no code implementations • NAACL 2022 • Hanzhang Zhou, Kezhi Mao
In document-level event argument extraction, an argument is likely to appear multiple times in different expressions in the document.
1 code implementation • IEEE Transactions on Artificial Intelligence 2024 • Qing Xu, Keyu Wu, Min Wu, Kezhi Mao, XiaoLi Li, and Zhenghua Chen
As one of the most popular and effective methods in model compression, knowledge distillation (KD) attempts to transfer knowledge from single or multiple large-scale networks (i. e., Teachers) to a compact network (i. e., Student).
1 code implementation • 14 Jun 2024 • Zijian Feng, Hanzhang Zhou, Zixiao Zhu, Kezhi Mao
FreeCtrl hinges on the principle that the weights of different FFN vectors influence the likelihood of different tokens appearing in the output.
1 code implementation • 31 May 2024 • Hanzhang Zhou, Zijian Feng, Zixiao Zhu, Junlang Qian, Kezhi Mao
Large language models (LLMs) have demonstrated impressive capabilities in various tasks using the in-context learning (ICL) paradigm.
1 code implementation • 20 May 2024 • Zijian Feng, Hanzhang Zhou, Zixiao Zhu, Junlang Qian, Kezhi Mao
Prompts play a crucial role in guiding the responses of Large Language Models (LLMs).
1 code implementation • 22 Feb 2024 • Anqi Cheng, Zhiyuan Yang, Haiyue Zhu, Kezhi Mao
Self-supervised depth estimation has evolved into an image reconstruction task that minimizes a photometric loss.
1 code implementation • 11 Nov 2023 • Hanzhang Zhou, Junlang Qian, Zijian Feng, Hui Lu, Zixiao Zhu, Kezhi Mao
In this study, we investigate in-context learning (ICL) in document-level event argument extraction (EAE) to alleviate the dependency on large-scale labeled data for this task.
no code implementations • 2 Aug 2023 • Xinze Li, Kezhi Mao, Fanfan Lin, Zijian Feng
To address these issues, this paper proposes a novel GAN framework, the feature-aware conditional GAN (FA-GAN), for controllable category text generation.
no code implementations • 2 Aug 2023 • Xinze Li, Kezhi Mao, Fanfan Lin, Xin Zhang
Several adaptive VL strategies have been introduced with which the performance of PSO can be improved.
no code implementations • 1 Aug 2023 • Xinze Li, Xin Zhang, Fanfan Lin, Changjiang Sun, Kezhi Mao
ZVS range and efficiency are two significant performance indicators for DAB converter.
no code implementations • 1 Aug 2023 • Xinze Li, Xin Zhang, Fanfan Lin, Changjiang Sun, Kezhi Mao
However, to minimize the current stress when the DAB converter is under TPS modulation, two difficulties exist in analysis process and realization process, respectively.
1 code implementation • 7 Jul 2023 • Qing Xu, Min Wu, XiaoLi Li, Kezhi Mao, Zhenghua Chen
More specifically, a feature-domain discriminator is employed to align teacher's and student's representations for universal knowledge transfer.
no code implementations • 13 Apr 2022 • Xiyu Wang, Yuecong Xu, Kezhi Mao, Jianfei Yang
It utilizes a novel class weight calibration method to alleviate the negative transfer caused by incorrect class weights.
no code implementations • 26 Sep 2021 • Haozhi Cao, Yuecong Xu, Jianfei Yang, Kezhi Mao, Lihua Xie, Jianxiong Yin, Simon See
This paper introduces a novel self-supervised method that leverages incoherence detection for video representation learning.
no code implementations • 11 Jul 2021 • Yuecong Xu, Jianfei Yang, Haozhi Cao, Kezhi Mao, Jianxiong Yin, Simon See
Yet correlation features of the same action would differ across domains due to domain shift.
no code implementations • ICCV 2021 • Yuecong Xu, Jianfei Yang, Haozhi Cao, Qi Li, Kezhi Mao, Zhenghua Chen
For videos, such negative transfer could be triggered by both spatial and temporal features, which leads to a more challenging Partial Video Domain Adaptation (PVDA) problem.
no code implementations • 26 Aug 2020 • Haozhi Cao, Yuecong Xu, Jianfei Yang, Kezhi Mao, Jianxiong Yin, Simon See
Temporal feature extraction is an essential technique in video-based action recognition.
no code implementations • 9 Jun 2020 • Yuecong Xu, Haozhi Cao, Jianfei Yang, Kezhi Mao, Jianxiong Yin, Simon See
Empirical results prove the effectiveness and efficiency of our PNL module, which achieves state-of-the-art performance of 83. 09% on the Mini-Kinetics dataset, with decreased computation cost compared to the non-local block.
1 code implementation • 6 Jun 2020 • Yuecong Xu, Jianfei Yang, Haozhi Cao, Kezhi Mao, Jianxiong Yin, Simon See
We bridge the gap of the lack of data for this task by collecting a new dataset: the Action Recognition in the Dark (ARID) dataset.
no code implementations • 6 May 2020 • Yuecong Xu, Jianfei Yang, Kezhi Mao, Jianxiong Yin, Simon See
Temporal feature extraction is an important issue in video-based action recognition.
no code implementations • IJCNLP 2019 • Pengfei Li, Kezhi Mao, Xuefeng Yang, Qi Li
While attention mechanisms have been proven to be effective in many NLP tasks, majority of them are data-driven.
1 code implementation • 16 Dec 2016 • Rui Zhao, Ruqiang Yan, Zhenghua Chen, Kezhi Mao, Peng Wang, Robert X. Gao
Since 2006, deep learning (DL) has become a rapidly growing research direction, redefining state-of-the-art performances in a wide range of areas such as object recognition, image segmentation, speech recognition and machine translation.
no code implementations • 29 May 2015 • Xuefeng Yang, Kezhi Mao
Inspired by deep learning, the authors propose a supervised framework for learning vector representation of words to provide additional supervised fine tuning after unsupervised learning.