no code implementations • Findings (EMNLP) 2021 • MengNan Qi, Hao liu, Yuzhuo Fu, Ting Liu
With the increasing abundance of meeting transcripts, meeting summary has attracted more and more attention from researchers.
1 code implementation • 23 Mar 2024 • Jiacheng Ruan, Jingsheng Gao, Mingye Xie, Daize Dong, Suncheng Xiang, Ting Liu, Yuzhuo Fu
Adapter-Tuning (AT) method involves freezing a pre-trained model and introducing trainable adapter modules to acquire downstream knowledge, thereby calibrating the model for better adaptation to downstream tasks.
no code implementations • 4 Jan 2024 • Zeyu Li, Jingsheng Gao, Tong Yu, Suncheng Xiang, Jiacheng Ruan, Ting Liu, Yuzhuo Fu
Existing research on audio classification faces challenges in recognizing attributes of passive underwater vessel scenarios and lacks well-annotated datasets due to data privacy concerns.
1 code implementation • 13 Dec 2023 • Jingsheng Gao, Jiacheng Ruan, Suncheng Xiang, Zefang Yu, Ke Ji, Mingye Xie, Ting Liu, Yuzhuo Fu
We conduct experiments on 11 downstream vision datasets and demonstrate that our method significantly improves the performance of existing multi-modal prompt learning models in few-shot scenarios, exhibiting an average accuracy improvement of 2. 31(\%) compared to the state-of-the-art methods on 16 shots.
1 code implementation • 12 Dec 2023 • Jiacheng Ruan, Jingsheng Gao, Mingye Xie, Suncheng Xiang, Zefang Yu, Ting Liu, Yuzhuo Fu
2) They neglect the interaction between the intrinsic task-agnostic knowledge of pre-trained models and the task-specific knowledge in downstream tasks.
1 code implementation • 17 Jul 2023 • Jiacheng Ruan, Mingye Xie, Jingsheng Gao, Ting Liu, Yuzhuo Fu
Moreover, to our best knowledge, this is the first model with a parameter count limited to just 50KB.
1 code implementation • 14 Jun 2023 • Jingsheng Gao, Yixin Lian, Ziyi Zhou, Yuzhuo Fu, Baoyuan Wang
Open-domain dialogue systems have made promising progress in recent years.
1 code implementation • 19 Apr 2023 • Suncheng Xiang, Jingsheng Gao, Mengyuan Guan, Jiacheng Ruan, Chengfeng Zhou, Ting Liu, Dahong Qian, Yuzhuo Fu
In this paper, we propose a Multi-Modal Equivalent Transformer called MMET for more robust visual-semantic embedding learning on visual, textual and visual-textual tasks respectively.
Generalizable Person Re-identification Representation Learning
1 code implementation • 16 Feb 2023 • Jingsheng Gao, Zeyu Li, Suncheng Xiang, Ting Liu, Yuzhuo Fu
A huge number of multi-participant dialogues happen online every day, which leads to difficulty in understanding the nature of dialogue dynamics for both humans and machines.
1 code implementation • 3 Nov 2022 • Jiacheng Ruan, Suncheng Xiang, Mingye Xie, Ting Liu, Yuzhuo Fu
To address this challenge, we propose a light-weight model to achieve competitive performances for skin lesion segmentation at the lowest cost of parameters and computational complexity so far.
1 code implementation • 2 Nov 2022 • Suncheng Xiang, Hao Chen, Wei Ran, Zefang Yu, Ting Liu, Dahong Qian, Yuzhuo Fu
Person re-identification plays a significant role in realistic scenarios due to its various applications in public security and video surveillance.
Domain Generalization Generalizable Person Re-identification +2
1 code implementation • 25 Oct 2022 • Jiacheng Ruan, Mingye Xie, Suncheng Xiang, Ting Liu, Yuzhuo Fu
Specifically, our block performs a Fourier transform on the three axes of the input feature and assigns the external weight in the frequency domain, which is generated by our Weights Generator.
1 code implementation • 11 Oct 2021 • Suncheng Xiang, Jingsheng Gao, Zirui Zhang, Mengyuan Guan, Binjie Yan, Ting Liu, Dahong Qian, Yuzhuo Fu
Pretraining is a dominant paradigm in computer vision.
1 code implementation • 22 Sep 2021 • Suncheng Xiang, Guanjie You, Mengyuan Guan, Hao Chen, Binjie Yan, Ting Liu, Yuzhuo Fu
Moreover, aiming to fully exploit the potential of FineGPR and promote the efficient training from millions of synthetic data, we propose an attribute analysis pipeline called AOST, which dynamically learns attribute distribution in real domain, then eliminates the gap between synthetic and real-world data and thus is freely deployed to new scenarios.
1 code implementation • 6 Apr 2021 • Suncheng Xiang, Yuzhuo Fu, Mengyuan Guan, Ting Liu
Employing clustering strategy to assign unlabeled target images with pseudo labels has become a trend for person re-identification (re-ID) algorithms in domain adaptation.
no code implementations • 15 Oct 2020 • Suncheng Xiang, Yuzhuo Fu, Guanjie You, Ting Liu
Person re-identification (re-ID) plays an important role in applications such as public security and video surveillance.
no code implementations • 12 Jun 2020 • Suncheng Xiang, Yuzhuo Fu, Guanjie You, Ting Liu
To address this problem, firstly, we develop a large-scale synthetic data engine, the salient characteristic of this engine is controllable.