Design of a foveated imaging system based on liquid crystal microlens array

Xie, Xingwang; Dai, Wei; Xin, Zhaowei; Dong, Weixia; Chen, Mingce; Zhang, Xinyu; Xie, Conghua; Wang, Haiwei; Han, Xinjie

doi:10.1117/12.2506392

Cited by 2 publications

(2 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…• Soft top-𝑘 based objective computation. To make the top-𝑘 operation differentiable, we employ a smoothed approximation for it, namely SOFT [33]. Specifically, SOFT approximates the output of the top-𝑘 operation as the solution of an Entropic Optimal Transport problem, and the gradient of the SOFT operator could be efficiently computed based on the optimality conditions of the problem.…”

Section: Objective Representationmentioning

confidence: 99%

“…During training, we utilize the soft top-𝑘 technique [33] to compute them, enabling gradient updates, and we employ dynamic balancing schemes to prevent the skewed optimization of the different aspects. We demonstrate our method on Deep Interest Network (DIN) [44] and conduct experiments on two real-world datasets, validating its capability to consistently achieve favorable outcomes across all aspects of the platform objectives.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

LabelCraft: Empowering Short Video Recommendations with Automated Label Crafting

Bai,

Zhang,

et al. 2024

Proceedings of the 17th ACM International Conference on Web Search and Data Mining

View full text Add to dashboard Cite

Short video recommendations often face limitations due to the quality of user feedback, which may not accurately depict user interests. To tackle this challenge, a new task has emerged: generating more dependable labels from original feedback. Existing label generation methods rely on manual rules, demanding substantial human effort and potentially misaligning with the desired objectives of the platform. To transcend these constraints, we introduce LabelCraft, a novel automated label generation method explicitly optimizing pivotal operational metrics for platform success. By formulating label generation as a higher-level optimization problem above recommender model optimization, LabelCraft introduces a trainable labeling model for automatic label mechanism modeling. Through meta-learning techniques, LabelCraft effectively addresses the bilevel optimization hurdle posed by the recommender and labeling models, enabling the automatic acquisition of intricate label generation mechanisms. Extensive experiments on real-world datasets corroborate LabelCraft's excellence across varied operational metrics, encompassing usage time, user engagement, and retention. Codes are available at https://github.com/baiyimeng/LabelCraft.

show abstract

Section: Objective Representationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%