Filters








14,162 Hits in 5.0 sec

Visual Vocabulary Learning and Its Application to 3D and Mobile Visual Search [article]

Liujuan Cao
2012 arXiv   pre-print
Especial focuses would be also given for the recent trends in supervised/unsupervised vocabulary optimization, compact descriptor for visual search, as well as in multi-view based 3D object representation  ...  In this technical report, we review related works and recent trends in visual vocabulary based web image search, object recognition, mobile visual search, and 3D object retrieval.  ...  Vocabulary Tree [5] , Approximate K-means [6] , Hamming Embedding [14] , Locality Sensitive Hashing [15] and their variances [16] [17] [6] [18] [8] [19] .  ... 
arXiv:1207.7244v1 fatcat:b6y7yvvcu5davkwh3zuv762qq4

Learning Compact Visual Descriptors for Low Bit Rate Mobile Landmark Search

Ling-Yu Duan, Jie Chen, Rongrong Ji, Tiejun Huang, Wen Gao
2013 The AI Magazine  
The learning process involves segmenting the landmark photo collection by discrete geographical regions using Gaussian mixture model, and then boosting a ranking sensitive vocabulary within each region  ...  Beyond landmark search, this article will summarize the MPEG standarization progress of compact descriptor for visual search (CDVS) (Yuri et al. 2010; Yuri et al. 2011) towards application interoperability  ...  Toward compact visual descriptors, this working pipeline essentially employs a contextual learning to optimize the vocabularies (in terms of scale and retrieval performance of test queries) with respect  ... 
doi:10.1609/aimag.v34i2.2469 fatcat:a26mz5iqs5dwtbuwdovlwaeoca

Automatic Tissue Differentiation Based on Confocal Endomicroscopic Images for Intraoperative Guidance in Neurosurgery

Ali Kamen, Shanhui Sun, Shaohua Wan, Stefan Kluckner, Terrence Chen, Alexander M. Gigler, Elfriede Simon, Maximilian Fleischer, Mehreen Javed, Samira Daali, Alhadi Igressa, Patra Charalampaki
2016 BioMed Research International  
Diagnosis of tumor and definition of tumor borders intraoperatively using fast histopathology is often not sufficiently informative primarily due to tissue architecture alteration during sample preparation  ...  Confocal laser microscopy (CLE) provides microscopic information of tissue in real-time on cellular and subcellular levels, where tissue characterization is possible.  ...  First, 1-2 drops of 0.01 mg/mL acriflavine hydrochloride AF from Sigma Pharmaceuticals, Victoria, Australia, dissolved in saline were administered topically to the excised tissue sample.  ... 
doi:10.1155/2016/6183218 pmid:27127791 pmcid:PMC4835625 fatcat:ju5ulk2mgvh37ivtgz7k2h5x4e

Category Level Object Segmentation by Combining Bag-of-Words Models with Dirichlet Processes and Random Fields

Diane Larlus, Jakob Verbeek, Frédéric Jurie
2009 International Journal of Computer Vision  
Gibbs sampling is used for parameter estimations and object segmentation.  ...  First, we evaluate the result of two methods to build visual vocabularies.  ...  Towards a pixel-level segmentation The model presented above works at the patch level, but our goal is to produce a precise pixel level segmentation.  ... 
doi:10.1007/s11263-009-0245-x fatcat:pr44gilf4vhxjhbysuxgpbvzrm

Image Retrieval based on Bag-of-Words model [article]

Jialu Liu
2013 arXiv   pre-print
A common way to achieve this is first quantizing local descriptors into visual words, and then applying scalable textual indexing and retrieval schemes.  ...  As local descriptors like SIFT demonstrate great discriminative power in solving vision problems like object recognition, image classification and annotation, more and more state-of-the-art large scale  ...  We then sequentially discuss the key point detection, local description, vocabulary generation, vector quantization, indexing and search.  ... 
arXiv:1304.5168v1 fatcat:6jycm42bg5guzgzlzdbc2pydby

Quality of caregiver-child play interactions with toddlers born preterm and full term: Antecedents and language outcome

Elizabeth C. Loi, Kelsey E.C. Vaca, Melanie D. Ashland, Virginia A. Marchman, Anne Fernald, Heidi M. Feldman
2017 Early Human Development  
Language skills are sensitive to the quality of caregiver-child interactions.  ...  The caregiver composite measure was associated with later receptive vocabulary at 36 months.  ...  Third, in this small, relatively high-SES sample, we may not have sampled the full range of possible levels of caregiver behavior.  ... 
doi:10.1016/j.earlhumdev.2017.10.001 pmid:29111418 pmcid:PMC5689464 fatcat:6futtpou45dh5pomxjjld5ukei

Towards low bit rate mobile visual search with multiple-channel coding

Rongrong Ji, Ling-Yu Duan, Jie Chen, Hongxun Yao, Yong Rui, Shih-Fu Chang, Wen Gao
2011 Proceedings of the 19th ACM international conference on Multimedia - MM '11  
In this paper, we propose a multiple-channel coding scheme to extract compact visual descriptors for low bit rate mobile visual search.  ...  at the mobile end (such as GPS tags for mobile visual search and 2D barcodes or RFID tags for mobile product search), together with the visual statistics at the reference database, to learn multiple coding  ...  Towards low bit rate mobile visual search, previous local descriptors e.g.  ... 
doi:10.1145/2072298.2072372 dblp:conf/mm/JiDCYRCG11 fatcat:ir7dmmnitvg2fgdsitm376oqde

Measuring Conversational Productivity in Child Forensic Interviews [article]

