no code implementations • 16 Mar 2023 • Marwa Dhiaf, Mohamed Ali Souibgui, Kai Wang, Yuyang Liu, Yousri Kessentini, Alicia Fornés, Ahmed Cheikh Rouhou
In this paper, we explore the potential of continual self-supervised learning to alleviate the catastrophic forgetting problem in handwritten text recognition, as an example of sequence recognition.
no code implementations • 13 Mar 2023 • Jianyang Gu, Kai Wang, Hao Luo, Chen Chen, Wei Jiang, Yuqiang Fang, Shanghang Zhang, Yang You, Jian Zhao
Neural Architecture Search (NAS) has been increasingly appealing to the society of object Re-Identification (ReID), for that task-specific architectures significantly improve the retrieval performance.
1 code implementation • 12 Mar 2023 • Zangwei Zheng, Mingyuan Ma, Kai Wang, Ziheng Qin, Xiangyu Yue, Yang You
To address this challenge, we propose a novel method ZSCL to prevent zero-shot transfer degradation in the continual learning of vision-language models in both feature and parameter space.
2 code implementations • 8 Mar 2023 • Kai Wang, Jianyang Gu, Daquan Zhou, Zheng Zhu, Wei Jiang, Yang You
To the best of our knowledge, we are the first to achieve higher accuracy on complex architectures than simple ones, such as 75. 1\% with ResNet-18 and 72. 6\% with ConvNet-3 on ten images per class of CIFAR-10.
1 code implementation • 8 Mar 2023 • Ziheng Qin, Kai Wang, Zangwei Zheng, Jianyang Gu, Xiangyu Peng, Daquan Zhou, Yang You
We train the full data in the last few epochs to improve the performance of our method, which further reduces the bias of the total update.
2 code implementations • 28 Feb 2023 • Yanqing Liu, Jianyang Gu, Kai Wang, Zheng Zhu, Wei Jiang, Yang You
Although there are various matching objectives, currently the strategy for selecting original images is limited to naive random sampling.
no code implementations • 10 Feb 2023 • Deyun Zhang, Shijia Geng, Yang Zhou, Weilun Xu, Guodong Wei, Kai Wang, Jie Yu, Qiang Zhu, Yongkui Li, Yonghong Zhao, Xingyue Chen, Rui Zhang, Zhaoji Fu, Rongbo Zhou, Yanqi E, Sumei Fan, Qinghao Zhao, Chuandong Cheng, Nan Peng, Liang Zhang, Linlin Zheng, Jianjun Chu, Hongbin Xu, Chen Tan, Jian Liu, Huayue Tao, Tong Liu, Kangyin Chen, Chenyang Jiang, Xingpeng Liu, Shenda Hong
In this study, we present an AI system developed to detect and screen cardiac abnormalities (CAs) from real-world ECG images.
1 code implementation • 3 Feb 2023 • Li Fang, Qingyu Chen, Chih-Hsuan Wei, Zhiyong Lu, Kai Wang
We thoroughly evaluated the performance of Bioformer as well as existing biomedical BERT models including BioBERT and PubMedBERT on 15 benchmark datasets of four different biomedical NLP tasks: named entity recognition, relation extraction, question answering and document classification.
1 code implementation • 2 Dec 2022 • Maowei Jiang, Pengyu Zeng, Kai Wang, Huan Liu, Wenbo Chen, Haoran Liu
However, use of FT is problematic due to Gibbs phenomenon.
1 code implementation • 25 Nov 2022 • Yifan Zhang, Daquan Zhou, Bryan Hooi, Kai Wang, Jiashi Feng
The two criteria are verified to be essential for effective dataset expansion: GIF-SD obtains 13. 5\% higher model accuracy on natural image datasets than unguided expansion with SD.
no code implementations • 21 Nov 2022 • Yuhao Wang, Kai Wang, Xiaohong Liu, Tianrun Gao, Jingyue Zhang, Guangyu Wang
Automated radiology report generation aims at automatically generating a detailed description of medical images, which can greatly alleviate the workload of radiologists and provide better medical services to remote areas.
2 code implementations • 15 Nov 2022 • Xingqian Xu, Zhangyang Wang, Eric Zhang, Kai Wang, Humphrey Shi
Through our experiments, we demonstrate that VD and its underlying framework have the following merits: a) VD handles all subtasks with competitive quality; b) VD initiates novel extensions and applications such as disentanglement of style and semantic, image-text dual-guided generation, etc.
1 code implementation • NIPS 2022 • Songhua Liu, Kai Wang, Xingyi Yang, Jingwen Ye, Xinchao Wang
In this paper, we study dataset distillation (DD), from a novel perspective and introduce a \emph{dataset factorization} approach, termed \emph{HaBa}, which is a plug-and-play strategy portable to any existing DD baseline.
