Atjaunināt sīkdatņu piekrišanu

E-grāmata: Human Action Analysis with Randomized Trees

  • Formāts - PDF+DRM
  • Cena: 53,52 €*
  • * ši ir gala cena, t.i., netiek piemērotas nekādas papildus atlaides
  • Ielikt grozā
  • Pievienot vēlmju sarakstam
  • Šī e-grāmata paredzēta tikai personīgai lietošanai. E-grāmatas nav iespējams atgriezt un nauda par iegādātajām e-grāmatām netiek atmaksāta.

DRM restrictions

  • Kopēšana (kopēt/ievietot):

    nav atļauts

  • Drukāšana:

    nav atļauts

  • Lietošana:

    Digitālo tiesību pārvaldība (Digital Rights Management (DRM))
    Izdevējs ir piegādājis šo grāmatu šifrētā veidā, kas nozīmē, ka jums ir jāinstalē bezmaksas programmatūra, lai to atbloķētu un lasītu. Lai lasītu šo e-grāmatu, jums ir jāizveido Adobe ID. Vairāk informācijas šeit. E-grāmatu var lasīt un lejupielādēt līdz 6 ierīcēm (vienam lietotājam ar vienu un to pašu Adobe ID).

    Nepieciešamā programmatūra
    Lai lasītu šo e-grāmatu mobilajā ierīcē (tālrunī vai planšetdatorā), jums būs jāinstalē šī bezmaksas lietotne: PocketBook Reader (iOS / Android)

    Lai lejupielādētu un lasītu šo e-grāmatu datorā vai Mac datorā, jums ir nepieciešamid Adobe Digital Editions (šī ir bezmaksas lietotne, kas īpaši izstrādāta e-grāmatām. Tā nav tas pats, kas Adobe Reader, kas, iespējams, jau ir jūsu datorā.)

    Jūs nevarat lasīt šo e-grāmatu, izmantojot Amazon Kindle.

This book will provide a comprehensive overview on human action analysis with randomized trees. It will cover both the supervised random trees and the unsupervised random trees. When there are sufficient amount of labeled data available, supervised random trees provides a fast method for space-time interest point matching. When labeled data is minimal as in the case of example-based action search, unsupervised random trees is used to leverage the unlabelled data. We describe how the randomized trees can be used for action classification, action detection, action search, and action prediction. We will also describe techniques for space-time action localization including branch-and-bound sub-volume search and propagative Hough voting.
1 Introduction to Human Action Analysis
1(8)
1.1 Overview
1(2)
1.2 Action Recognition
3(1)
1.3 Action Detection
3(1)
1.4 Action Search
4(1)
1.5 Action Prediction
5(1)
1.6 Tree-Based Approaches
5(1)
1.7 Outline of the Book
6(3)
References
7(2)
2 Supervised Trees for Human Action Recognition and Detection
9(20)
2.1 Introduction
9(2)
2.2 Multiclass Action Recognition
11(4)
2.2.1 Mutual Information-Based Classification
11(1)
2.2.2 Random Forest-Based Voting
12(3)
2.3 Action Detection and Localization
15(6)
2.3.1 Spatial Down-Sampling
16(3)
2.3.2 Top-K Search Algorithm
19(2)
2.4 Experiments
21(5)
2.4.1 Action Classification
21(1)
2.4.2 Action Detection
22(3)
2.4.3 Computational Cost
25(1)
2.5 Summary of this
Chapter
26(3)
References
27(2)
3 Unsupervised Trees for Human Action Search
29(28)
3.1 Introduction
29(3)
3.2 Video Representation and Randomized Visual Vocabularies
32(2)
3.3 Action Matching Using Randomized Visual Vocabularies
34(2)
3.4 Efficient Action Search
36(5)
3.4.1 Coarse-to Hierarchical Subvolume Search Scheme
36(2)
3.4.2 Refinement with Hough Voting
38(1)
3.4.3 Interactive Search
39(1)
3.4.4 Computational Complexity
40(1)
3.5 Experimental Results
41(13)
3.5.1 Action Classification on KTH
42(1)
3.5.2 Action Detection on MSR II
42(2)
3.5.3 Action Retrieval on MSR II
44(2)
3.5.4 Action Retrieval on CMU Database
46(2)
3.5.5 Action Retrieval on Youtube Video
48(1)
3.5.6 Action Retrieval on UCF Sports Database
48(1)
3.5.7 Action Retrieval on Large-Scale Database
49(1)
3.5.8 Implementation Issues
50(1)
3.5.9 Computational Cost
51(3)
3.6 Summary of this
Chapter
54(3)
References
55(2)
4 Propagative Hough Voting to Leverage Contextual Information
57(16)
4.1 Introduction
57(2)
4.2 Activity Recognition by Detection
59(2)
4.3 Propagative Interest Point Matching
61(2)
4.3.1 Random Projection Trees
61(1)
4.3.2 Theoretical Justification
62(1)
4.4 Scale Determination
63(1)
4.5 Experiments
64(7)
4.5.1 RPT on the Testing Data
65(2)
4.5.2 RPT on the Training Data
67(3)
4.5.3 Computational Complexity
70(1)
4.6 Summary of this
Chapter
71(2)
References
71(2)
5 Human Action Prediction with Multiclass Balanced Random Forest
73(10)
5.1 Introduction
73(1)
5.2 Problem Formulation
74(2)
5.3 Matching and Predicting
76(2)
5.4 Experiments
78(2)
5.5 Summary of this
Chapter
80(3)
References
81(2)
6 Conclusion
83