Abstract | ||
---|---|---|
This paper augments the Bag-of-Word scheme in several respects: we incorporate a category label into the clustering process, build classifier-tailored codebooks, and weight codewords according to their probability to occur. A size-adaptive feature clustering algorithm is also proposed as an alternative to k-means. Experiments on the PASCAL VOC 2007 challenge validate the approach for classical hard-assignment as well as VLAD encoding. |
Year | DOI | Venue |
---|---|---|
2016 | 10.1007/978-3-319-48680-2_35 | ADVANCED CONCEPTS FOR INTELLIGENT VISION SYSTEMS, ACIVS 2016 |
Field | DocType | Volume |
Computer vision,Digital video,Fisher vector,Pattern recognition,Computer science,Image processing,Vector quantization,Artificial intelligence,Cluster analysis,Encoding (memory) | Conference | 10016 |
ISSN | Citations | PageRank |
0302-9743 | 0 | 0.34 |
References | Authors | |
20 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Rémi Trichet | 1 | 27 | 7.32 |
Noel E. O'Connor | 2 | 2137 | 223.20 |