2 code implementations • 30 Oct 2022 • Songhua Liu, Kai Wang, Xingyi Yang, Jingwen Ye, Xinchao Wang
In this paper, we study \xw{dataset distillation (DD)}, from a novel perspective and introduce a \emph{dataset factorization} approach, termed \emph{HaBa}, which is a plug-and-play strategy portable to any existing DD baseline.
no code implementations • 14 Oct 2022 • Ge Fan, Chaoyun Zhang, Kai Wang, Junyang Chen
In this paper, we introduce a novel Multi-View Approach with Hybrid Attentive Networks (MV-HAN) for contents retrieval at the matching stage of recommender systems.
no code implementations • 6 Oct 2022 • Xiang Wang, Kai Wang, Xiaohong Li, Shiguo Lian
To compensate for the imbalance of different kernel numbers and classify kernels with multiple flaws accurately, we propose a multi-stage workflow which is able to locate the kernels in the captured image and classify their properties.
1 code implementation • 4 Oct 2022 • Kai Wang, Chenshen Wu, Andy Bagdanov, Xialei Liu, Shiqi Yang, Shangling Jui, Joost Van de Weijer
Lifelong object re-identification incrementally learns from a stream of re-identification tasks.
1 code implementation • 3 Oct 2022 • Kai Wang, Fei Yang, Joost Van de Weijer
In experiments on ImageNet-Subset and ImageNet-1K, we show that our method AttnDistill outperforms existing self-supervised knowledge distillation (SSKD) methods and achieves state-of-the-art k-NN accuracy compared with self-supervised learning (SSL) methods learning from scratch (with the ViT-S model).
no code implementations • 2 Oct 2022 • Michael Dohopolski, Kai Wang, Biling Wang, Ti Bai, Dan Nguyen, David Sher, Steve Jiang, Jing Wang
Especially for smaller, single institutional datasets, it may be important to evaluate multiple estimations techniques before incorporating a model into clinical practice.
no code implementations • 27 Sep 2022 • Hao Yu, Ji Hou, Zheng Qin, Mahdi Saleh, Ivan Shugurov, Kai Wang, Benjamin Busam, Slobodan Ilic
More specifically, 3D structures of the whole frame are first represented by our global PPF signatures, from which structural descriptors are learned to help geometric descriptors sense the 3D world beyond local regions.
1 code implementation • 22 Sep 2022 • Kai Wang, Yunxiang Li, Michael Dohopolski, Tao Peng, Weiguo Lu, You Zhang, Jing Wang
For Head and Neck Cancers (HNC) patient management, automatic gross tumor volume (GTV) segmentation and accurate pre-treatment cancer recurrence prediction are of great importance to assist physicians in designing personalized management plans, which have the potential to improve the treatment outcome and quality of life for HNC patients.
no code implementations • 11 Sep 2022 • Yuanchao Bai, Xianming Liu, Kai Wang, Xiangyang Ji, Xiaolin Wu, Wen Gao
In the lossless mode, the DLPR coding system first performs lossy compression and then lossless coding of residuals.
no code implementations • 18 Aug 2022 • Zangwei Zheng, Xiangyu Yue, Kai Wang, Yang You
In this paper, we propose a novel approach DoPrompt based on prompt learning to embed the knowledge of source domains in domain prompts for target domain prediction.
no code implementations • 15 Aug 2022 • Chaoyun Zhang, Kai Wang, Hao Chen, Ge Fan, Yingjie Li, Lifang Wu, Bingchao Zheng
However, the skill rating of a novice is usually inaccurate, as current matchmaking rating algorithms require considerable amount of games for learning the true skill of a new player.
1 code implementation • 14 Jul 2022 • Pengfei Chen, Xuehui Yu, Xumeng Han, Najmul Hassan, Kai Wang, Jiachen Li, Jian Zhao, Humphrey Shi, Zhenjun Han, Qixiang Ye
However, the performance gap between point supervised object detection (PSOD) and bounding box supervised detection remains large.
1 code implementation • 7 Jun 2022 • Shiqi Yang, Yaxing Wang, Kai Wang, Shangling Jui, Joost Van de Weijer
In this paper, we investigate Source-free Open-partial Domain Adaptation (SF-OPDA), which addresses the situation where there exist both domain and category shifts between source and target domains.
1 code implementation • 31 May 2022 • Along He, Kai Wang, Tao Li, Wang Bo, Hong Kang, Huazhu Fu
The two proposed PFF and DAB blocks can be integrated with the off-the-shelf backbone networks to address the two issues of multi-scale and feature inconsistency in the multi-class segmentation of fundus lesions, which will produce better feature representation in the feature space.
1 code implementation • 31 May 2022 • Shengqin Wang, Yongji Zhang, Minghao Zhao, Hong Qi, Kai Wang, Fenglin Wei, Yu Jiang
Skeleton-based action recognition methods are limited by the semantic extraction of spatio-temporal skeletal maps.
Ranked #4 on
Skeleton Based Action Recognition
on N-UCLA
1 code implementation • 28 May 2022 • Jianfei Yang, Xiangyu Peng, Kai Wang, Zheng Zhu, Jiashi Feng, Lihua Xie, Yang You
Domain Adaptation of Black-box Predictors (DABP) aims to learn a model on an unlabeled target domain supervised by a black-box predictor trained on a source domain.
1 code implementation • 23 May 2022 • Kai Wang, Bo Zhao, Xiangyu Peng, Zheng Zhu, Jiankang Deng, Xinchao Wang, Hakan Bilen, Yang You
Firstly, randomly masked face images are used to train the reconstruction module in FaceMAE.