Victor Ardulov, Manoj Kumar, Shanna Williams, Thomas Lyon, Shrikanth Narayanan
2018 arXiv   pre-print
As a first step toward computationally modeling and producing quality spoken interviewing strategies and a generalized understanding of interview dynamics, we propose a novel methodology to computationally  ...  model effectiveness criteria, by applying summarization and topic modeling techniques to objectively measure and rank the responsiveness and conversational productivity of a child during FI.  ...  We further suggest the value captured by measuring responsiveness is equivalent to a time-dilated matching of vocabulary usage corresponding to lexical entrainment of local interactions, a known indicator  ... 
arXiv:1806.03357v1 fatcat:ca2awgjlufayhn65rfn7cdmvo4

Semantic hashing

Ruslan Salakhutdinov, Geoffrey Hinton
2009 International Journal of Approximate Reasoning  
This way of extending the efficiency of hash-coding to approximate matching is much faster than locality sensitive hashing, which is the fastest current method.  ...  For relatively small codes we use semantic hashing and for larger binary codes we simply compare the code of the query document to the codes Semantically Similar Documents Document Address Space Semantic  ...  It is shown in [16] that for any approximating distribution Q(hjv) we can write: This is exactly what is being learned when samples from p(hjv) are used as the training data for a higher-level RBM.  ... 
doi:10.1016/j.ijar.2008.11.006 fatcat:c7ugvfdvtjf4xgq4kwrmu5dt6m

Four Years of FAccT: A Reflexive, Mixed-Methods Analysis of Research Contributions, Shortcomings, and Future Prospects [article]

Benjamin Laufer, Sameer Jain, A. Feder Cooper, Jon Kleinberg, Hoda Heidari
2022 arXiv   pre-print
On the qualitative front, we develop a protocol for reviewing and coding prior FAccT papers, tracing their distribution of topics, methods, datasets, and disciplinary roots.  ...  We also design and administer a questionnaire to reflect the voices of FAccT community members and affiliates on a wide range of topics.  ...  For example, fairness/sensitive-attributes contains attribute-class related words, including "parity", "protected", and "sensitive"; fairness/optimization has optimization-related words, such as "optimal  ... 
arXiv:2206.06738v1 fatcat:axn3224rpjdfxgb5mh7qgrrgte

Graph Structural-topic Neural Network [article]

Qingqing Long, Yilun Jin, Guojie Song, Yi Li, Wei Lin
2020 arXiv   pre-print
Graph Convolutional Networks (GCNs) achieved tremendous success by effectively gathering local features for nodes.  ...  However, such local structural patterns are shown to be indicative of node properties in numerous fields.  ...  ACKNOWLEDGMENTS We are grateful to Ziyao Li for his insightful advice towards this work.  ... 
arXiv:2006.14278v2 fatcat:jxpqezg3sbdndkjx5lbo4mmxea

Reliable and Scalable Variational Inference for the Hierarchical Dirichlet Process

Michael C. Hughes, Dae Il Kim, Erik B. Sudderth
2015 International Conference on Artificial Intelligence and Statistics  
Improving on the point estimates of topic probabilities used in previous work, we define full variational posteriors for all latent variables and optimize parameters via a novel surrogate likelihood bound  ...  We show that this approach has crucial advantages for data-driven learning of the number of topics.  ...  Collapsed variational methods (Teh et al., 2008) are based on a sophisticated family of marginal likelihood bounds, but lead to challenging optimization problems and sensitivity to initialization.  ... 
dblp:conf/aistats/HughesKS15 fatcat:ab3kwtvtg5agjoczlzht7o6nfa

Bridging the Vocabulary Gap between Health Seekers and Healthcare Knowledge

Liqiang Nie, Yi-Liang Zhao, Mohammad Akbari, Jialie Shen, Tat-Seng Chua
2015 IEEE Transactions on Knowledge and Data Engineering  
Global learning, on the other hand, works towards enhancing the local medical coding via collaboratively discovering missing key terminologies and keeping off the irrelevant terminologies by analyzing  ...  To bridge this gap, this paper presents a novel scheme to code the medical records by jointly utilizing local mining and global learning approaches, which are tightly linked and mutually reinforced.  ...  in high-level topic level via continuous quantization.  ... 
doi:10.1109/tkde.2014.2330813 fatcat:u7mtdhsb65fwlhh254ql45dkeu

Learning to Distribute Vocabulary Indexing for Scalable Visual Search

Rongrong Ji, Ling-Yu Duan, Jie Chen, Lexing Xie, Hongxun Yao, Wen Gao
2013 IEEE transactions on multimedia  
We optimize the distribution of vocabulary indexing from a machine learning perspective, which provides a "memory light" search paradigm that leverages the computational power across multiple servers to  ...  "How to distribute" is addressed by learning an optimal distribution function, which maximizes the uniformity of assigning the words of a given query to multiple servers.  ...  Comparing to topic models in abstracting a compact topical level image representation, our aim is to partition concurrent words into multiple machines as uniform as possible, so as to minimize the parallel  ... 
doi:10.1109/tmm.2012.2225035 fatcat:m2xcewl5kffq3cq6qek5forusm

Practices, norms, and aspirations regarding the construction, validation, and reuse of code sets in the analysis of real-world data [article]

Sigfried Gold, Harold Lehmann, Lisa Schilling, Wayne Lutters
2021 medRxiv   pre-print
Methods: Survey and field study using semi-structured interviews of a purposive sample of code set practitioners.  ...  A primary divide exists between those who rely on empirical techniques using patient-level data and those who only rely on expertise and semantic data.  ...  interoperable at the code set level.  ... 
doi:10.1101/2021.10.14.21264917 fatcat:w7jsm6e6hrc57hcirv2ykdpkku
« Previous Showing results 1 — 15 out of 14,162 results