Filters








5,187 Hits in 5.4 sec

Blocks That Shout: Distinctive Parts for Scene Classification

Mayank Juneja, Andrea Vedaldi, C.V. Jawahar, Andrew Zisserman
2013 2013 IEEE Conference on Computer Vision and Pattern Recognition  
The automatic discovery of distinctive parts for an object or scene class is challenging since it requires simultaneously to learn the part appearance and also to identify the part occurrences in images  ...  We show that our method can learn parts which are significantly more informative and for a fraction of the cost, compared to previous part-learning methods such as Singh et al. [4] .  ...  Blocks that shout: learning distinctive parts In characterizing images of particular scene classes, e.g. a computer room, library, book store, auditorium, theatre, etc., it is not hard to think of distinctive  ... 
doi:10.1109/cvpr.2013.124 dblp:conf/cvpr/JunejaVJZ13 fatcat:anbvzjavlbgztfiaqpzwa6x7nu

Assessing the Performances of different Neural Network Architectures for the Detection of Screams and Shouts in Public Transportation

Pierre Laffitte, Yun Wang, David Sodoyer, Laurent Girin
2018 Expert systems with applications  
detection of screams and shouts.  ...  The present article proposes an audio-based intelligent system for surveillance in public transportation, investigating the use of some state-of-the-art artificial intelligence methods for the automatic  ...  For frames above a certain threshold, −20dB for instance, the 8 classification into shouts may be easier.  ... 
doi:10.1016/j.eswa.2018.08.052 fatcat:5w67iau5vbhttl4lq63fk2hyxi

Adaptive Indoor Scene Classification with Multi-SVM Classification to solve Multi-Class Problem

Neetu Bala, Harpreet Singh
2017 International Journal of Advanced Research in Computer Science and Software Engineering  
This project presents an indoor scene detection technique mainly based on the appearance based feature segmentation, SVM training and SVM classification methods to recognize the indoor scenes.  ...  For example, the template-matching methods are used for indoor scene localization and detection by computing the correlation of an input image to a standard and training scene appearance or pattern.  ...  [5] have worked on blocks that shout: distinctive parts for scene classification. In this paper, authors have proposed a simple, efficient, and effective method to do so.  ... 
doi:10.23956/ijarcsse/v7i2/0147 fatcat:m7cmlzgdorbppefm3mzzaauxle

Shouts & Whispers: Re-engaging Disaffected Girls through Peer-Teaching Drama

Morag G Morrison, University, My, Bruce Burton
2018
Although my first project had its genesis as part of a large Action Research study, as I began to focus on the experiences of these three Year 11 girls, it became apparent that a closer analysis of the  ...  In the course of research for the first project i.e. how Drama might be used to teach Conflict management, it was noted that peer teaching as a strategy in itself seemed to have a marked impact on several  ...  I know it's real hard for you not to shout at somebody. You get so stressed, but I don't think shouting does anything. (Kayleigh.  ... 
doi:10.25904/1912/2468 fatcat:yn4vds5oxbgaznfhc3hehepole

Resolving the neural dynamics of visual and auditory scene processing in the human brain: a methodological approach

Radoslaw Martin Cichy, Santani Teng
2017 Philosophical Transactions of the Royal Society of London. Biological Sciences  
Finally, we discuss the limits of this perspective and sketch a concrete roadmap for future research. This article is part of the themed issue 'Auditory and visual scene analysis'.  ...  We showcase two recent efforts that have been undertaken in this spirit and provide novel results about visual and auditory scene analysis.  ...  We thank Aude Oliva, Dimitrios Pantazis, Aditya Khosla and Antonio Torralba for support and collaboration, and Talia Konkle and Chen-Ping Yu for helpful comments on DNNs. rstb.royalsocietypublishing.org  ... 
doi:10.1098/rstb.2016.0108 pmid:28044019 pmcid:PMC5206276 fatcat:xusihs36drbmrjobpwavrbajle

Discovering and Aligning Discriminative Mid-level Features for Image Classification

Ronan Sicre, Frederic Jurie
2014 2014 22nd International Conference on Pattern Recognition  
This paper proposes a new algorithm for image recognition, which consists of (i) modeling categories as a set of distinctive parts that are discovered automatically, (ii) aligning them across images while  ...  The so-obtained parts are free of any appearance constraint and are optimized to allow the distinction between the categories to be recognized.  ...  features, as the structural element patch model [27] or the blocks that shout [8] .  ... 
doi:10.1109/icpr.2014.345 dblp:conf/icpr/SicreJ14 fatcat:vptvsza2gzd6hgqxpokwv3ujiu

Time and Encoding Effects in the Concealed Knowledge Test

Travis L. Seymour, Becky R. Fraynt
2009 Applied Psychophysiology and Biofeedback  
Results show that more elaborately encoded information afforded higher detection accuracy than poorly encoded items.  ...  Although classification accuracy following deep study was unaffected by delay, detection of poorly elaborated information was initially high, but compromised after 1 week.  ...  We also thank Colleen Seifert, Eric Schumacher, Chris Baker, and anonymous reviewers for their comments and suggestions.  ... 
doi:10.1007/s10484-009-9092-3 pmid:19536648 pmcid:PMC2727398 fatcat:dthxn565gvg4nfpbpmz2k7uwuu

Multi-Moments in Time: Learning and Interpreting Models for Multi-Action Video Understanding [article]