1 code implementation • 9 May 2022 • Shiqi Yang, Yaxing Wang, Kai Wang, Shangling Jui, Joost Van de Weijer
Treating SFDA as an unsupervised clustering problem and following the intuition that local neighbors in feature space should have more similar predictions than other features, we propose to optimize an objective of prediction consistency.
no code implementations • 2 May 2022 • Xiaohong Li, Xiang Wang, Kai Wang, Shiguo Lian
Generating synchronized and natural lip movement with speech is one of the most important tasks in creating realistic virtual characters.
1 code implementation • 30 Apr 2022 • Kai Wang, Xiangyu Peng, Shuo Yang, Jianfei Yang, Zheng Zhu, Xinchao Wang, Yang You
This paradigm, however, is prone to significant degeneration under heavy label noise, as the number of clean samples is too small for conventional methods to behave well.
1 code implementation • 27 Apr 2022 • Qiucheng Wu, Yifan Jiang, Junru Wu, Kai Wang, Gong Zhang, Humphrey Shi, Zhangyang Wang, Shiyu Chang
To study the motion features in the latent space of StyleGAN, in this paper, we hypothesize and demonstrate that a series of meaningful, natural, and versatile small, local movements (referred to as "micromotion", such as expression, head movement, and aging effect) can be represented in low-rank spaces extracted from the latent space of a conventionally pre-trained StyleGAN-v2 model for face generation, with the guidance of proper "anchors" in the form of either short text or video clips.
1 code implementation • 26 Apr 2022 • Minghao Zhao, Le Wu, Yile Liang, Lei Chen, Jian Zhang, Qilin Deng, Kai Wang, Xudong Shen, Tangjie Lv, Runze Wu
While conventional CF models are known for facing the challenges of the popularity bias that favors popular items, one may wonder "Whether the existing graph-based CF models alleviate or exacerbate popularity bias of recommender systems?"
no code implementations • 23 Apr 2022 • Kai Wang, Zhao Song, Georgios Theocharous, Sridhar Mahadevan
Smoothed online combinatorial optimization considers a learner who repeatedly chooses a combinatorial decision to minimize an unknown changing cost function with a penalty on switching decisions in consecutive rounds.
no code implementations • 20 Apr 2022 • Qingyu Chen, Alexis Allot, Robert Leaman, Rezarta Islamaj Doğan, Jingcheng Du, Li Fang, Kai Wang, Shuo Xu, Yuefu Zhang, Parsa Bagherzadeh, Sabine Bergler, Aakash Bhatnagar, Nidhir Bhavsar, Yung-Chun Chang, Sheng-Jie Lin, Wentai Tang, Hongtong Zhang, Ilija Tavchioski, Senja Pollak, Shubo Tian, Jinfeng Zhang, Yulia Otmakhova, Antonio Jimeno Yepes, Hang Dong, Honghan Wu, Richard Dufour, Yanis Labrak, Niladri Chatterjee, Kushagri Tandon, Fréjus Laleye, Loïc Rakotoson, Emmanuele Chersoni, Jinghang Gu, Annemarie Friedrich, Subhash Chandra Pujari, Mariia Chizhikova, Naveen Sivadasan, Zhiyong Lu
To close the gap, we organized the BioCreative LitCovid track to call for a community effort to tackle automated topic annotation for COVID-19 literature.
no code implementations • 14 Apr 2022 • Li Fang, Kai Wang
Our results show that Bioformer outperforms BioBERT and PubMedBERT in this task.
1 code implementation • CVPR 2022 • Wangbo Zhao, Kai Wang, Xiangxiang Chu, Fuzhao Xue, Xinchao Wang, Yang You
Text-based video segmentation aims to segment the target object in a video based on a describing sentence.
Ranked #7 on
Referring Expression Segmentation
on A2D Sentences
Optical Flow Estimation
Referring Expression Segmentation
+2
no code implementations • 1 Apr 2022 • Hongmei Zhang, Kai Wang, Yan Zhou, Shadab Momin, Xiaofeng Yang, Mostafa Fatemi, Michael F. Insana
Significance: DQMP method is promising for imaging of multiple parameters, and can be generalized to global optimization for many other complex nonconvex functions and imaging of physical parameters.
no code implementations • 30 Mar 2022 • Sanket Shah, Kai Wang, Bryan Wilder, Andrew Perrault, Milind Tambe
Decision-Focused Learning (DFL) is a paradigm for tailoring a predictive model to a downstream optimization task that uses its predictions in order to perform better on that specific task.
1 code implementation • CVPR 2022 • Shiming Chen, Ziming Hong, Guo-Sen Xie, Wenhan Yang, Qinmu Peng, Kai Wang, Jian Zhao, Xinge You
Prior works either simply align the global features of an image with its associated class semantic vector or utilize unidirectional attention to learn the limited latent semantic representations, which could not effectively discover the intrinsic semantic knowledge e. g., attribute semantics) between visual and attribute features.
