Search Results - "Hung, Dao Huu"
-
1
Logovit: Local-Global Vision Transformer for Object Re-Identification
Published in ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (04-06-2023)“…Object re-identification (ReID) is prone to errors under variations in scale, illumination, complex background, and object occlusion scenarios. To overcome…”
Get full text
Conference Proceeding -
2
Human Density Estimation by Exploiting Deep Spatial Contextual Information
Published in 2019 International Conference on Image and Vision Computing New Zealand (IVCNZ) (01-12-2019)“…We propose in this paper a deep learning method for human density estimation, targeted to sparse density scenarios. We divide the image into a grid of cells…”
Get full text
Conference Proceeding -
3
An efficient approach for real-time abnormal human behavior recognition on surveillance cameras
Published in 2023 IEEE 17th International Conference on Automatic Face and Gesture Recognition (FG) (05-01-2023)“…In recent years, abnormal human behavior recognition has become an attractive research topic of computer vision due to the rapid growth of demand to monitor…”
Get full text
Conference Proceeding -
4
An omnidirectional vision system for bus safety surveillance
Published in 2015 12th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS) (01-08-2015)“…Sudden brake seems to be unavoidable in driving practice to prevent from accidence. The sudden brake may often cause falling risks to on-board passengers in…”
Get full text
Conference Proceeding -
5
Detecting Fall Incidents of the Elderly Based on Human-Ground Contact Areas
Published in 2013 2nd IAPR Asian Conference on Pattern Recognition (01-11-2013)“…People always make a little contact with the ground during usual activities mainly by feet but often lie completely on the ground after accidental falls. Thus,…”
Get full text
Conference Proceeding -
6
Sampling Foundational Transformer: A Theoretical Perspective
Published 11-08-2024“…The versatility of self-attention mechanism earned transformers great success in almost all data modalities, with limitations on the quadratic complexity and…”
Get full text
Journal Article -
7
SAMSA: Efficient Transformer for Many Data Modalities
Published 09-08-2024“…The versatility of self-attention mechanism earned transformers great success in almost all data modalities, with limitations on the quadratic complexity and…”
Get full text
Journal Article