Filters








56 Hits in 8.4 sec

Exploring Consistent Preferences

Lei Zhu, Zi Huang, Xiaojun Chang, Jingkuan Song, Heng Tao Shen
2017 Proceedings of the 2017 ACM on Multimedia Conference - MM '17  
Motivated by the characteristic of landmark, we explore the consistent preferences of tourists on landmark as pair-exemplars for scalable discrete hashing learning.  ...  In this paper, we propose a novel discrete hashing with pair-exemplar (DHPE) to support scalable and e cient large-scale CBVLS.  ...  In this paper, we explore the consistent preferences of tourists on landmark as pair-exemplars for scalable landmark hashing.  ... 
doi:10.1145/3123266.3123301 dblp:conf/mm/ZhuHCSS17 fatcat:macfoja72naytapxfzcmn6rz64

Improved Similarity Search for Large Data in Machine Learning and Robotics

Josiah Walker
2019 Figshare  
to consider total memory usage, scalability, and sometimes construction costs for the search structures.This thesis presents a locality-sensitive hash (LSH) code generation method which has a lower computational  ...  for locality-sensitive hash collections is also presented.  ...  Search area for 5 hash functions shown, each with random o↵sets. Figure 2 . 2 10 shows the patches explored by naive search for a collection of 5 grid-based hash functions.  ... 
doi:10.6084/m9.figshare.9942509 fatcat:ajvkwfnmyff6hjw7kh2njeuosm

2021 Index IEEE Transactions on Multimedia Vol. 23

2021 IEEE transactions on multimedia  
The Author Index contains the primary entry for each item, listed under the first author's name.  ...  ., +, TMM 2021 3907-3918 Rank-Consistency Deep Hashing for Scalable Multi-Label Image Search.  ...  ., +, TMM 2021 1722-1730 Deep Collaborative Discrete Hashing With Semantic-Invariant Structure Construction.  ... 
doi:10.1109/tmm.2022.3141947 fatcat:lil2nf3vd5ehbfgtslulu7y3lq

Do We Need More Training Data?

Xiangxin Zhu, Carl Vondrick, Charless C. Fowlkes, Deva Ramanan
2015 International Journal of Computer Vision  
Datasets for training object recognition systems are steadily increasing in size.  ...  This paper investigates the question of whether existing detectors will continue to improve as data grows, or saturate in performance due to limited model complexity and the Bayes risk associated with  ...  In the extreme case, each mixture will consist of a single training exemplar.  ... 
doi:10.1007/s11263-015-0812-2 fatcat:wk3igce2xnexfj2xa775knp6dm

NeuMapper: A scalable computational framework for multiscale exploration of the brain's dynamical organization

Caleb Geniesse, Samir Chowdhury, Manish Saggar
2022 Network Neuroscience  
Here, we present a novel computational framework for Mapper—designed specifically for neuroimaging data—that removes limitations and reduces computational costs associated with dimensionality reduction  ...  and parameter exploration.  ...  different tasks are connected to each other without any preference for those associated with the same task).  ... 
doi:10.1162/netn_a_00229 pmid:35733428 pmcid:PMC9207992 fatcat:rz57dwfvrrbb5iyqhhmgfgf3nu

2020 Index IEEE Transactions on Circuits and Systems for Video Technology Vol. 30

2020 IEEE transactions on circuits and systems for video technology (Print)  
Lai, H., +, TCSVT April 2020 1162-1172 SCRATCH: A Scalable Discrete Matrix Factorization Hashing Framework for Cross-Modal Retrieval.  ...  ., +, TCSVT Oct. 2020 3788-3802 SCRATCH: A Scalable Discrete Matrix Factorization Hashing Framework for Cross-Modal Retrieval.  ...  A Memory-Efficient Hardware Architecture for Connected Component Labeling in Embedded System.  ... 
doi:10.1109/tcsvt.2020.3043861 fatcat:s6z4wzp45vfflphgfcxh6x7npu

Index—Volumes 1–89

1997 Artificial Intelligence  
searching -75 searching, min/max -422 with probability nodes 257 game logic I1 12.1258 with continuous terminal values 162 map for metric information 268 with WIN-LOSS terminals 162 fuzzy sets  ...  approach 584 exemplars, indexing -584 exhaustive I86 assumptions 683 invocation 178 model-driven approach 131 exhaustive search 2 10, 1270 strategy 257 to a given depth 77 with cut-offs 77 exhaustivity  ... 
doi:10.1016/s0004-3702(97)80122-1 fatcat:6az7xycuifaerl7kmv7l3x6rpm

Edge-Cloud Polarization and Collaboration: A Comprehensive Survey for AI [article]

Jiangchao Yao, Shengyu Zhang, Yang Yao, Feng Wang, Jianxin Ma, Jianwei Zhang, Yunfei Chu, Luo Ji, Kunyang Jia, Tao Shen, Anpeng Wu, Fengda Zhang (+6 others)
2022 arXiv   pre-print
Specifically, we are the first to set up the collaborative learning mechanism for cloud and edge modeling with a thorough review of the architectures that enable such mechanism.  ...  In this survey, we conduct a systematic review for both cloud and edge AI.  ...  Due to the latency constraint for the multimedia data, the hash techniques are usually explored to accelerate the retrieval [89] .  ... 
arXiv:2111.06061v3 fatcat:5rq6s5s4cvcidblidgahwynp34