2 code implementations • CVPR 2022 • Kai Wang, Bo Zhao, Xiangyu Peng, Zheng Zhu, Shuo Yang, Shuo Wang, Guan Huang, Hakan Bilen, Xinchao Wang, Yang You
Dataset condensation aims at reducing the network training effort through condensing a cumbersome training set into a compact synthetic one.
no code implementations • 1 Mar 2022 • Kaiqi Fu, Shaojun Gao, Kai Wang, Wei Li, Xiaohai Tian, Zejun Ma
Moreover, we utilize multi-source information (e. g., MFCC and deep features) to further improve the scoring system performance.
1 code implementation • CVPR 2022 • Xiangyu Peng, Kai Wang, Zheng Zhu, Mang Wang, Yang You
For high performance Siamese representation learning, one of the keys is to design good contrastive pairs.
no code implementations • 2 Feb 2022 • Kai Wang, Shresth Verma, Aditya Mate, Sanket Shah, Aparna Taneja, Neha Madhiwalla, Aparna Hegde, Milind Tambe
To address this shortcoming, we propose a novel approach for decision-focused learning in RMAB that directly trains the predictive model to maximize the Whittle index solution quality.
no code implementations • 3 Jan 2022 • Kai Wang, Yu Liu, Quan Z. Sheng
Knowledge graph embedding (KGE) has shown great potential in automatic knowledge graph (KG) completion and knowledge-driven tasks.
no code implementations • 10 Dec 2021 • Kai Wang, Xianghao Xu, Leon Lei, Selena Ling, Natalie Lindsay, Angel X. Chang, Manolis Savva, Daniel Ritchie
We then discuss different strategies for solving the problem, and design two representative pipelines: one uses available 2D floor plans to guide selection and deformation of 3D rooms; the other learns to retrieve a set of compatible 3D rooms and combine them into novel layouts.
no code implementations • 1 Dec 2021 • Kai Wang, Paul Guerrero, Vladimir Kim, Siddhartha Chaudhuri, Minhyuk Sung, Daniel Ritchie
We present the Shape Part Slot Machine, a new method for assembling novel 3D shapes from existing parts by performing contact-based reasoning.
1 code implementation • 9 Nov 2021 • Kai Wang, Xialei Liu, Andy Bagdanov, Luis Herranz, Shangling Jui, Joost Van de Weijer
We propose an approach to IML, which we call Episodic Replay Distillation (ERD), that mixes classes from the current task with class exemplars from previous tasks when sampling episodes for meta-learning.
1 code implementation • 27 Oct 2021 • Theodore Jiang, Li Fang, Kai Wang
In this study, we introduce MutFormer, a transformer-based model for the prediction of deleterious missense mutations, which uses reference and mutated protein sequences from the human genome as the primary features.
1 code implementation • 21 Oct 2021 • Kai Wang, Xialei Liu, Luis Herranz, Joost Van de Weijer
To overcome forgetting in this benchmark, we propose Hierarchy-Consistency Verification (HCV) as an enhancement to existing continual learning methods.
1 code implementation • 18 Oct 2021 • Kai Wang, Zhene Zou, Yue Shang, Qilin Deng, Minghao Zhao, Yile Liang, Runze Wu, Jianrong Tao, Xudong Shen, Tangjie Lyu, Changjie Fan
Reinforcement learning based recommender systems (RL-based RS) aim at learning a good policy from a batch of collected data, by casting sequential recommendations to multi-step decision-making tasks.
no code implementations • 13 Oct 2021 • Kai Wang, Zhonghao Wang, Mo Yu, Humphrey Shi
The manager agent is a multi-hop plan generator dealing with high-level abstract information and generating a series of sub-goals in a backward manner.
no code implementations • 4 Sep 2021 • Ruizhi Chen, Xiaoyu Wu, Yansong Pan, Kaizhao Yuan, Ling Li, TianYun Ma, JiYuan Liang, Rui Zhang, Kai Wang, Chen Zhang, Shaohui Peng, Xishan Zhang, Zidong Du, Qi Guo, Yunji Chen
In this framework, the environment can be easily configured to realize all kinds of RL tasks in the mainstream research.
no code implementations • 7 Jul 2021 • Kai Wang, Bryan Wilder, Sze-chuan Suen, Bistra Dilkina, Milind Tambe
We introduce a novel decomposed GP regression to incorporate the subgroup decomposed feedback.
no code implementations • NeurIPS 2021 • Kai Wang, Sanket Shah, Haipeng Chen, Andrew Perrault, Finale Doshi-Velez, Milind Tambe
In the predict-then-optimize framework, the objective is to train a predictive model, mapping from environment features to parameters of an optimization problem, which maximizes decision quality when the optimization is subsequently solved.
no code implementations • NeurIPS 2021 • Kai Wang, Sanket Shah, Haipeng Chen, Andrew Perrault, Finale Doshi-Velez, Milind Tambe
In the predict-then-optimize framework, the objective is to train a predictive model, mapping from environment features to parameters of an optimization problem, which maximizes decision quality when the optimization is subsequently solved.
