2 code implementations • 9 May 2016 • Liqian Ma, Hong Liu, Liang Hu, Can Wang, Qianru Sun
Experimental results on three public datasets and two proposed datasets demonstrate the superiority of the proposed approach, indicating the effectiveness of body structure and orientation information for improving re-identification performance.
no code implementations • 19 Nov 2016 • Hong Liu, Rongrong Ji, Yongjian Wu, Feiyue Huang
By given a large-scale training data set, it is very expensive to embed such ranking tuples in binary code learning.
1 code implementation • The 13th Asian Conference on Computer Vision 2016 • Haomiao Ni, Hong Liu, Xiangdong Wang, Yueliang Qian
This paper proposes a novel human action recognition using the decision-level fusion of both skeleton and depth sequence.
no code implementations • 23 May 2017 • Hong Liu, Juanhui Tu, Mengyuan Liu
Extensive experiments on the SmartHome dataset and the large-scale NTU RGB-D dataset demonstrate that our method outperforms most of RNN-based methods, which verify the complementary property between spatial and temporal information and the robustness to noise.
Skeleton Based Action Recognition Vocal Bursts Valence Prediction
no code implementations • CVPR 2017 • Hong Liu, Rongrong Ji, Yongjian Wu, Feiyue Huang, Baochang Zhang
In this paper, we propose a hashing scheme, termed Fusion Similarity Hashing (FSH), which explicitly embeds the graph-based fusion similarity across modalities into a common Hamming space.
no code implementations • Pattern Recognition 2017 • Mengyuan Liu, Hong Liu, Chen Chen
First, a sequence-based view invariant transform is developed to eliminate the effect of view variations on spatio-temporal locations of skeleton joints.
Ranked #2 on Skeleton Based Action Recognition on UWA3D
no code implementations • 4 Dec 2017 • Mengyuan Liu, Hong Liu, Chen Chen
Then, motion and shape cues are jointly used to generate robust and distinctive spatial-temporal interest points (STIPs): motion-based STIPs and shape-based STIPs.
no code implementations • 22 Dec 2017 • Fanyang Meng, Hong Liu, Yongsheng Liang, Wei Liu, Jihong Pei
The bandwidth of a kernel function is a crucial parameter in the mean shift algorithm.
1 code implementation • CVPR 2018 • Dan Xu, Wei Wang, Hao Tang, Hong Liu, Nicu Sebe, Elisa Ricci
Recent works have shown the benefit of integrating Conditional Random Fields (CRFs) models into deep architectures for improving pixel-level prediction tasks.
no code implementations • 5 May 2018 • Haichao Cao, Hong Liu, Enmin Song
The localization of BMC is achieved from a color transformation enhanced BMC sample image and stepwise averaging method (SAM).
no code implementations • 28 May 2018 • Xiao Liu, Shengchuan Zhang, Hong Liu, Xin Liu, Cheng Deng, Rongrong Ji
In principle, CerfGAN contains a novel component, i. e., a multi-class discriminator (MCD), which gives the model an extremely powerful ability to match multiple translation mappings.
no code implementations • ECCV 2018 • Xia Li, Jianlong Wu, Zhouchen Lin, Hong Liu, Hongbin Zha
In heavy rain, rain streaks have various directions and shapes, which can be regarded as the accumulation of multiple rain streak layers.
Ranked #7 on Single Image Deraining on Test2800
1 code implementation • 11 Aug 2018 • Bochen Guan, Hanrong Ye, Hong Liu, William A. Sethares
Estimation of the frequency and duration of logos in videos is important and challenging in the advertisement industry as a way of estimating the impact of ad purchases.
1 code implementation • 6 Nov 2018 • Hanrong Ye, Xia Li, Hong Liu, Wei Shi, Mengyuan Liu, Qianru Sun
Rain removal aims to extract and remove rain streaks from images.
no code implementations • 13 Nov 2018 • Haotian Hang, Bin Yu, Yang Xiang, Bin Zhang, Hong Liu
High-accuracy and high-efficiency finite-time Lyapunov exponent (FTLE) calculation method has long been a research hot point, and adaptive refinement method is a kind of method in this field.
Fluid Dynamics
1 code implementation • 27 Nov 2018 • Renqiang Li, Hong Liu, Xiangdong Wan, Yueliang Qian
Braille dots detection is the core and basic step for Braille image recognition.
