Item Infomation
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Zhuangzhuang, Miao | - |
dc.contributor.author | Yong, Zhang | - |
dc.contributor.author | Yuan, Peng | - |
dc.date.accessioned | 2023-04-10T04:36:40Z | - |
dc.date.available | 2023-04-10T04:36:40Z | - |
dc.date.issued | 2023 | - |
dc.identifier.uri | https://link.springer.com/article/10.1007/s41095-022-0313-5 | - |
dc.identifier.uri | https://dlib.phenikaa-uni.edu.vn/handle/PNK/7722 | - |
dc.description | CC BY | vi |
dc.description.abstract | Crowd counting provides an important foundation for public security and urban management. Due to the existence of small targets and large density variations in crowd images, crowd counting is a challenging task. Mainstream methods usually apply convolution neural networks (CNNs) to regress a density map, which requires annotations of individual persons and counts. Weakly-supervised methods can avoid detailed labeling and only require counts as annotations of images, but existing methods fail to achieve satisfactory performance because a global perspective field and multi-level information are usually ignored. We propose a weakly-supervised method, DTCC, which effectively combines multi-level dilated convolution and transformer methods to realize end-to-end crowd counting. | vi |
dc.language.iso | en | vi |
dc.publisher | Springer | vi |
dc.subject | Weakly-supervised methods | vi |
dc.subject | DTCC | vi |
dc.title | DTCC: Multi-level dilated convolution with transformer for weakly-supervised crowd counting | vi |
dc.type | Book | vi |
Appears in Collections | ||
OER - Công nghệ thông tin |
Files in This Item: