision of aesthetic and semantic labels...
January 11, 2017: IEEE Transactions on Image Processing: a Publication of the IEEE Signal Processing Society
Zheng Zhang, Zhihui Lai, Yong Xu, Ling Shao, Jian Wu, Guo-Sen Xie
In this paper, we aim at learning compact and discriminative linear regression models. Linear regression has been widely used in different problems. However, most of the existing linear regression methods exploit the conventional zeroone matrix as the regression targets, which greatly narrows the flexibility of the regression model. Another major limitation of theses methods is that the learned projection matrix fails to precisely project the image features to the target space due to their weak discriminative capability...
January 11, 2017: IEEE Transactions on Image Processing: a Publication of the IEEE Signal Processing Society
Jun Li, Chang Xu, Wankou Yang, Changyin Sun, Dacheng Tao
-Given unreliable visual patterns and insufficient query information, content-based image retrieval (CBIR) is often suboptimal and requires image re-ranking using auxiliary information. In this paper, we propose Discriminative Multi-view INTeractive Image Re-ranking (DMINTIR), which integrates User Relevance Feedback (URF) capturing users' intentions and multiple features that sufficiently describe the images. In DMINTIR, heterogeneous property features are incorporated in the multi-view learning scheme to exploit their complementarities...
January 10, 2017: IEEE Transactions on Image Processing: a Publication of the IEEE Signal Processing Society
Shireen Y Elhabian, Praful Agrawal, Ross T Whitaker
Probabilistic label maps are a useful tool for important medical image analysis tasks such as segmentation, shape analysis, and atlas building. Existing methods typically rely on blurred signed distance maps or smoothed label maps to model uncertainties and shape variabilities, which do not conform to any generative model or estimation process, and are therefore suboptimal. In this paper, we propose to learn probabilistic label maps using a generative model on given set of binary label maps. The proposed approach generalizes well on unseen data while simultaneously capturing the variability in the training samples...
April 2016: Proceedings of the IEEE International Symposium on Biomedical Imaging: from Nano to Macro
Sandra Vieira, Walter H L Pinaya, Andrea Mechelli
Deep learning (DL) is a family of machine learning methods that has gained considerable attention in the scientific community, breaking benchmark records in areas such as speech and visual recognition. DL differs from conventional machine learning methods by virtue of its ability to learn the optimal representation from the raw data through consecutive nonlinear transformations, achieving increasingly higher levels of abstraction and complexity. Given its ability to detect abstract and complex patterns, DL has been applied in neuroimaging studies of psychiatric and neurological disorders, which are characterised by subtle and diffuse alterations...
January 10, 2017: Neuroscience and Biobehavioral Reviews
Dae Hoe Kim, Seong Tae Kim, Jung Min Chang, Yong Man Ro
Characterization of masses in computer-aided detection systems for digital breast tomosynthesis (DBT) is an important step to reduce false positive (FP) rates. To effectively differentiate masses from FPs in DBT, discriminative mass feature representation is required. In this paper, we propose a new latent feature representation boosted by depth directional long-term recurrent learning for characterizing malignant masses. The proposed network is designed to encode mass characteristics in two parts. First, 2D spatial image characteristics of DBT slices are encoded as a slice feature representation by convolutional neural network (CNN)...
February 7, 2017: Physics in Medicine and Biology
David C Plaut, Anna K Vande Velde
Statistical learning is often considered to be a means of discovering the units of perception, such as words and objects, and representing them as explicit "chunks." However, entities are not undifferentiated wholes but often contain parts that contribute systematically to their meanings. Studies of incidental auditory or visual statistical learning suggest that, as participants learn about wholes they become insensitive to parts embedded within them, but this seems difficult to reconcile with a broad range of findings in which parts and wholes work together to contribute to behavior...
January 12, 2017: Journal of Experimental Psychology. General
James M Heather, Mazlina Ismail, Theres Oakes, Benny Chain
T-cell specificity is determined by the T-cell receptor, a heterodimeric protein coded for by an extremely diverse set of genes produced by imprecise somatic gene recombination. Massively parallel high-throughput sequencing allows millions of different T-cell receptor genes to be characterized from a single sample of blood or tissue. However, the extraordinary heterogeneity of the immune repertoire poses significant challenges for subsequent analysis of the data. We outline the major steps in processing of repertoire data, considering low-level processing of raw sequence files and high-level algorithms, which seek to extract biological or pathological information...
January 10, 2017: Briefings in Bioinformatics
G Ritov, G Richter-Levin