1 code implementation • CVPR 2022 • Kai Wang, Shuo Wang, Panpan Zhang, Zhipeng Zhou, Zheng Zhu, Xiaobo Wang, Xiaojiang Peng, Baigui Sun, Hao Li, Yang You
This method adopts Dynamic Class Pool (DCP) for storing and updating the identities features dynamically, which could be regarded as a substitute for the FC layer.
Ranked #1 on
Face Verification
on IJB-C
(training dataset metric)
no code implementations • 18 May 2021 • Kai Wang, Luis Herranz, Joost Van de Weijer
Methods are typically allowed to use a limited buffer to store some of the images in the stream.
no code implementations • 23 Apr 2021 • Jinxing Ye, Xioajiang Peng, Baigui Sun, Kai Wang, Xiuyu Sun, Hao Li, Hanqing Wu
In this paper, we repurpose the well-known Transformer and introduce a Face Transformer for supervised face clustering.
no code implementations • 14 Apr 2021 • Kai Wang, Luis Herranz, Joost Van de Weijer
We found that the indexing stage pays an important role and that simply avoiding reindexing the database with updated embedding networks can lead to significant gains.
no code implementations • 12 Apr 2021 • Qilin Deng, Kai Wang, Minghao Zhao, Zhene Zou, Runze Wu, Jianrong Tao, Changjie Fan, Liang Chen
In business domains, \textit{bundling} is one of the most important marketing strategies to conduct product promotions, which is commonly used in online e-commerce and offline retailers.
no code implementations • 7 Apr 2021 • Kai Wang, Zhene Zou, Qilin Deng, Runze Wu, Jianrong Tao, Changjie Fan, Liang Chen, Peng Cui
As a part of the value function, free from the sparse and high-variance reward signals, a high-capacity reward-independent world model is trained to simulate complex environmental dynamics under a certain goal.
Model-based Reinforcement Learning
Recommendation Systems
+2
no code implementations • Findings (EMNLP) 2021 • Kai Wang, Yu Liu, Dan Lin, Quan Z. Sheng
Recent knowledge graph embedding (KGE) models based on hyperbolic geometry have shown great potential in a low-dimensional embedding space.
no code implementations • 18 Mar 2021 • Kai Wang, Bengbeng He, Wei-Ping Zhu
In this paper, we propose a transformer-based architecture, called two-stage transformer neural network (TSTNN) for end-to-end speech denoising in the time domain.
no code implementations • 8 Mar 2021 • Shiqi Yang, Kai Wang, Luis Herranz, Joost Van de Weijer
Zero-shot learning (ZSL) aims to discriminate images from unseen classes by exploiting relations to seen classes via their attribute-based descriptions.
no code implementations • 16 Feb 2021 • Ning li, Tao Li, Chunyu Hu, Kai Wang, Hong Kang
In ophthalmology, early fundus screening is an economic and effective way to prevent blindness caused by ophthalmic diseases.
1 code implementation • 25 Jan 2021 • Tao Li, Wang Bo, Chunyu Hu, Hong Kang, Hanruo Liu, Kai Wang, Huazhu Fu
The use of fundus images for the early screening of eye diseases is of great clinical importance.
no code implementations • 27 Dec 2020 • Hengshun Zhou, Debin Meng, Yuanyuan Zhang, Xiaojiang Peng, Jun Du, Kai Wang, Yu Qiao
The audio-video based emotion recognition aims to classify a given video into basic emotions.
Facial Expression Recognition (FER)
Video Emotion Recognition
no code implementations • 20 Dec 2020 • Kai Wang, Chunxu Shen, Chaoyun Zhang Wenye Ma
In this paper, we consider the Click-Through-Rate (CTR) prediction problem.
no code implementations • 18 Dec 2020 • Kai Wang, Yuxin Gu, Xiaojiang Peng, Panpan Zhang, Baigui Sun, Hao Li
The domain diversities including inconsistent annotation and varied image collection conditions inevitably exist among different facial expression recognition (FER) datasets, which pose an evident challenge for adapting the FER model trained on one dataset to another one.
no code implementations • 17 Dec 2020 • Jia-Xiao Dai, Kai Wang, Shengyuan A. Yang, Y. X. Zhao
Particularly, the global Takagi's factorization can (cannot) be done on a $3$D ($2$D) sphere.
Mesoscale and Nanoscale Physics
1 code implementation • ICCV 2021 • Zhonghao Wang, Kai Wang, Mo Yu, JinJun Xiong, Wen-mei Hwu, Mark Hasegawa-Johnson, Humphrey Shi
Finally, we achieve a higher level of interpretability by imposing OCCAM on the objects represented in the induced symbolic concept space.
Ranked #3 on
Visual Question Answering
on CLEVR
2 code implementations • NeurIPS 2021 • Muhan Zhang, Pan Li, Yinglong Xia, Kai Wang, Long Jin
In this paper, we provide a theory of using graph neural networks (GNNs) for multi-node representation learning (where we are interested in learning a representation for a set of more than one node, such as link).
