1 code implementation • Findings (EMNLP) 2021 • Longyin Zhang, Xin Tan, Fang Kong, Guodong Zhou
Discourse analysis has long been known to be fundamental in natural language processing.
1 code implementation • EMNLP 2021 • Xin Tan, Longyin Zhang, Guodong Zhou
Natural language generation (NLG) tasks on pro-drop languages are known to suffer from zero pronoun (ZP) problems, and the problems remain challenging due to the scarcity of ZP-annotated NLG corpora.
2 code implementations • 8 Apr 2024 • Xiaofan Li, Zhizhong Zhang, Xin Tan, Chengwei Chen, Yanyun Qu, Yuan Xie, Lizhuang Ma
The vision-language model has brought great improvement to few-shot industrial anomaly detection, which usually needs to design of hundreds of prompts through prompt engineering.
no code implementations • 12 Mar 2024 • Qibing Ren, Chang Gao, Jing Shao, Junchi Yan, Xin Tan, Yu Qiao, Wai Lam, Lizhuang Ma
The rapid advancement of Large Language Models (LLMs) has brought about remarkable generative capabilities but also raised concerns about their potential misuse.
1 code implementation • 17 Jan 2024 • Hexiang Wang, Fengqi Liu, Qianyu Zhou, Ran Yi, Xin Tan, Lizhuang Ma
To address this issue, we propose to model motion from the source image to the driving frame in highly-expressive diffeomorphism spaces.
no code implementations • 13 Dec 2023 • Yujun Chen, Xin Tan, Zhizhong Zhang, Yanyun Qu, Yuan Xie
Second, in the Image Branch, we propose the Instance Position-scale Learning (IPSL) Module to learn and fuse the information of instance position and scale, which is from a 2D pre-trained detector and a type of latent label obtained from 3D to 2D projection.
no code implementations • 10 Dec 2023 • Xin Tan, Bowei Zou, Ai Ti Aw
Universal fact-checking systems for real-world claims face significant challenges in gathering valid and sufficient real-time evidence and making reasoned decisions.
1 code implementation • 4 Dec 2023 • Qihang Ma, Xin Tan, Yanyun Qu, Lizhuang Ma, Zhizhong Zhang, Yuan Xie
The autonomous driving community has shown significant interest in 3D occupancy prediction, driven by its exceptional geometric perception and general object recognition capabilities.
1 code implementation • 22 Nov 2023 • Zhen Zhao, Jingqun Tang, Chunhui Lin, Binghong Wu, Can Huang, Hao liu, Xin Tan, Zhizhong Zhang, Yuan Xie
A straightforward solution is performing model fine-tuning tailored to a specific scenario, but it is computationally intensive and requires multiple model copies for various scenarios.
1 code implementation • 20 Nov 2023 • Zhengyuan Peng, Qijian Tian, Jianqing Xu, Yizhang Jin, Xuequan Lu, Xin Tan, Yuan Xie, Lizhuang Ma
This paper explores a novel setting called Generalized Category Discovery in Semantic Segmentation (GCDSS), aiming to segment unlabeled images given prior knowledge from a labeled set of base classes.
1 code implementation • CVPR 2023 • Yuhao Chen, Xin Tan, Borui Zhao, Zhaowei Chen, RenJie Song, Jiajun Liang, Xuequan Lu
ANL introduces the additional negative pseudo-label for all unlabeled data to leverage low-confidence examples.
no code implementations • CVPR 2023 • Zhen Zhao, Zhizhong Zhang, Xin Tan, Jun Liu, Yanyun Qu, Yuan Xie, Lizhuang Ma
In this paper, we propose a space decoupling (SD) algorithm to decouple the feature space into a pair of complementary subspaces, i. e., the stability space I, and the plasticity space R. I is established by conducting space intersection between the historic and current feature space, and thus I contains more task-shared bases.
no code implementations • CVPR 2023 • Tenghao Cai, Zhizhong Zhang, Xin Tan, Yanyun Qu, Guannan Jiang, Chengjie Wang, Yuan Xie
As a result, our dynamic inference network is trained independently of baseline and provides a flexible, efficient solution to distinguish between tasks.
no code implementations • CVPR 2023 • Jiaying Lin, Xin Tan, Rynson W.H. Lau
However, detecting mirrors over dynamic scenes is still under-explored due to the lack of a high-quality dataset and an effective method for video mirror detection (VMD).
no code implementations • ICCV 2023 • Xudong Tian, Zhizhong Zhang, Xin Tan, Jun Liu, Chengjie Wang, Yanyun Qu, Guannan Jiang, Yuan Xie
Continual Learning (CL) is the constant development of complex behaviors by building upon previously acquired skills.
no code implementations • 16 Sep 2022 • Tianfang Sun, Zhizhong Zhang, Xin Tan, Yanyun Qu, Yuan Xie, Lizhuang Ma
In this paper, we propose a novel cross-modality weakly supervised method for 3D segmentation, incorporating complementary information from unlabeled images.
