no code implementations • COLING 2022 • Jie zhou, Shenpo Dong, Hongkui Tu, Xiaodong Wang, Yong Dou
In this paper, we propose RSGT: Relational Structure Guided Temporal Relation Extraction to extract the relational structure features that can fit for both inter-sentence and intra-sentence relations.
Ranked #1 on Temporal Relation Classification on MATRES
Natural Language Understanding Temporal Relation Classification
no code implementations • COLING 2022 • Biao Hu, Zhen Huang, Minghao Hu, Ziwen Zhang, Yong Dou
Recently, Transformer has achieved great success in Chinese named entity recognition (NER) owing to its good parallelism and ability to model long-range dependencies, which utilizes self-attention to encode context.
Chinese Named Entity Recognition named-entity-recognition +2
no code implementations • 10 Apr 2023 • Zhongwu Chen, Chengjin Xu, Fenglong Su, Zhen Huang, Yong Dou
In the inductive setting where test TKGs contain emerging entities, the latest methods are based on symbolic rules or pre-trained language models (PLMs).
no code implementations • 29 Jan 2023 • Peng Qiao, Sidun Liu, Tao Sun, Ke Yang, Yong Dou
It provides a promising way to introduce the Transformer in low-level vision tasks.
1 code implementation • COLING 2022 • Hao Wang, Yangguang Li, Zhen Huang, Yong Dou
Then we integrate the multi-view contextual information to encode the evidence sentences to handle the task.
1 code implementation • 27 Aug 2022 • Sidun Liu, Peng Qiao, Yong Dou
Therefore, we propose to make the network learn the distribution of feasible solutions, and design based on this consideration a novel multi-head output architecture and corresponding loss function for distribution learning.
Ranked #2 on Image Deblurring on GoPro
1 code implementation • 16 Jan 2022 • Hao Wang, Yangguang Li, Zhen Huang, Yong Dou, Lingpeng Kong, Jing Shao
To alleviate feature suppression, we propose contrastive learning for unsupervised sentence embedding with soft negative samples (SNCSE).
no code implementations • COLING 2020 • Hao Wang, Zhen Huang, Yong Dou, Yu Hong
Recent research mainly models the task as a sequence tagging problem and deal with all the argumentation components at word level.
no code implementations • 29 May 2020 • Hengyue Pan, Xin Niu, Rongchun Li, Siqi Shen, Yong Dou
Instead, we propose a novel method to encode all background objects in each image by using one fixed-size vector (i. e., FBE vector).
1 code implementation • ICCV 2019 • Ke Yang, Dongsheng Li, Yong Dou
It is challenging for weakly supervised object detection network to precisely predict the positions of the objects, since there are no instance-level category annotations.
no code implementations • 23 Jul 2019 • Tao Sun, Dongsheng Li, Zhe Quan, Hao Jiang, Shengguo Li, Yong Dou
In this paper, we answer a question: can the nonconvex heavy-ball algorithms with random initialization avoid saddle points?
no code implementations • 5 Jun 2019 • Yuntao Liu, Yong Dou, Ruochun Jin, Rongchun Li
In order to optimize models and meet the requirement mentioned above, we propose a method that replaces the fully-connected layers of convolution neural network models with a tree classifier.
no code implementations • 4 Jun 2019 • Yuntao Liu, Yong Dou, Ruochun Jin, Peng Qiao
In image classification, Convolutional Neural Network(CNN) models have achieved high performance with the rapid development in deep learning.
no code implementations • 26 Feb 2019 • Ke Yang, Peng Qiao, Dongsheng Li, Yong Dou
Focusing on discriminate spatiotemporal feature learning, we propose Information Fused Temporal Transformation Network (IF-TTN) for action recognition on top of popular Temporal Segment Network (TSN) framework.
no code implementations • 14 Feb 2019 • Ke Yang, Xiaolong Shen, Peng Qiao, Shijie Li, Dongsheng Li, Yong Dou
The proposed FSN can make dense predictions at frame-level for a video clip using both spatial and temporal context information.
no code implementations • 16 Nov 2018 • Hengyue Pan, Hui Jiang, Xin Niu, Yong Dou
Most of previous methods mainly consider to drop features from input data and hidden layers, such as Dropout, Cutout and DropBlocks.
no code implementations • 17 Jul 2018 • Peng Qiao, Yong Dou, Yunjin Chen, Wensen Feng
On the contrary, the regularization term learned via discriminative approaches are usually trained for a specific image restoration problem, and fail in the problem for which it is not trained.
no code implementations • 10 Aug 2017 • Ke Yang, Peng Qiao, Dongsheng Li, Shaohe Lv, Yong Dou
A newly proposed work exploits Convolutional-Deconvolutional-Convolutional (CDC) filters to upsample the predictions of 3D ConvNets, making it possible to perform per-frame action predictions and achieving promising performance in terms of temporal action localization.
no code implementations • 24 Feb 2017 • Peng Qiao, Yong Dou, Wensen Feng, Yunjin Chen
In order to preserve the expected property that end-to-end training is available, we exploit the NSS prior by a set of non-local filters, and derive our proposed trainable non-local reaction diffusion (TNLRD) model for image denoising.
no code implementations • 16 Jul 2016 • Ke Yang, Dongsheng Li, Yong Dou, Shaohe Lv, Qiang Wang
Object detection is an import task of computer vision. A variety of methods have been proposed, but methods using the weak labels still do not have a satisfactory result. In this paper, we propose a new framework that using the weakly supervised method's output as the pseudo-strong labels to train a strongly supervised model. One weakly supervised method is treated as black-box to generate class-specific bounding boxes on train dataset. A de-noise method is then applied to the noisy bounding boxes. Then the de-noised pseudo-strong labels are used to train a strongly object detection network. The whole framework is still weakly supervised because the entire process only uses the image-level labels. The experiment results on PASCAL VOC 2007 prove the validity of our framework, and we get result 43. 4% on mean average precision compared to 39. 5% of the previous best result and 34. 5% of the initial method, respectively. And this frame work is simple and distinct, and is promising to be applied to other method easily.
no code implementations • 18 May 2016 • Ke Yang, Yong Dou, Shaohe Lv, Fei Zhang, Qi Lv
This study focuses on human recognition with gait feature obtained by Kinect and shows that gait feature can effectively distinguish from different human beings through a novel representation -- relative distance-based gait features.