Ranked #1 on
Link Property Prediction
on ogbl-citation2
1 code implementation • ECCV 2020 • Xiaojiang Peng, Kai Wang, Zhaoyang Zeng, Qing Li, Jianfei Yang, Yu Qiao
Specifically, this plug-and-play AFM first leverages a \textit{group-to-attend} module to construct groups and assign attention weights for group-wise samples, and then uses a \textit{mixup} module with the attention weights to interpolate massive noisy-suppressed samples.
no code implementations • 14 Oct 2020 • Kai Wang, Yu Liu, Qian Ma, Quan Z. Sheng
Link prediction based on knowledge graph embeddings (KGE) aims to predict new triples to automatically construct knowledge graphs (KGs).
no code implementations • 29 Sep 2020 • Yixin Li, Chen Li, Xiaoyan Li, Kai Wang, Md Mamunur Rahaman, Changhao Sun, Hao Chen, Xinran Wu, Hong Zhang, Qian Wang
In this review, we present a comprehensive overview of pathology image analysis based on the markov random fields (MRFs) and conditional random fields (CRFs), which are two popular random field models.
no code implementations • 28 Sep 2020 • Muhan Zhang, Pan Li, Yinglong Xia, Kai Wang, Long Jin
Graph neural networks (GNNs) have achieved great success in recent years.
1 code implementation • 17 Sep 2020 • R. Kenny Jones, Theresa Barton, Xianghao Xu, Kai Wang, Ellen Jiang, Paul Guerrero, Niloy J. Mitra, Daniel Ritchie
The program captures the subset of variability that is interpretable and editable.
2 code implementations • 14 Sep 2020 • Lily Xu, Elizabeth Bondi, Fei Fang, Andrew Perrault, Kai Wang, Milind Tambe
Conservation efforts in green security domains to protect wildlife and forests are constrained by the limited availability of defenders (i. e., patrollers), who must patrol vast areas to protect from attackers (e. g., poachers or illegal loggers).
1 code implementation • 31 Aug 2020 • Jiacheng Meng, Cheng Li, Houjun Mo, Yangyao Chen, Kai Wang
Using realistic mock catalogs we show that target selection and redshift incompleteness can lead to significantly biased results.
Astrophysics of Galaxies
1 code implementation • 4 Jul 2020 • Shenda Hong, Zhaoji Fu, Rongbo Zhou, Jie Yu, Yongkui Li, Kai Wang, Guanlin Cheng
Electrocardiogram (ECG) is one of the most convenient and non-invasive tools for monitoring peoples' heart condition, which can use for diagnosing a wide range of heart diseases, including Cardiac Arrhythmia, Acute Coronary Syndrome, et al.
no code implementations • ACL 2020 • Jianxing Yu, Wei Liu, Shuang Qiu, Qinliang Su, Kai Wang, Xiaojun Quan, Jian Yin
Specifically, we first build a multi-hop generation model and guide it to satisfy the logical rationality by the reasoning chain extracted from a given text.
no code implementations • 26 Jun 2020 • Kai Wang, Luis Herranz, Anjan Dutta, Joost Van de Weijer
We propose bookworm continual learning(BCL), a flexible setting where unseen classes can be inferred via a semantic model, and the visual model can be updated continually.
2 code implementations • NeurIPS 2020 • Kai Wang, Bryan Wilder, Andrew Perrault, Milind Tambe
Solving optimization problems with unknown parameters often requires learning a predictive model to predict the values of the unknown parameters and then solving the problem using these values.
no code implementations • 10 Jun 2020 • Shiqi Yang, Kai Wang, Luis Herranz, Joost Van de Weijer
Zero-shot learning (ZSL) aims to discriminate images from unseen classes by exploiting relations to seen classes via their semantic descriptions.
1 code implementation • ACL 2020 • Kai Wang, Weizhou Shen, Yunyi Yang, Xiaojun Quan, Rui Wang
Then, we propose a relational graph attention network (R-GAT) to encode the new tree structure for sentiment prediction.
1 code implementation • ACL 2020 • Kai Wang, Junfeng Tian, Rui Wang, Xiaojun Quan, Jianxing Yu
Unlike those pipeline approaches, our act generation module preserves the semantic structures of multi-domain dialogue acts and our response generation module dynamically attends to different acts as needed.
1 code implementation • 21 Apr 2020 • Mang Tik Chiu, Xingqian Xu, Kai Wang, Jennifer Hobbs, Naira Hovakimyan, Thomas S. Huang, Honghui Shi, Yunchao Wei, Zilong Huang, Alexander Schwing, Robert Brunner, Ivan Dozier, Wyatt Dozier, Karen Ghandilyan, David Wilson, Hyunseong Park, Junhee Kim, Sungho Kim, Qinghui Liu, Michael C. Kampffmeyer, Robert Jenssen, Arnt B. Salberg, Alexandre Barbosa, Rodrigo Trevisan, Bingchen Zhao, Shaozuo Yu, Siwei Yang, Yin Wang, Hao Sheng, Xiao Chen, Jingyi Su, Ram Rajagopal, Andrew Ng, Van Thong Huynh, Soo-Hyung Kim, In-Seop Na, Ujjwal Baid, Shubham Innani, Prasad Dutande, Bhakti Baheti, Sanjay Talbar, Jianyu Tang
The first Agriculture-Vision Challenge aims to encourage research in developing novel and effective algorithms for agricultural pattern recognition from aerial images, especially for the semantic segmentation task associated with our challenge dataset.
