Filters








10,852 Hits in 4.8 sec

One Sketch for All: One-Shot Personalized Sketch Segmentation [article]

Anran Qi, Yulia Gryaditskaya, Tao Xiang, Yi-Zhe Song
2021 arXiv   pre-print
We present the first one-shot personalized sketch segmentation method.  ...  We evaluate our method against the state-of-the-art segmentation and perceptual grouping baselines re-purposed for the one-shot setting and against two few-shot 3D shape segmentation methods.  ...  The problem of one-shot personalized sketch segmentation is however non-trivial.  ... 
arXiv:2112.10838v1 fatcat:td2xkgyzpnamnpkckxq2gtjiu4

On Training Sketch Recognizers for New Domains [article]

Kemal Tugrul Yesilbek, T. Metin Sezgin
2021 arXiv   pre-print
We pose learning from small datasets as a key problem for the deep sketch recognition field, one which has been ignored in the bulk of the existing literature.  ...  While existing datasets contain sketches of a limited set of generic objects, each new domain inevitably requires collecting new data for training domain specific recognizers.  ...  Unlike SBIR, our focus is on recognition instead of retrieval. The efficacy of zero-shot SBIR methods for recognition tasks has not been assessed.  ... 
arXiv:2104.08850v1 fatcat:yykeqpp6d5bdhhku4s32bf647q

Speech and sketching for multimodal design

Aaron Adler, Randall Davis
2007 ACM SIGGRAPH 2007 courses on - SIGGRAPH '07  
We studied the behavior of people sketching and speaking, and from this derived a set of rules for segmenting and aligning the signals from both modalities.  ...  While sketches are commonly and effectively used in the early stages of design, some information is far more easily conveyed verbally than by sketching.  ...  The hand segmentation had the advantage of having all the sketching and speech events to examine at once, as well as the spatial relationships between sketched components.  ... 
doi:10.1145/1281500.1281525 dblp:conf/siggraph/AdlerD07 fatcat:ovwyaffeqzb7rh6fb73bipkary

Speech and sketching for multimodal design

Aaron Adler, Randall Davis
2006 ACM SIGGRAPH 2006 Courses on - SIGGRAPH '06  
We studied the behavior of people sketching and speaking, and from this derived a set of rules for segmenting and aligning the signals from both modalities.  ...  While sketches are commonly and effectively used in the early stages of design, some information is far more easily conveyed verbally than by sketching.  ...  The hand segmentation had the advantage of having all the sketching and speech events to examine at once, as well as the spatial relationships between sketched components.  ... 
doi:10.1145/1185657.1185792 dblp:conf/siggraph/AdlerD06 fatcat:usx5sp256rb5njjlq7eesfgkgm

Speech and sketching for multimodal design

Aaron Adler, Randall Davis
2004 Proceedings of the 9th international conference on Intelligent user interface - IUI '04  
We studied the behavior of people sketching and speaking, and from this derived a set of rules for segmenting and aligning the signals from both modalities.  ...  While sketches are commonly and effectively used in the early stages of design, some information is far more easily conveyed verbally than by sketching.  ...  The hand segmentation had the advantage of having all the sketching and speech events to examine at once, as well as the spatial relationships between sketched components.  ... 
doi:10.1145/964442.964483 dblp:conf/iui/AdlerD04 fatcat:xiruxkgkbra6zcivyqbdfe75la

Speech and sketching for multimodal design

Aaron Adler, Randall Davis
2004 Proceedings of the 9th international conference on Intelligent user interface - IUI '04  
We studied the behavior of people sketching and speaking, and from this derived a set of rules for segmenting and aligning the signals from both modalities.  ...  While sketches are commonly and effectively used in the early stages of design, some information is far more easily conveyed verbally than by sketching.  ...  The hand segmentation had the advantage of having all the sketching and speech events to examine at once, as well as the spatial relationships between sketched components.  ... 
doi:10.1145/964482.964483 fatcat:tdcxgp3nt5a2daql4ozbv7xori

Markov random fields for sketch based video retrieval

Rui Hu, Stuart James, Tinghuai Wang, John Collomosse
2013 Proceedings of the 3rd ACM conference on International conference on multimedia retrieval - ICMR '13  
We describe a new system for searching video databases using free-hand sketched queries.  ...  The MRF energy function is used to rank videos for relevance and contains unary, pairwise and higher-order potentials that reflect the colour, shape, motion and type of sketched objects.  ...  Our query sketches Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit  ... 
doi:10.1145/2461466.2461510 dblp:conf/mir/HuJWC13 fatcat:r2ybk5kmc5hqrbafjebbyj2yae

A Sketch-Based Approach for Interactive Organization of Video Clips

Yong-Jin Liu, Cui-Xia Ma, Qiufang Fu, Xiaolan Fu, Sheng-Feng Qin, Lexing Xie
2014 ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP)  
free-form sketching on touch devices.  ...  The third user study showed that, for video content organization, using sketch graph users took on average 1/3 less time than using a mass-market tool Movie Maker and took on average 1/4 less time than  ...  ACKNOWLEDGMENTS The authors thank the editor and the reviewers for their constructive comments that helped improve this article.  ... 
doi:10.1145/2645643 fatcat:s6ajyzqcp5e7fhxrnkuhkzm64m

