Amin Ansari

Zanjan University of Medical Sciences

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Trends

Author Order

Document Type

Co-Authors

Fatih Porikli

Qualcomm (United Kingdom)

Yunxiao Shi

Shenyang University of Technology

Maedeh Mostanadi

Zanjan University of Medical Sciences

Hong Cai

Hong Kong Polytechnic University

M Adib Hajbagari

Seyyed Solmaz Taheri

Shahid Beheshti University of Medical Sciences

Nikoo Ghasemi

Zanjan University of Medical Sciences

Mahya Farsadeghi

Zanjan University of Medical Sciences

Sona Rafieyan

Zanjan University of Medical Sciences

Hong Cai

Agency for Science, Technology and Research

Cooperative Institutions

Zanjan University of Medical Sciences

Qualcomm (United Kingdom)

Hong Kong Polytechnic University

Qualcomm (United States)

Air Force General Hospital PLA

University of California, Santa Barbara

PLA Academy of Military Science

Space Engineering University

Nankai University

Chongqing University of Posts and Telecommunications

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Field

EGA-Depth: Efficient Guided Attention for Self-Supervised Multi-Camera Depth Estimation

2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (2023)

Yunxiao Shi Hong Cai Amin Ansari Fatih Porikli

The ubiquitous multi-camera setup on modern autonomous vehicles provides an opportunity to construct surround-view depth. Existing methods, however, either perform independent monocular depth estimations on each camera or rely on computationally heavy self attention mechanisms. In this paper, we propose a novel guided attention architecture, EGA-Depth, which can improve both the efficiency and accuracy of self-supervised multi-camera depth estimation. More specifically, for each camera, we use its perspective view as the query to cross-reference its neighboring views to derive informative features for this camera view. This allows the model to perform attention only across views with considerable overlaps and avoid the costly computations of standard self-attention. Given its efficiency, EGA-Depth enables us to exploit higher-resolution visual features, leading to improved accuracy. Furthermore, EGA-Depth can incorporate more frames from previous time steps as it scales linearly w.r.t. the number of views and frames. Extensive experiments on two challenging autonomous driving benchmarks nuScenes and DDAD demonstrate the efficacy of our proposed EGA-Depth and show that it achieves the new state-of-the-art in self-supervised multi-camera depth estimation.

Monocular

10.1109/cvprw59228.2023.00017

Cite

Citations (10)

NURSES OPINIONS AND PRACTICE IN MOUTH CARE FOR ICU PATIENTS UNDER MECHANICAL VENTILATION

Faṣlnāmah-i dānishkadah-i parastāri va māmāyī-i Urūmiyyah/Faṣlnāmah-i dānishkadah-i parastāri va māmāyī-i Urūmiyyah. (2012)

M Adib Hajbagari Amin Ansari

Source

Cite

Citations (4)

EGA-Depth: Efficient Guided Attention for Self-Supervised Multi-Camera Depth Estimation

arXiv (Cornell University) (2023)

Yunxiao Shi Hong Cai Amin Ansari Fatih Porikli

Monocular

10.48550/arxiv.2304.03369

Cite

Citations (0)

Oral Health Literacy and Its Correlation with Socioeconomic Status in an Iranian Population

Journal of Research in Dental and Maxillofacial Sciences (2024)

Seyyed Solmaz Taheri Mahya Farsadeghi Maedeh Mostanadi Amin Ansari Nikoo Ghasemi

Background and Aim:This study aimed to assess the oral health literacy (OHL) and its correlation with socioeconomic status (SES) in residents of Zanjan city, Iran by introducing a new questionnaire for this purpose.Materials and Methods: This cross-sectional study was conducted on 1,513 individuals residing in Zanjan city, Iran, in 2019.The demographic information, OHL, and SES of the participants were evaluated by using relevant questionnaires.The reliability of the questionnaire designed for assessment of OHL was evaluated by calculation of the intra-class correlation coefficient and Cronbach's alpha, while its validity was assessed by calculation of content validity index and content validity ratio.Data were analyzed by the Chi-square test and one-way ANOVA (alpha=0.05).Results: Data of 1,513 individuals with a mean age of 33.3±9.93 years were analyzed, including 59.6% males and 40.4% females.The Cronbach's alpha and intra-class correlation coefficient were found to be 0.71 and 0.81, respectively.OHL was inadequate in 29.1%, marginal in 37.4%, and adequate in 33.4% of the participants.The mean level of OHL of females was higher than males.Those with low SES had low OHL and this correlation was statistically significant (P<0.001). Conclusion:The OHL of the study population was moderate.Since there is no specific practical method for enhancement of OHL of the general population, educational OHL programs are recommended with particular attention to older individuals and those with lower SES.

Health Literacy

10.61186/jrdms.9.1.49

Cite

Citations (0)