2 code implementations • CVPR 2020 • Lu Yu, Bartłomiej Twardowski, Xialei Liu, Luis Herranz, Kai Wang, Yongmei Cheng, Shangling Jui, Joost Van de Weijer
The vast majority of methods have studied this scenario for classification networks, where for each new task the classification layer of the network must be augmented with additional weights to make room for the newly added classes.
no code implementations • Remote Sensing 2020 • Zhifeng Xiao, Linjun Qian, Weiping Shao, Xiaowei Tan, Kai Wang
Arbitrary orientated objects are detected by predicting the axis of the object, which is the line connecting the head and tail of the object, and the width of the object is vertical to the axis.
Ranked #1 on
One-stage Anchor-free Oriented Object Detection
on HRSC2016
( mAP metric)
2 code implementations • 11 Mar 2020 • Yangyao Chen, H. J. Mo, Cheng Li, Huiyuan Wang, Xiaohu Yang, Youcai Zhang, Kai Wang
Using decision trees built with the random ensemble method, we find that the correlation between halo concentration and assembly history is tight: more than 60% of the variance in halo concentration can be explained by assembly history alone.
Astrophysics of Galaxies Cosmology and Nongalactic Astrophysics
2 code implementations • CVPR 2020 • Kai Wang, Xiaojiang Peng, Jianfei Yang, Shijian Lu, Yu Qiao
Annotating a qualitative large-scale facial expression dataset is extremely difficult due to the uncertainties caused by ambiguous facial expressions, low-quality facial images, and the subjectiveness of annotators.
no code implementations • 20 Feb 2020 • Qilin Fan, Xiuhua Li, Jian Li, Qiang He, Kai Wang, Junhao Wen
Compared to the conventional content delivery networks, caches in edge networks with smaller sizes usually have to accommodate more bursty requests.
no code implementations • 4 Feb 2020 • Yaoting Wang, Yongzhen Ke, Kai Wang, Cuijiao Zhang, Fan Qin
Image aesthetic quality assessment has got much attention in recent years, but not many works have been done on a specific genre of photos: Group photograph.
no code implementations • 21 Aug 2019 • Zezhou Chen, Zhaoxiang Liu, Huan Hu, Jinqiang Bai, Shiguo Lian, Fuyuan Shi, Kai Wang
Based on the models' output, the synthesizer uses the Pixel2Pixel model to generate realistic facial images.
no code implementations • 20 Aug 2019 • Liang Zhao, Zhiyuan Ma, Yangming Zhou, Kai Wang, Shengping Liu, Ju Gao
Electronic health record is an important source for clinical researches and applications, and errors inevitably occur in the data, which could lead to severe damages to both patients and hospital services.
no code implementations • 19 Aug 2019 • Zhaoxiang Liu, Huan Hu, Zipeng Wang, Kai Wang, Jinqiang Bai, Shiguo Lian
This paper presents a generative adversarial learning-based human upper body video synthesis approach to generate an upper body video of target person that is consistent with the body motion, face expression, and pose of the person in source video.
no code implementations • 9 Aug 2019 • Yimin Lin, Kai Wang, Wanxin Yi, Shiguo Lian
In this paper, we propose a deep learning based assistive system to improve the environment perception experience of visually impaired (VI).
no code implementations • 12 Jul 2019 • Chun-Mei Feng, Kai Wang, Shijian Lu, Yong Xu, Heng Kong, Ling Shao
The deep sub-network learns from the residuals of the high-frequency image information, where multiple residual blocks are cascaded to magnify the MRI images at the last network layer.
no code implementations • 8 Jul 2019 • Kai Wang, Jianfei Yang, Da Guo, Kaipeng Zhang, Xiaojiang Peng, Yu Qiao
Based on our winner solution last year, we mainly explore head features and body features with a bootstrap strategy and two novel loss functions in this paper.
1 code implementation • 29 Jun 2019 • Debin Meng, Xiaojiang Peng, Kai Wang, Yu Qiao
The feature embedding module is a deep Convolutional Neural Network (CNN) which embeds face images into feature vectors.
Ranked #2 on
Facial Expression Recognition (FER)
on CK+
(Accuracy (7 emotion) metric)
1 code implementation • ACL 2019 • Kai Wang, Xiaojun Quan, Rui Wang
The success of neural summarization models stems from the meticulous encodings of source articles.
Ranked #14 on
Text Summarization
on GigaWord
1 code implementation • 16 May 2019 • Guoguang Du, Kai Wang, Shiguo Lian, Kaiyong Zhao
We conclude three key tasks during vision-based robotic grasping, which are object localization, object pose estimation and grasp estimation.
1 code implementation • 14 May 2019 • Lin-Zhuo Chen, Xuan-Yi Li, Deng-Ping Fan, Kai Wang, Shao-Ping Lu, Ming-Ming Cheng
We design a novel Local Spatial Aware (LSA) layer, which can learn to generate Spatial Distribution Weights (SDWs) hierarchically based on the spatial relationship in local region for spatial independent operations, to establish the relationship between these operations and spatial distribution, thus capturing the local geometric structure sensitively. We further propose the LSANet, which is based on LSA layer, aggregating the spatial information with associated features in each layer of the network better in network design. The experiments show that our LSANet can achieve on par or better performance than the state-of-the-art methods when evaluating on the challenging benchmark datasets.
