1 code implementation • 4 Mar 2024 • Xinyue Li, Aous Naman, David Taubman
The proposed approach involves two steps, a high-to-low step followed by a low-to-high step.
no code implementations • 29 Feb 2024 • Wentao Shi, Xiangnan He, Yang Zhang, Chongming Gao, Xinyue Li, Jizhi Zhang, Qifan Wang, Fuli Feng
To achieve this, we propose a Bi-level Learnable LLM Planner framework, which combines macro-learning and micro-learning through a hierarchical mechanism.
no code implementations • 29 Feb 2024 • Xinyue Li, Aous Naman, David Taubman
Moreover, we demonstrate that employing more learned lifting steps and more layers in each learned lifting operator do not contribute strongly to the compression performance.
no code implementations • 6 Oct 2023 • Patrick Tinsley, Sandip Purnapatra, Mahsa Mitcheff, Aidan Boyd, Colton Crum, Kevin Bowyer, Patrick Flynn, Stephanie Schuckers, Adam Czajka, Meiling Fang, Naser Damer, Xingyu Liu, Caiyong Wang, Xianyun Sun, Zhaohua Chang, Xinyue Li, Guangzhe Zhao, Juan Tapia, Christoph Busch, Carlos Aravena, Daniel Schulz
New elements in this fifth competition include (1) GAN-generated iris images as a category of presentation attack instruments (PAI), and (2) an evaluation of human accuracy at detecting PAI as a reference benchmark.
no code implementations • 28 Aug 2023 • Collin Sakal, Tingyou Li, Juan Li, Xinyue Li
Timely implementation of interventions to slow cognitive decline among older adults requires accurate monitoring to detect changes in cognitive function.
no code implementations • 5 Aug 2023 • Xinyue Li, Zhenpeng Chen, Jie M. Zhang, Federica Sarro, Ying Zhang, Xuanzhe Liu
This paper analyzes fairness in automated pedestrian detection, a crucial but under-explored issue in autonomous driving systems.
1 code implementation • 8 Jul 2023 • Yuxuan Song, Xinyue Li, Lin Qi
In order to better explore the advantages of the two encoders, we design a cross-attention-based Feature Grafting Module to graft features extracted from Transformer branch into CNN branch, after which the features are aggregated in the Feature Fusion Module.
no code implementations • 24 May 2023 • Rishi Sonthalia, Xinyue Li, Bochao Gu
For larger values of $\mu$, we observe that the curve for the norm of the estimator has a peak but that this no longer translates to a peak in the generalization error.
no code implementations • 6 Apr 2023 • Xinyue Li, Jian Wang, Wei Song, Yanling Du, Zhixiang Liu
The mainstream researche in deep metric learning can be divided into two genres: proxy-based and pair-based methods.
1 code implementation • 3 Oct 2022 • Guangyi Chen, Weiran Yao, Xiangchen Song, Xinyue Li, Yongming Rao, Kun Zhang
To solve this problem, we propose to apply optimal transport to match the vision and text modalities.