Read by QxMD icon Read

scene recognition

Alon Hafri, John C Trueswell, Russell A Epstein
People interact with other people and with objects in distinct and categorizable ways (e.g., kicking is making contact with foot). We can recognize these action categories across variations in actors, objects, and settings; moreover, we can recognize them from both dynamic and static visual input. However, the neural systems that support action recognition across these perceptual differences are unclear. Here we used multivoxel pattern analysis of fMRI data to identify brain regions that support visual action categorization in a format-independent way...
February 16, 2017: Journal of Neuroscience: the Official Journal of the Society for Neuroscience
Zhe Wang, Limin Wang, Yali Wang, Bowen Zhang, Yu Qiao
Traditional feature encoding scheme (e.g., Fisher vector) with local descriptors (e.g., SIFT) and recent convolutional neural networks (CNNs) are two classes of successful methods for image recognition. In this paper, we propose a hybrid representation, which leverages the discriminative capacity of CNNs and the simplicity of descriptor encoding schema for image recognition, with a focus on scene recognition. To this end, we make three main contributions from the following aspects. First, we propose a patch-level and end-to-end architecture to model the appearance of local patches, called PatchNet...
February 9, 2017: IEEE Transactions on Image Processing: a Publication of the IEEE Signal Processing Society
Akihiko Torii, Relja Arandjelovic, Josef Sivic, Masatoshi Okutomi, Tomas Pajdla
We address the problem of large-scale visual place recognition for situations where the scene undergoes a major change in appearance, for example, due to illumination (day/night), change of seasons, aging, or structural modifications over time such as buildings being built or destroyed. Such situations represent a major challenge for current large-scale place recognition methods. This work has the following three principal contributions. First, we demonstrate that matching across large changes in the scene appearance becomes much easier when both the query image and the database image depict the scene from approximately the same viewpoint...
February 13, 2017: IEEE Transactions on Pattern Analysis and Machine Intelligence
Hung-Yu Chen, Adrian W Gilmore, Steven M Nelson, Kathleen B McDermott
What brain regions underlie retrieval from episodic memory? The bulk of research addressing this question with fMRI has relied upon recognition memory for materials encoded within the laboratory. Another, less dominant tradition has employed autobiographical methods, whereby people recall events from their lifetime, often after being cued with words or pictures. The current study addressed how the neural substrates of successful memory retrieval differ as a function of the targeted memory when the experimental parameters were held constant in the two conditions (except for instructions)...
February 8, 2017: Journal of Neuroscience: the Official Journal of the Society for Neuroscience
Tineke K Steiger, Nico Bunzeck
Motivation can have invigorating effects on behavior via dopaminergic neuromodulation. While this relationship has mainly been established in theoretical models and studies in younger subjects, the impact of structural declines of the dopaminergic system during healthy aging remains unclear. To investigate this issue, we used electroencephalography (EEG) in healthy young and elderly humans in a reward-learning paradigm. Specifically, scene images were initially encoded by combining them with cues predicting monetary reward (high vs...
2017: Frontiers in Aging Neuroscience
Germán Martín García, Mircea Pavel, Simone Frintrop
We present a computational framework for attention-guided visual scene exploration in sequences of RGB-D data. For this, we propose a visual object candidate generation method to produce object hypotheses about the objects in the scene. An attention system is used to prioritise the processing of visual information by (1) localising candidate objects, and (2) integrating an inhibition of return (IOR) mechanism grounded in spatial coordinates. This spatial IOR mechanism naturally copes with camera motions and inhibits objects that have already been the target of attention...
February 2, 2017: Cognitive Processing
Thang M Le, John A Borghi, Autumn J Kujawa, Daniel N Klein, Hoi-Chung Leung
The present study examined the impacts of major depressive disorder (MDD) on visual and prefrontal cortical activity as well as their connectivity during visual working memory updating and related them to the core clinical features of the disorder. Impairment in working memory updating is typically associated with the retention of irrelevant negative information which can lead to persistent depressive mood and abnormal affect. However, performance deficits have been observed in MDD on tasks involving little or no demand on emotion processing, suggesting dysfunctions may also occur at the more basic level of information processing...