Memetically Optimized MCWLD for Matching Sketches With Digital Face Images

H. S. Bhatt, S. Bharadwaj, R. Singh, M. Vatsa
2012 IEEE Transactions on Information Forensics and Security  
One of the important cues in solving crimes and apprehending criminals is matching sketches with digital face images.  ...  Comprehensive experimental evaluation on different sketch databases show that the proposed algorithm yields better identification performance compared to existing face recognition algorithms and two commercial  ...  ACKNOWLEDGEMENT The authors are thankful to Lois Gibson and Karen Taylor for providing the forensic sketch-digital image pairs. Special acknowledgement to Dr. A.  ... 
doi:10.1109/tifs.2012.2204252 fatcat:u33eilqs3vh4fbznrcrkofn6ui

Face Detection-based Video Key Frame Extraction [chapter]

Jian Yin, Su Huan Wang
2013 Lecture Notes in Electrical Engineering  
Further longer shots are segmented into sub shots based on location and camera motion features. Each shot and sub shot contains a number of frames.  ...  This paper presents the video key frame extraction for face recognition in video. The video sequences are segmented into shots by detecting gradual and abrupt cuts.  ...  Since we assume all the faces are to be in the frontal pose with normal lighting and Sub Shot Boundary Detection: The segmentation of shots neutral expression and have occlusions this algorithm in smaller  ... 
doi:10.1007/978-1-4471-4847-0_81 fatcat:fpccrs5v3jfuxn6bc5iacvkc3a

Semantic Sketch-Based Video Retrieval with Autocompletion

Claudiu Tanase, Ivan Giangreco, Luca Rossetto, Heiko Schuldt, Omar Seddati, Stephane Dupont, Ozan Can Altiok, Metin Sezgin
2016 Companion Publication of the 21st International Conference on Intelligent User Interfaces - IUI '16 Companion  
The latter is enabled by a predictive sketch-based UI that identifies likely candidates for the sketched object via state-of-the-art sketch recognition techniques and offers on-screen completion suggestions  ...  In this demo, we show how the sketch-based video retrieval of the IMOTION system is used in a collection of roughly 30,000 video shots.  ...  Sketch recognition and concept mapping The Demo At the demo, conference participants will be able to use the IMOTION UI to search for video shots on the basis of sketches they draw.  ... 
doi:10.1145/2876456.2879473 dblp:conf/iui/TanaseGRSSDAS16 fatcat:ntw37glsjbhv3d3bbh44ashkcy

One-Shot Learning of Sketch Categories with Co-regularized Sparse Coding [chapter]

Yonggang Qi, Wei-Shi Zheng, Tao Xiang, Yi-Zhe Song, Honggang Zhang, Jun Guo
2014 Lecture Notes in Computer Science  
To overcome this limitation, we propose a transfer learning framework which enables one-shot learning of sketch categories.  ...  We contribute a new dataset consisting of 7,760 human segmented sketches from 97 object categories.  ...  SVMwhere all one-shot instances are used for training SVM classifiers to classify unknown sketches.  ... 
doi:10.1007/978-3-319-14364-4_8 fatcat:lgr3kclx2jbmfgbka26bcrbeda

Simulating DNA Chip Design Using All-Electronic Graphene-Based Substrates

Ernane de Freitas Martins, Gustavo Troiano Feliciano, Ralph Hendrik Scheicher, Alexandre Reily Rocha
2019 Molecules  
In this paper, we present a theoretical investigation of an all-electronic biochip based on graphene to detect DNA including a full dynamical treatment for the environment.  ...  Our proposed device design is based on the changes in the electronic transport properties of graphene interacting with DNA strands under the effect of the solvent.  ...  Abbreviations The following abbreviations are used in this manuscript: Figure 1 . 1 Sketch of all-electronic biochips. An active region that acts as a substrate connecting a source and a drain.  ... 
doi:10.3390/molecules24050951 fatcat:ulnvlfogsrg6loyttbihhnnvfm

Hume's Principle and the Number of all Objects

Ian Rumfitt
2001 Noûs  
is 'Nx:Fx', or 'NF' for short.  ...  Boolos also used the name Frege arithmetic to stand for the system obtained by adjoining Hume's principle to axiomatic second-order logic, and the name Frege's theorem for the result that 'zero', 'immediately  ...  Such a set would be, for example, $tree, person, natural number, molecule, direction%.  ... 
doi:10.1111/0029-4624.00350 fatcat:s3g4zx6ibjaxbbe7qy3mkcjwpy

VideoQ

Shih-Fu Chang, William Chen, Horace J. Meng, Hari Sundaram, Di Zhong
1997 Proceedings of the fifth ACM international conference on Multimedia - MULTIMEDIA '97  
We have developed algorithms for automated video object segmentation and tracking and use real-time video editing techniques while responding to user queries.  ...  In this paper, we propose a novel, real-time, interactive system on the Web, based on the visual paradigm, with spatio-temporal attributes playing a key role in video retrieval.  ...  For example a shot of a person (the person is the "object" here) walking would be segmented into a collection of adjoining regions differing in criteria such as shape, color and texture, but all the regions  ... 
doi:10.1145/266180.266382 dblp:conf/mm/ChangCMSZ97 fatcat:54gdz3aetjfy3jsxl6als27joi
« Previous Showing results 1 — 15 out of 10,852 results