Advances in Multimedia Information Processing – PCM 2012: by Chao Wang, Yunhong Wang, Zhaoxiang Zhang (auth.), Weisi Lin,

By Chao Wang, Yunhong Wang, Zhaoxiang Zhang (auth.), Weisi Lin, Dong Xu, Anthony Ho, Jianxin Wu, Ying He, Jianfei Cai, Mohan Kankanhalli, Ming-Ting Sun (eds.)

This publication constitutes the court cases of the thirteenth Pacific Rim convention on Multimedia, held in Singapore in the course of December 4-6, 2012. The fifty nine revised complete papers provided have been conscientiously reviewed and chosen from 106 submissions for the most convention and are followed through 23 shows of four unique periods. The papers are geared up in topical sections on multimedia content material research, snapshot and video processing, video coding and multimedia info processing, image/video processing and research, video coding and multimedia approach, complicated photo and video coding, move media studying with structural priors, in addition to effective multimedia research and utilization.

Show description

Read or Download Advances in Multimedia Information Processing – PCM 2012: 13th Pacific-Rim Conference on Multimedia, Singapore, December 4-6, 2012. Proceedings PDF

Best nonfiction_7 books

Beyond Born-Oppenheimer : conical intersections and electronic nonadiabatic coupling terms

INTRODUCING a strong method of constructing trustworthy QUANTUM MECHANICAL remedies of a big number of procedures IN MOLECULAR platforms. The Born-Oppenheimer approximation has been primary to calculation in molecular spectroscopy and molecular dynamics because the early days of quantum mechanics.

Quantitative Information Fusion for Hydrological Sciences

In a swiftly evolving international of data and expertise, do you ever ask yourself how hydrology is catching up? This ebook takes the attitude of computational hydrology andenvisions one of many destiny instructions, specifically, quantitative integration of fine quality hydrologic box facts with geologic, hydrologic, chemical, atmospheric, and organic info to symbolize and are expecting normal structures in hydrological sciences.

Advances in Computational Intelligence and Learning: Methods and Applications

Advances in Computational Intelligence and studying: equipment and purposes provides new advancements and purposes within the quarter of Computational Intelligence, which basically describes equipment and ways that mimic biologically clever habit for you to resolve difficulties which were tough to unravel via classical arithmetic.

Additional info for Advances in Multimedia Information Processing – PCM 2012: 13th Pacific-Rim Conference on Multimedia, Singapore, December 4-6, 2012. Proceedings

Example text

IEEE Trans. Pattern Anal. Mach. Intell. 31(12), 2143–2157 (2009) 6. : Semi-supervised hashing for large scale search. IEEE Transactions on Pattern Analysis and Machine Intelligence (2012) 7. : Spectral hashing. In: NIPS, pp. 1753–1760 (2008) 8. : Hashing with graphs. , Scheffer, T. ) Proceedings of the 28th International Conference on Machine Learning, ICML 2011. ACM, New York (2011) 9. : Semantic hashing. Int. J. Approx. Reasoning 50(7), 969–978 (2009) 10. : Spherical hashing. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, CVPR (2012) 11.

Meanwhile, the evaluations show highly competitive performance of CGE as well (see Sect. 4). Given the K-dimensional embedded Hamming space H = (h1 , . . , hn ) ∈ IRK×n , the optimization formulation can be defined as below. max Q = H subject to: Balance constraint: Independence constraint: i,j wij K k=1 hk (xi ) − hk (xj ) hk (xi ) ∈ {−1, +1}, H·e = 0, 1 T n H·H = I. 2 + σ2 (2) Hashing with Cauchy Graph 25 Equation (2) is quite different from Spectral Hashing [7] algorithm that is one of the most popular unsupervised hashing algorithms, as (2) places strong emphasis on local topology structure information.

Precision outcome for the top 50 and 100 returned samples. It is clear that HCGE achieves the stronger performance among the three different datasets. Hashing with Cauchy Graph 31 Fig. 4. Top 25 retrieved neighbors of two query digits and one cat query image marked by three red squares. , 6 and 8. Note that the unrelated retrieved images in CIFAR-10 are marked by blue rectangles. 5 Future Work and Conclusion In this paper, we employ two independent steps to learn hashing functions. A natural question would be, however, could we well combine the aforementioned two steps to the one whole optimization?

Download PDF sample

Rated 4.61 of 5 – based on 31 votes