2017: NeuroImage: Clinical
Eamon Caddigan, Heeyoung Choo, Li Fei-Fei, Diane M Beck
Traditional models of recognition and categorization proceed from registering low-level features, perceptually organizing that input, and linking it with stored representations. Recent evidence, however, suggests that this serial model may not be accurate, with object and category knowledge affecting rather than following early visual processing. Here, we show that the degree to which an image exemplifies its category influences how easily it is detected. Participants performed a two-alternative forced-choice task in which they indicated whether a briefly presented image was an intact or phase-scrambled scene photograph...
January 1, 2017: Journal of Vision
Qiguang Miao, Pengfei Xu, Xuelong Li, Jianfeng Song, Weisheng Li, Yun Yang
It is difficult to separate the point symbols from the scanned topographic maps accurately, which brings challenges for the recognition of the point symbols. In this paper, based on the framework of generalized Hough transform (GHT), we propose a new algorithm, which is named as Shear Line Segment GHT (SLS-GHT), to recognize the point symbols directly in the scanned topographic maps. SLS-GHT combines Line Segment GHT (LS-GHT) and the shear transformation. On the one hand, LS-GHT is proposed to represent the features of the point symbols more completely...
September 23, 2016: IEEE Transactions on Image Processing: a Publication of the IEEE Signal Processing Society
Chongyi Li, Jichang Guo, Runmin Cong, Yanwei Pang, Bo Wang
Images captured under water are usually degraded due to the effects of absorption and scattering. Degraded underwater images show some limitations when they are used for display and analysis. For example, underwater images with low contrast and color cast decrease the accuracy rate of underwater object detection and marine biology recognition. To overcome those limitations, a systematic underwater image enhancement method which includes an underwater image dehazing algorithm and a contrast enhancement algorithm is proposed...
September 22, 2016: IEEE Transactions on Image Processing: a Publication of the IEEE Signal Processing Society
Sheng Guo, Weilin Huang, Limin Wang, Yu Qiao
Convolutional neural networks (CNN) have recently achieved remarkable successes in various image classification and understanding tasks. The deep features obtained at the top fully-connected layer of the CNN (FC-features) exhibit rich global semantic information and are extremely effective in image classification. On the other hand, the convolutional features in the middle layers of the CNN also contain meaningful local information, but are not fully explored for image representation. In this paper, we propose a novel Locally-Supervised Deep Hybrid Model (LS-DHM) that effectively enhances and explores the convolutional features for scene recognition...
November 16, 2016: IEEE Transactions on Image Processing: a Publication of the IEEE Signal Processing Society
Xiang Bai, Cong Yao, Wenyu Liu
In this paper, we are concerned with the problem of automatic scene text recognition, which involves localizing and reading characters in natural images. We investigate this problem from the perspective of representation and propose a novel multiscale representation, which leads to accurate, robust character identification and recognition. This representation consists of a set of mid-level primitives, termed as strokelets, which capture the underlying substructures of characters at different granularities. Strokelets possess four distinctive advantages: (1) Usability: automatically learned from character level annotations; (2) Robustness: insensitive to interference factors; (3) Generality: applicable to variant languages; and (4) Expressivity: effective at describing characters...
April 15, 2016: IEEE Transactions on Image Processing: a Publication of the IEEE Signal Processing Society
Xiaoyang Wang, Qiang Ji
Current video event recognition research remains largely target-centered. For real-world surveillance videos, targetcentered event recognition faces great challenges due to large intra-class target variation, limited image resolution, and poor detection and tracking results. To mitigate these challenges, we introduced a context-augmented video event recognition approach. Specifically, we explicitly capture different types of contexts from three levels including image level, semantic level, and prior level. At the image level, we introduce two types of contextual features including the appearance context features and interaction context features to capture the appearance of context objects and their interactions with the target objects...
