no code implementations • 26 Apr 2024 • Hengfei Wang, Zhongqun Zhang, Yihua Cheng, Hyung Jin Chang
Our work first introduces a text-of-gaze dataset containing over 90k text descriptions spanning a dense distribution of gaze and head poses.
no code implementations • 23 Mar 2024 • Yihua Cheng, Yaning Zhu, Zongji Wang, Hongquan Hao, Yongwei Liu, Shiqing Cheng, Xi Wang, Hyung Jin Chang
GazeDPTR shows state-of-the-art performance on the IVGaze dataset.
no code implementations • 23 Jan 2024 • Hanchen Li, YuHan Liu, Yihua Cheng, Siddhant Ray, Kuntai Du, Junchen Jiang
To render each generated token in real time, the LLM server generates response tokens one by one and streams each generated token (or group of a few tokens) through the network to the user right after it is generated, which we refer to as LLM token streaming.
1 code implementation • 9 Nov 2023 • Yuqi Hou, Zhongqun Zhang, Nora Horanyi, Jaewon Moon, Yihua Cheng, Hyung Jin Chang
We then use the identity information to enhance scene images and propose a gaze candidate estimation network.
1 code implementation • 11 Oct 2023 • YuHan Liu, Hanchen Li, Yihua Cheng, Siddhant Ray, YuYang Huang, Qizheng Zhang, Kuntai Du, Jiayi Yao, Shan Lu, Ganesh Ananthanarayanan, Michael Maire, Henry Hoffmann, Ari Holtzman, Junchen Jiang
Compared to the recent systems that reuse the KV cache, CacheGen reduces the KV cache size by 3. 5-4. 3x and the total delay in fetching and processing contexts by 3. 2-3. 7x while having negligible impact on the LLM response quality in accuracy or perplexity.
1 code implementation • ICCV 2023 • Yihua Cheng, Feng Lu
We further propose a dual-view transformer to estimate gaze from dual-view features.
no code implementations • 1 Aug 2023 • Hengfei Wang, Zhongqun Zhang, Yihua Cheng, Hyung Jin Chang
In this paper, we aim to learn a face NeRF model that is sensitive to eye movements from multi-view images.
no code implementations • 21 May 2023 • Yihua Cheng, Ziyi Zhang, Hanchen Li, Anton Arapin, Yue Zhang, Qizheng Zhang, YuHan Liu, Xu Zhang, Francis Y. Yan, Amrita Mazumdar, Nick Feamster, Junchen Jiang
In real-time video communication, retransmitting lost packets over high-latency networks is not viable due to strict latency requirements.
1 code implementation • 30 May 2021 • Yihua Cheng, Feng Lu
In this paper, we employ transformers and assess their effectiveness for gaze estimation.
7 code implementations • 26 Apr 2021 • Yihua Cheng, Haofei Wang, Yiwei Bao, Feng Lu
This paper serves not only as a reference to develop deep learning-based gaze estimation methods, but also a guideline for future gaze estimation research.
1 code implementation • 24 Mar 2021 • Yihua Cheng, Yiwei Bao, Feng Lu
Different from common domain adaption methods, we propose a domain generalization method to improve the cross-domain performance without touching target samples.
no code implementations • 20 Mar 2021 • Yiwei Bao, Yihua Cheng, Yunfei Liu, Feng Lu
Meanwhile, we also propose Adaptive Group Normalization to recalibrate eye features with the guidance of facial feature.
no code implementations • 1 Jan 2020 • Yihua Cheng, Shiyao Huang, Fei Wang, Chen Qian, Feng Lu
Human gaze is essential for various appealing applications.
no code implementations • ECCV 2018 • Yihua Cheng, Feng Lu, Xucong Zhang
Inspired by this, we design the multi-stream ARE-Net; one asymmetric regression network (AR-Net) predicts 3D gaze directions for both eyes with a novel asymmetric strategy, and the evaluation network (E-Net) adaptively adjusts the strategy by evaluating the two eyes in terms of their performance during optimization.