1 code implementation • 30 Aug 2022 • Zhifeng Xie, Sen Wang, Ke Xu, Zhizhong Zhang, Xin Tan, Yuan Xie, Lizhuang Ma
Based on this, we propose to exploit the image frequency distributions for night-time scene parsing.
no code implementations • 19 Aug 2022 • Xin Tan, Longyin Zhang, Guodong Zhou
It is well known that translations generated by an excellent document-level neural machine translation (NMT) model are consistent and coherent.
no code implementations • 8 Jun 2022 • Qiuli Wang, Xin Tan, Chen Liu
Since the pandemic of COVID-19, several deep learning methods were proposed to analyze the chest Computed Tomography (CT) for diagnosis.
1 code implementation • CVPR 2022 • Zhengyang Feng, Shaohua Guo, Xin Tan, Ke Xu, Min Wang, Lizhuang Ma
This paper presents a novel parametric curve-based method for lane detection in RGB images.
Ranked #2 on Lane Detection on LLAMAS
no code implementations • 18 Jun 2021 • Chengwei Chen, Yuan Xie, Shaohui Lin, Ruizhi Qiao, Jian Zhou, Xin Tan, Yi Zhang, Lizhuang Ma
Moreover, our model is more stable for training in a non-adversarial manner, compared to other adversarial based novelty detection methods.
2 code implementations • CVPR 2021 • Jingyu Gong, Jiachen Xu, Xin Tan, Haichuan Song, Yanyun Qu, Yuan Xie, Lizhuang Ma
Our method can significantly improve the backbones in all three datasets.
Ranked #2 on Semantic Segmentation on Semantic3D
no code implementations • 9 Mar 2021 • Bingliang Jiao, Xin Tan, Jinghao Zhou, Lu Yang, Yunlong Wang, Peng Wang
The proposed model is composed of three main branches where a self-guided dynamic branch is constructed to strengthen instance-specific features, focusing on every single image.
no code implementations • 7 Jan 2021 • Jingyu Gong, Jiachen Xu, Xin Tan, Jie zhou, Yanyun Qu, Yuan Xie, Lizhuang Ma
Boundary information plays a significant role in 2D image segmentation, while usually being ignored in 3D point cloud segmentation where ambiguous features might be generated in feature extraction, leading to misclassification in the transition area between two objects.
no code implementations • 4 Jan 2021 • Xin Tan, Longyin Zhang, Guodong Zhou
Various neural-based methods have been proposed so far for joint mention detection and coreference resolution.
no code implementations • 4 Jan 2021 • Xiaoyang Zheng, Xin Tan, Jie zhou, Lizhuang Ma, Rynson W. H. Lau
This allows the supervision to be aligned with the property of saliency detection, where the salient objects of an image could be from more than one class.
1 code implementation • 18 Apr 2020 • Zhengyang Feng, Qianyu Zhou, Qiqi Gu, Xin Tan, Guangliang Cheng, Xuequan Lu, Jianping Shi, Lizhuang Ma
Instead, leveraging inter-model disagreement between different models is a key to locate pseudo label errors.
no code implementations • 15 Mar 2020 • Xin Tan, Ke Xu, Ying Cao, Yiheng Zhang, Lizhuang Ma, Rynson W. H. Lau
Although huge progress has been made on scene analysis in recent years, most existing works assume the input images to be in day-time with good lighting conditions.
1 code implementation • 24 Jan 2020 • Jiachen Xu, Jingyu Gong, Jie zhou, Xin Tan, Yuan Xie, Lizhuang Ma
Besides local features, global information plays an essential role in semantic segmentation, while recent works usually fail to explicitly extract the meaningful global information and make full use of it.
no code implementations • IJCNLP 2019 • Xin Tan, Longyin Zhang, Deyi Xiong, Guodong Zhou
In this paper, we propose a hierarchical model to learn the global context for document-level neural machine translation (NMT).
no code implementations • ICCV 2019 • Chuchu Han, Jiacheng Ye, Yunshan Zhong, Xin Tan, Chi Zhang, Changxin Gao, Nong Sang
The state-of-the-art methods train the detector individually, and the detected bounding boxes may be sub-optimal for the following re-ID task.
no code implementations • 26 Mar 2019 • Jie Zhou, Xin Tan, Zhiwei Shao, Lizhuang Ma
We then introduce a proposal generation network to predict 3D region proposals from the generated maps and further extrude objects of interest from the whole point cloud.
1 code implementation • 5 Aug 2018 • Zhiwen Shao, Hengliang Zhu, Xin Tan, Yangyang Hao, Lizhuang Ma
Most of the existing deep learning methods only use one fully-connected layer called shape prediction layer to estimate the locations of facial landmarks.
Ranked #3 on Face Alignment on AFLW2000