October 11, 2016: IEEE Transactions on Pattern Analysis and Machine Intelligence
Salman Khan, Munawar Hayat, Mohammed Bennamoun, Ferdous Sohel, Roberto Togneri
Indoor scene recognition is a multi-faceted and challenging problem due to the diverse intra-class variations and the confusing inter-class similarities that characterize such scenes. This paper presents a novel approach that exploits rich mid-level convolutional features to categorize indoor scenes. Traditional convolutional features retain the global spatial structure, which is a desirable property for general object recognition. We, however, argue that the structure-preserving property of the CNN activations is not of substantial help in the presence of large variations in scene layouts, e...
May 11, 2016: IEEE Transactions on Image Processing: a Publication of the IEEE Signal Processing Society
Weiyao Lin, Yang Zhou, Hongteng Xu, Junchi Yan, Mingliang Xu, Jianxin Wu, Zicheng Liu
Trajectory analysis is essential in many applications. In this paper, we address the problem of representing motion trajectories in a highly informative way, and consequently utilize it for analyzing trajectories. Our approach first leverages the complete information from given trajectories to construct a thermal transfer field which provides a contextrich way to describe the global motion pattern in a scene. Then, a 3D tube is derived which depicts an input trajectory by integrating its surrounding motion patterns contained in the thermal transfer field...
September 13, 2016: IEEE Transactions on Pattern Analysis and Machine Intelligence
Zifeng Wu, Yongzhen Huang, Liang Wang, Xiaogang Wang, Tieniu Tan
This paper studies an approach to gait based human identification via similarity learning by deep convolutional neural networks (CNNs).With a pretty small group of labeled multi-view human walking videos, we can train deep networks to recognize the most discriminative changes of gait patterns which suggest the change of human identity. To the best of our knowledge, this is the first work based on deep CNNs for gait recognition in the literature. Here, we provide an extensive empirical evaluation in terms of various scenarios, namely, cross-view and cross-walkingcondition, with different preprocessing approaches and network architectures...
March 23, 2016: IEEE Transactions on Pattern Analysis and Machine Intelligence
Sebastian Schwarz, Michael Mangan, Jochen Zeil, Barbara Webb, Antoine Wystrach
Ants can navigate over long distances between their nest and food sites using visual cues [1, 2]. Recent studies show that this capacity is undiminished when walking backward while dragging a heavy food item [3-5]. This challenges the idea that ants use egocentric visual memories of the scene for guidance [1, 2, 6]. Can ants use their visual memories of the terrestrial cues when going backward? Our results suggest that ants do not adjust their direction of travel based on the perceived scene while going backward...
February 6, 2017: Current Biology: CB
Christine N Smith, Larry R Squire
Eye movements can reflect memory. For example, participants make fewer fixations and sample fewer regions when viewing old versus new scenes (the repetition effect). It is unclear whether the repetition effect requires that participants have knowledge (awareness) of the old-new status of the scenes or if it can occur independent of knowledge about old-new status. It is also unclear whether the repetition effect is hippocampus-dependent or hippocampus-independent. A complication is that testing conscious memory for the scenes might interfere with the expression of unconscious (unaware), experience-dependent eye movements...
February 2017: Learning & Memory
Delphine Grynberg, Pierre Maurage, Jean-Louis Nandrino
BACKGROUND: Prior research has repeatedly shown that alcohol dependence is associated with a large range of impairments in psychological processes, which could lead to interpersonal deficits. Specifically, it has been suggested that these interpersonal difficulties are underpinned by reduced recognition and sharing of others' emotional states. However, this pattern of deficits remains to be clarified. The present study thus aimed to investigate whether alcohol dependence is associated with impaired abilities in decoding contextual complex emotions and with altered sharing of others' emotions...
January 16, 2017: Alcoholism, Clinical and Experimental Research
Manfred Hartbauer
Modern cars are equipped with both active and passive sensor systems that can detect potential collisions. In contrast, locusts avoid collisions solely by responding to certain visual cues that are associated with object looming. In neurophysiological experiments, I investigated the possibility that the 'collision-detector neurons' of locusts respond to impending collisions in films recorded with dashboard cameras of fast driving cars. In a complementary modelling approach, I developed a simple algorithm to reproduce the neuronal response that was recorded during object approach...
February 15, 2017: Bioinspiration & Biomimetics
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"