Mathew Monfort, Bowen Pan, Kandan Ramakrishnan, Alex Andonian, Barry A McNamara, Alex Lascelles, Quanfu Fan, Dan Gutfreund, Rogerio Feris, Aude Oliva
2021 arXiv   pre-print
Consequently, models can be incorrectly penalized for classifying actions that exist in the videos but are not explicitly labeled and do not learn the full spectrum of information present in each video  ...  Videos capture events that typically contain multiple sequential, and simultaneous, actions even in the span of only a few seconds.  ...  For example, we can consider a feature in the final residual block of the network that has been interpreted as a highway scene feature.  ... 
arXiv:1911.00232v4 fatcat:u245hymiwjbd7mymr27ukmt4ty

Augmenting Interpersonal Communication through Connected Lighting

Margaret E. Morris, Douglas M. Carmean, Artem Minyaylov, Luis Ceze
2017 Proceedings of the 2017 CHI Conference Extended Abstracts on Human Factors in Computing Systems - CHI EA '17  
This paper describes a system, WeLight, that we developed to facilitate communication. It allows individuals to configure the lights in one another's homes as well as their own.  ...  To support spontaneous communication within and across households, we developed scene creation capabilities involving natural language processing and image search.  ...  For example, a toddler and her friends enjoyed seeing how they could make the room change color by shouting out words to her dad, who transcribed the words into WeLight text messages.  ... 
doi:10.1145/3027063.3053141 dblp:conf/chi/MorrisCMC17 fatcat:xm4z3vdju5hmbkfgmubldazcp4

An Adaptive Framework for Acoustic Monitoring of Potential Hazards

Stavros Ntalampiras, Ilyas Potamitis, Nikos Fakotakis
2009 EURASIP Journal on Audio, Speech, and Music Processing  
The primary goal is the continuous acoustic monitoring of a scene for potentially hazardous events in order to help an authorized officer to take the appropriate actions towards preventing human loss and  ...  A feature of the proposed system is its model adaptation loop that provides adaptability to different sound environments.  ...  The feature extraction part is Matlab c based while the classification part is written in C++. The system is practically real time since it reports an event with an average delay of 2 seconds.  ... 
doi:10.1155/2009/594103 fatcat:jdmrekbzzrbofjvui7tcffdegq

The analysis of perception via preference: A strategy for studying how the environment is experienced

Rachel Kaplan
1985 Landscape and Planning  
The analysis of perception via preference: a strategy for studying how the environment is experienced. Landscape Plann., 12: 161--176.  ...  In the Forest Service system, for example, the notion of Character Type identifies the basic classifications.  ...  It does not call for shouting matches, nor is it at the mercy of the vocal few. It draws on the strengths of the public and the designer alike.  ... 
doi:10.1016/0304-3924(85)90058-9 fatcat:xmu57ilxevfftbil5mfzi3uida

Mining Mid-level Features for Image Classification

Basura Fernando, Elisa Fromont, Tinne Tuytelaars
2014 International Journal of Computer Vision  
In this paper we propose a new and effective scheme for extracting mid-level features for image classification, based on relevant pattern mining.  ...  We show that these bag-of-FLHs are more discriminative than traditional bag-of-words and yield state-of-the-art results on various image classification benchmarks, including Pascal VOC.  ...  ] , discriminative patches [41] or blocks that shout [22] .  ... 
doi:10.1007/s11263-014-0700-1 fatcat:bxpm4ntmp5gwhgng344ofeneei

Audio Surveillance: a Systematic Review [article]

Marco Crocco, Marco Cristani, Andrea Trucco, Vittorio Murino
2014 arXiv   pre-print
For each of these tasks, all the significant works are reviewed, detailing their pros and cons and the context for which they have been proposed.  ...  comprehensive survey: a general taxonomy, inspired by the more widespread video surveillance field, is proposed in order to systematically describe the methods covering background subtraction, event classification  ...  A large part of them was developed for specific tasks such as speech recognition [Hunt et al., 1980] , speaker recognition [Reynolds, 1994] , music classification [Tzanetakis and Cook, 2002] or music  ... 
arXiv:1409.7787v1 fatcat:75lzk33wnnho5h3pbqr7nqaxxy

SuperPixel based mid-level image description for image recognition

H. Emrah Tasli, Ronan Sicre, Theo Gevers
2015 Journal of Visual Communication and Image Representation  
in order to obtain a superior scene description.  ...  We hypothesize that the commonly used pixel based low-level descriptions are useful but can be improved with the introduction of mid-level region information.  ...  features, as the structural element patch model [30] , the blocks that shout [31] , or the discriminative parts [32] .  ... 
doi:10.1016/j.jvcir.2015.09.021 fatcat:xgjdpk3n3jh4hdvifpummwade4

Cross-Task Transfer for Geotagged Audiovisual Aerial Scene Recognition [article]

Di Hu, Xuhong Li, Lichao Mou, Pu Jin, Dong Chen, Liping Jing, Xiaoxiang Zhu, Dejing Dou
2020 arXiv   pre-print
of exploiting the audio information for the aerial scene recognition.  ...  For this purpose, we have constructed a new dataset named AuDio Visual Aerial sceNe reCognition datasEt (ADVANCE).  ...  t for aerial scene classification N * network, which can be one of the network for extracting visual representation, the network for extracting audio representation, the pretrained (fixed) one for extracting  ... 
arXiv:2005.08449v2 fatcat:hf6a7oxsjba7jffgrfk7so6tsu
« Previous Showing results 1 — 15 out of 5,187 results