A comprehensive study of visual event computing

WeiQi Yan, Declan F. Kieran, Setareh Rafatirad, Ramesh Jain
2010 Multimedia tools and applications  
We start by presenting events and their classifications, and continue with discussing the problem of capturing events in terms of photographs, videos, etc, as well as the methodologies for event storing  ...  This work was partially supported by QUB research project: Unusual event detection in audio-visual surveillance for public transport (NO.D6223EEC).  ...  Acknowledgements We appreciate for the great help from the colleagues of Queen's University Belfast(QUB): Prof. Danny Crookes, Dr. Weiru Liu, Dr. Paul Miller, and Dr. Xiwu Gu etc.  ... 
doi:10.1007/s11042-010-0560-9 fatcat:ak6u3eefefgjhmbpr7asru3n7u

Towards large-scale nonparametric scene parsing of images and video [article]

Frederick Tung
2017
We formulate exemplar-based scene parsing for both 2D (from images) and 3D (from video), and demonstrate accurate labelling on standard benchmarks.  ...  Its goal is a complete and consistent semantic interpretation of the structure of the real world scene.  ...  Leveraging big data for search allows for the development of powerful exemplar-based algorithms for visual recognition.  ... 
doi:10.14288/1.0343064 fatcat:vwo3iigvdjajvn4o2br4wv5g4e

Deep Learning in Science [article]

Stefano Bianchini, Moritz Müller, Pierre Pelletier
2020 arXiv   pre-print
We find that DL adoption is negatively correlated with re-combinatorial novelty, but positively correlated with expectation as well as variance of citation performance.  ...  However, the 'DL principle' qualifies for its versatility as the nucleus of a general scientific method that advances science in a measurable way.  ...  The basic idea consists in examining for each paper whether it makes first-time-ever combinations of referenced journals -i.e., its list of references contains journal pairs that have never appeared jointly  ... 
arXiv:2009.01575v2 fatcat:4ttqgjdjfjbydp7flnhcgg5p7m

Artificial Intelligence and Law

ANTONIO A. MARTINO
1994 International Journal of Law and Information Technology  
Performance of exploration and search Retrieval time for a concept search and time for building semantic space exploration are also characterized for various corpus sizes and complexity of queries.  ...  And this methodology is so much more preferable than keyword searching.  ...  MD5 Hash Value Sampling: Random sample sets created by running a MS SQL Server query to select all records with MD5 hash values beginning with two designated characters (e.g., AF or 4A).  ... 
doi:10.1093/ijlit/2.2.154 fatcat:ff7kwvvn3vcbblhlkf63oqntyu

Artificial Intelligence and the Law

Charlotte Walker-Osborn, Christopher Chan
2017 ITNOW  
Performance of exploration and search Retrieval time for a concept search and time for building semantic space exploration are also characterized for various corpus sizes and complexity of queries.  ...  And this methodology is so much more preferable than keyword searching.  ...  MD5 Hash Value Sampling: Random sample sets created by running a MS SQL Server query to select all records with MD5 hash values beginning with two designated characters (e.g., AF or 4A).  ... 
doi:10.1093/itnow/bwx017 fatcat:62ezubai3fcwlpie35xjq3iyem

Large-Scale Machine Learning for Classification and Search

Wei Liu
2017
Our first approach is to explore data graphs to aid classification and nearest neighbor search.  ...  Large-Scale Semi-Supervised Learning: We employ Anchor Graphs to develop a scalable solution for [...]  ...  We follow two search procedures, i.e., hash lookup and Hamming ranking, for consistent evaluations across the two data sets.  ... 
doi:10.7916/d8f195s6 fatcat:src6ohjplfghxfjsyw6puqfjje

Learning Neural Textual Representations for Citation Recommendation

Binh Thanh Kieu, Inigo Jauregi Unanue, Son Bao Pham, Hieu Xuan Phan, Massimo Piccardi
2021 2020 25th International Conference on Pattern Recognition (ICPR)  
Based CNN for Speech Object Classification of Remote Sensing Images Based on Optimized Projection Supervised Discrete Hashing DAY 4 -Jan 15, 2021 Weng, Nina; Wang, Jiahao; Li, Annan; Wang, Yunhong 2778  ...  DAY 3 -Jan 14, 2021 -DAY 4 -Jan 15, 2021 Li, Weijian; Liao, Haofu; Miao, Shun; Lu, Le; Luo, Jiebo 1144 OS T2.2 Unsupervised Learning of Landmarks Based on Inter-Intra Subject Consistencies  ... 
doi:10.1109/icpr48806.2021.9412725 fatcat:3vge2tpd2zf7jcv5btcixnaikm
« Previous Showing results 1 — 15 out of 56 results