In basic research, the etiology of fear-related pathologies, such as post-traumatic stress disorder (PTSD), is conceptualized using fear-conditioning protocols that pair environmental stimuli (that is, a conditioned stimulus-CS) with an aversive, unconditioned stimulus (US) to elicit an assessable conditioned fear response. Although pathophysiological models agree that regulatory dysfunctions in this associative process may instigate fear-related pathology, current opinions differ in regard to the nature of these dysfunctions...
January 10, 2017: Translational Psychiatry
Matthias N Hartmann-Riemer, Steffen Aschenbrenner, Magdalena Bossert, Celina Westermann, Erich Seifritz, Philippe N Tobler, Matthias Weisbrod, Stefan Kaiser
Negative symptoms in schizophrenia have been linked to selective reinforcement learning deficits in the context of gains combined with intact loss-avoidance learning. Fundamental mechanisms of reinforcement learning and choice are prediction error signaling and the precise representation of reward value for future decisions. It is unclear which of these mechanisms contribute to the impairments in learning from positive outcomes observed in schizophrenia. A recent study suggested that patients with severe apathy symptoms show deficits in the representation of expected value...
January 10, 2017: Scientific Reports
Paz Suárez-Coalla, Fernando Cuetos
Recent studies have suggested that Spanish children with dyslexia have difficulty storing orthographic representations of new words. But given that the syllable plays an important role in word recognition in Spanish, it is possible that the formation of orthographic representations is influenced by the characteristics of the syllables that make up the words. The objective of this study was to determine whether syllabic frequency and syllabic complexity influence orthographic learning in children with dyslexia...
January 9, 2017: Dyslexia: the Journal of the British Dyslexia Association
Thomas Minot, Hannah L Dury, Akihiro Eguchi, Glyn W Humphreys, Simon M Stringer
We use an established neural network model of the primate visual system to show how neurons might learn to encode the gender of faces. The model consists of a hierarchy of 4 competitive neuronal layers with associatively modifiable feedforward synaptic connections between successive layers. During training, the network was presented with many realistic images of male and female faces, during which the synaptic connections are modified using biologically plausible local associative learning rules. After training, we found that different subsets of output neurons have learned to respond exclusively to either male or female faces...
January 9, 2017: Psychological Review
Mingxia Liu, Jun Zhang, Pew-Thian Yap, Dinggang Shen
Effectively utilizing incomplete multi-modality data for diagnosis of Alzheimer's disease (AD) is still an area of active research. Several multi-view learning methods have recently been developed to deal with missing data, with each view corresponding to a specific modality or a combination of several modalities. However, existing methods usually ignore the underlying coherence among views, which may lead to suboptimal learning performance. In this paper, we propose a view-aligned hypergraph learning (VAHL) method to explicitly model the coherence among the views...
October 2016: Medical Image Computing and Computer-assisted Intervention: MICCAI ..
Sheng Li, Kang Li, Yun Fu
The lack of labeled data presents a common challenge in many computer vision and machine learning tasks. Semisupervised learning and transfer learning methods have been developed to tackle this challenge by utilizing auxiliary samples from the same domain or from a different domain, respectively. Self-taught learning, which is a special type of transfer learning, has fewer restrictions on the choice of auxiliary data. It has shown promising performance in visual learning. However, existing self-taught learning methods usually ignore the structure information in data...
January 2, 2017: IEEE Transactions on Neural Networks and Learning Systems
Chunjie Zhang, Chao Liang, Liang Li, Jing Liu, Qingming Huang, Qi Tian
This paper tries to separate fine-grained images by jointly learning the encoding parameters and codebooks through low-rank sparse coding (LRSC) with general and class-specific codebook generation. Instead of treating each local feature independently, we encode the local features within a spatial region jointly by LRSC. This ensures that the spatially nearby local features with similar visual characters are encoded by correlated parameters. In this way, we can make the encoded parameters more consistent for fine-grained image representation...
April 7, 2016: IEEE Transactions on Neural Networks and Learning Systems
Fetch more papers »
Fetching more papers... Fetching...
Read by QxMD. Sign in or create an account to discover new knowledge that matter to you.
Remove bar
Read by QxMD icon Read

Search Tips

Use Boolean operators: AND/OR

diabetic AND foot
diabetes OR diabetic

Exclude a word using the 'minus' sign

Virchow -triad

Use Parentheses

water AND (cup OR glass)

Add an asterisk (*) at end of a word to include word stems

Neuro* will search for Neurology, Neuroscientist, Neurological, and so on

Use quotes to search for an exact phrase

"primary prevention of cancer"
(heart or cardiac or cardio*) AND arrest -"American Heart Association"