1 code implementation • CVPR 2019 • Jie Hu, Rongrong Ji, Hong Liu, Shengchuan Zhang, Cheng Deng, Qi Tian
In this paper, we make the first attempt towards visual feature translation to break through the barrier of using features across different visual search systems.
no code implementations • ICCV 2019 • Jie Li, Rongrong Ji, Hong Liu, Xiaopeng Hong, Yue Gao, Qi Tian
In this paper, we make the first attempt in attacking image retrieval systems.
1 code implementation • 15 Jan 2019 • Hao Tang, Hong Liu, Wei Xiao, Nicu Sebe
Gesture recognition is a hot topic in computer vision and pattern recognition, which plays a vitally important role in natural human-computer interface.
Ranked #1 on Hand Gesture Recognition on Cambridge
1 code implementation • 29 Jan 2019 • Mingbao Lin, Rongrong Ji, Hong Liu, Xiaoshuai Sun, Yongjian Wu, Yunsheng Wu
In this paper, we propose a novel supervised online hashing method, termed Balanced Similarity for Online Discrete Hashing (BSODH), to solve the above problems in a unified framework.
no code implementations • 8 Apr 2019 • Yong Luo, DaCheng Tao, Chang Xu, Chao Xu, Hong Liu, Yonggang Wen
In computer vision, image datasets used for classification are naturally associated with multiple labels and comprised of multiple views, because each image may contain several objects (e. g. pedestrian, bicycle and tree) and is properly characterized by multiple visual features (e. g. color, texture and shape).
1 code implementation • 28 Apr 2019 • Mingbao Lin, Rongrong Ji, Hong Liu, Yongjian Liu
Notably, the proposed HCOH can be embedded with supervised labels and it not limited to a predefined category number.
no code implementations • 9 May 2019 • Haichao Cao, Hong Liu, Enmin Song, Guangzhi Ma, Xiangyang Xu, Renchao Jin, Tengying Liu, Chih-Cheng Hung
The CNN architecture in the first stage is based on the improved UNet segmentation network to establish an initial detection of lung nodules.
1 code implementation • 11 May 2019 • Mingbao Lin, Rongrong Ji, Hong Liu, Xiaoshuai Sun, Shen Chen, Qi Tian
We then treat the learning of hash functions as a set of binary classification problems to fit the assigned target code.
no code implementations • 21 May 2019 • Haichao Cao, Hong Liu, Enmin Song, Chih-Cheng Hung, Guangzhi Ma, Xiangyang Xu, Renchao Jin, Jianguo Lu
Experimental results show that the DB-ResNet achieves superior segmentation performance with an average dice score of 82. 74% on the dataset.
no code implementations • 21 May 2019 • Haichao Cao, Hong Liu, Enmin Song
First, the nucleus of leukocyte was separated by using the stepwise averaging method.
1 code implementation • 24 May 2019 • Liwei Lin, Xiangdong Wang, Hong Liu, Yueliang Qian
In this paper, a special decision surface for the weakly-supervised sound event detection (SED) and a disentangled feature (DF) for the multi-label problem in polyphonic SED are proposed.
no code implementations • CVPR 2019 • Hong Liu, Zhangjie Cao, Mingsheng Long, Jianmin Wang, Qiang Yang
While several methods have been proposed to address OSDA, none of them takes into account the openness of the target domain, which is measured by the proportion of unknown classes in all target classes.
1 code implementation • 6 Jun 2019 • Liwei Lin, Xiangdong Wang, Hong Liu, Yueliang Qian
Instead of designing a single model by considering a trade-off between the two sub-targets, we design a teacher model aiming at audio tagging to guide a student model aiming at boundary detection to learn using the unlabeled data.
no code implementations • 13 Jun 2019 • Da Sun Handason Tam, Wing Cheong Lau, Bin Hu, Qiu Fang Ying, Dah Ming Chiu, Hong Liu
In the context of e-payment transaction graphs, the resultant node and edge embeddings can effectively characterize the user-background as well as the financial transaction patterns of individual account holders.
5 code implementations • ICCV 2019 • Xia Li, Zhisheng Zhong, Jianlong Wu, Yibo Yang, Zhouchen Lin, Hong Liu
It is designed to compute the representation of each position by a weighted sum of the features at all positions.