1 code implementation • 10 May 2019 • Kai Wang, Xiaojiang Peng, Jianfei Yang, Debin Meng, Yu Qiao
Extensive experiments show that our RAN and region biased loss largely improve the performance of FER with occlusion and variant pose.
Ranked #1 on
Facial Expression Recognition (FER)
on SFEW
no code implementations • 5 May 2019 • Minjie Hua, Fuyuan Shi, Yibing Nan, Kai Wang, Hao Chen, Shiguo Lian
This paper presents a novel system that enables intelligent robots to exhibit realistic body gestures while communicating with humans.
no code implementations • 30 Apr 2019 • Jinqiang Bai, Shiguo Lian, Zhaoxiang Liu, Kai Wang, Dijun Liu
In addition, with the ground segmentation using a deep neural network, a novel navigation strategy is proposed to guide the robot to move around.
no code implementations • 30 Apr 2019 • Jinqiang Bai, Shiguo Lian, Zhaoxiang Liu, Kai Wang, Dijun Liu
To help the blind people walk to the destination efficiently and safely in indoor environment, a novel wearable navigation device is presented in this paper.
no code implementations • 28 Apr 2019 • Kai Wang, Fuyuan Shi, Wenqi Wang, Yibing Nan, Shiguo Lian
This paper presents an improved scheme for the generation and adaption of synthetic images for the training of deep Convolutional Neural Networks(CNNs) to perform the object detection task in smart vending machines.
no code implementations • International Journal of Modern Physics C 2019 • Jinfang Sheng, Kai Wang, Zejun Sun, Jie Hu, Bin Wang and Aman Ullah
In recent years, community detection has gradually become a hot topic in the complex network data mining field.
no code implementations • 26 Apr 2019 • Xiang Wang, Kai Wang, Shiguo Lian
The quality and size of training set have great impact on the results of deep learning-based face related tasks.
no code implementations • 17 Feb 2019 • Weize Quan, Dong-Ming Yan, Kai Wang, Xiaopeng Zhang, Denis Pellerin
First, we design and implement a base network, which can attain better performance in terms of classification accuracy and generalization (in most cases) compared with state-of-the-art methods.
no code implementations • 25 Dec 2018 • Kai Wang, Yimin Lin, Luowei Wang, Liming Han, Minjie Hua, Xiang Wang, Shiguo Lian, Bill Huang
This paper presents a novel framework for simultaneously implementing localization and segmentation, which are two of the most important vision-based tasks for robotics.
1 code implementation • CVPR 2019 • Daniel Ritchie, Kai Wang, Yu-an Lin
We present a new, fast and flexible pipeline for indoor scene synthesis that is based on deep convolutional generative models.
no code implementations • 1 Nov 2018 • Sheng Shen, Yaliang Li, Nan Du, Xian Wu, Yusheng Xie, Shen Ge, Tao Yang, Kai Wang, Xingzheng Liang, Wei Fan
Question answering (QA) has achieved promising progress recently.
no code implementations • ECCV 2018 • Jie Liang, Jufeng Yang, Hsin-Ying Lee, Kai Wang, Ming-Hsuan Yang
The recent years have witnessed significant growth in constructing robust generative models to capture informative distributions of natural data.
no code implementations • WS 2018 • Ozan Caglayan, Adrien Bardet, Fethi Bougares, Loïc Barrault, Kai Wang, Marc Masana, Luis Herranz, Joost Van de Weijer
This paper describes the multimodal Neural Machine Translation systems developed by LIUM and CVC for WMT18 Shared Task on Multimodal Translation.
no code implementations • 11 Aug 2018 • Kai Wang, Yu Liu, Xiujuan Xu, Dan Lin
Knowledge Graph Embedding (KGE) aims to represent entities and relations of knowledge graph in a low-dimensional continuous vector space.
no code implementations • 14 Mar 2018 • Artem Maksov, Ondrej Dyck, Kai Wang, Kai Xiao, David B. Geohegan, Bobby G. Sumpter, Rama K. Vasudevan, Stephen Jesse, Sergei V. Kalinin, Maxim Ziatdinov
Understanding elementary mechanisms behind solid-state phase transformations and reactions is the key to optimizing desired functional properties of many technologically relevant materials.
Materials Science
1 code implementation • 11 Mar 2018 • Song Guo, Kai Wang, Hong Kang, Yujun Zhang, Yingqi Gao, Tao Li
Results: The proposed BTS-DSN has been verified on DRIVE, STARE and CHASE_DB1 datasets, and showed competitive performance over other state-of-the-art methods.
3 code implementations • CVPR 2017 • Yun Liu, Ming-Ming Cheng, Xiao-Wei Hu, Kai Wang, Xiang Bai
Using VGG16 network, we achieve \sArt results on several available datasets.
Ranked #5 on
Edge Detection
on BIPED