Abstract | ||
---|---|---|
Attributes now play a vital role for characterizing a crowded scene. Compared to low-level visual features, processing informed by attributes can capture rich semantic information. However, to effectively assign attributes to a crowded scene still remains a challenging task. In this letter, inspired by a recently proposed zero-shot learning framework, a novel attribute assignment method that maps ... |
Year | DOI | Venue |
---|---|---|
2016 | 10.1109/LSP.2016.2592689 | IEEE Signal Processing Letters |
Keywords | Field | DocType |
Feature extraction,Training,World Wide Web,Motion segmentation,Visualization,Semantics,Image analysis | Data mining,Pattern recognition,Fisher vector,Convolutional neural network,Computer science,Feature extraction,Semantic information,Exploit,Artificial intelligence,Optical flow,Encoding (memory) | Journal |
Volume | Issue | ISSN |
23 | 10 | 1070-9908 |
Citations | PageRank | References |
0 | 0.34 | 16 |
Authors | ||
6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Chunhua Deng | 1 | 0 | 1.35 |
Zhiguo Cao | 2 | 314 | 44.17 |
Yang Xiao | 3 | 237 | 26.58 |
Hao Lu | 4 | 140 | 20.86 |
Ke Xian | 5 | 55 | 8.99 |
Yin Chen | 6 | 16 | 7.04 |