Ranked #11 on Semantic Segmentation on COCO-Stuff test
1 code implementation • 11 Sep 2019 • Liwei Lin, Xiangdong Wang, Hong Liu, Yueliang Qian
In this paper, we describe in detail the system we submitted to DCASE2019 task 4: sound event detection (SED) in domestic environments.
no code implementations • 26 Sep 2019 • Hong Liu, Mingsheng Long, Jian-Min Wang, Michael. I. Jordan
3) The feasibility of transferability is related to the similarity of both input and label.
no code implementations • ICCV 2019 • Hong Liu, Rongrong Ji, Jie Li, Baochang Zhang, Yue Gao, Yongjian Wu, Feiyue Huang
Deep learning models have shown their vulnerabilities to universal adversarial perturbations (UAP), which are quasi-imperceptible.
no code implementations • 6 Nov 2019 • Yong Ruan, Xiangdong Wang, Hong Liu, Zhigang Ou, Yun Gao, Jianfeng Cheng, Yueliang Qian
For this, we train transformer model using feature sequence of audio and their phoneme sequence with lexical stress marks.
2 code implementations • 27 Nov 2019 • Hao Tang, Hong Liu, Dan Xu, Philip H. S. Torr, Nicu Sebe
State-of-the-art methods in image-to-image translation are capable of learning a mapping from a source domain to a target domain with unpaired image data.
Ranked #1 on Facial Expression Translation on CelebA
1 code implementation • 12 Dec 2019 • Hao Tang, Hong Liu, Nicu Sebe
The proposed model consists of a single generator and a discriminator taking a conditional image and the target controllable structure as input.
Ranked #1 on Cross-View Image-to-Image Translation on cvusa
Facial Expression Translation Generative Adversarial Network +3
1 code implementation • 14 Dec 2019 • Hao Tang, Dan Xu, Hong Liu, Nicu Sebe
In this paper, we analyze the limitation of the existing symmetric GAN models in asymmetric translation tasks, and propose an AsymmetricGAN model with both translation and reconstruction generators of unequal sizes and different parameter-sharing strategy to adapt to the asymmetric need in both unsupervised and supervised image-to-image translation tasks.
no code implementations • 14 Feb 2020 • Bin Ren, Mengyuan Liu, Runwei Ding, Hong Liu
To the best of our knowledge, this research represents the first comprehensive discussion of deep learning-based action recognition using 3D skeleton data.
no code implementations • CVPR 2020 • Xia Li, Yibo Yang, Qijie Zhao, Tiancheng Shen, Zhouchen Lin, Hong Liu
The convolution operation suffers from a limited receptive filed, while global modeling is fundamental to dense prediction tasks, such as semantic segmentation.
no code implementations • 12 Apr 2020 • Weibo Huang, Hong Liu, Weiwei Wan
To compensate for the impact of time offset, our method includes two short-term motion interpolation algorithms for the camera and IMU pose estimation.
no code implementations • 14 Apr 2020 • Hong Liu, Pinhao Song, Runwei Ding
This paper aims to build a GUOD with small underwater dataset with limited types of water quality.
1 code implementation • CVPR 2020 • Jie Li, Rongrong Ji, Hong Liu, Jianzhuang Liu, Bineng Zhong, Cheng Deng, Qi Tian
For reducing the solution space, we first model the adversarial perturbation optimization problem as a process of recovering frequency-sparse perturbations with compressed sensing, under the setting that random noise in the low-frequency space is more likely to be adversarial.
1 code implementation • 21 May 2020 • Hao Tang, Hong Liu, Wei Xiao, Nicu Sebe
Then the activated dictionary atoms are assembled and passed to the compound dictionary learning and coding layers.
1 code implementation • 1 Jun 2020 • Hanrong Ye, Hong Liu, Fanyang Meng, Xia Li
As an angularly discriminative feature space is important for classifying the human images based on their embedding vectors, in this paper, we propose a novel ranking loss function, named Bi-directional Exponential Angular Triplet Loss, to help learn an angularly separable common feature space by explicitly constraining the included angles between embedding vectors.
no code implementations • 11 Jul 2020 • Bin Yu, Miaosheng He, Bin Zhang, Hong Liu
Based on the objective coordinate system in frame of oblique shock structure, it is found that the nature of three-dimensional lift-off structure of a shockinduced streamwise vortex is inherently and precisely controlled by a two-stage growth mode of structure kinetics of a shock bubble interaction (SBI for short).
Fluid Dynamics
no code implementations • ECCV 2020 • Hanlin Chen, Baochang Zhang, Song Xue, Xuan Gong, Hong Liu, Rongrong Ji, David Doermann
Deep convolutional neural networks (DCNNs) have dominated as the best performers in machine learning, but can be challenged by adversarial attacks.
no code implementations • 9 Sep 2020 • Morteza Heidari, Sivaramakrishnan Lakshmivarahan, Seyedehnafiseh Mirniaharikandehei, Gopichandh Danala, Sai Kiran R. