Scalable visual instance mining with threads of features
We address the problem of visual instance mining, which is to extract frequently appearing visual instances automatically from a multimedia collection. We propose a scalable mining method by exploiting Thread of Features (ToF). Specifically, ToF, a compact representation that links consistent featur...
Saved in:
Main Authors: | ZHANG, Wei, LI, Hongzhi, NGO, Chong-wah, CHANG, Shih-Fu |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2014
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/6504 https://ink.library.smu.edu.sg/context/sis_research/article/7507/viewcontent/2647868.2654942.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
Similar Items
-
Searching visual instances with topology checking and context modeling
by: ZHANG, Wei, et al.
Published: (2013) -
Topological spatial verification for instance search
by: ZHANG, Wei, et al.
Published: (2015) -
Min-max hash for jaccard similarity
by: Ji, J., et al.
Published: (2014) -
Snap-and-ask: Answering multimodal question by naming visual instance
by: ZHANG, Wei, et al.
Published: (2012) -
FoodMask: Real-time food instance counting, segmentation and recognition
by: NGUYEN, Huu-Thanh, et al.
Published: (2024)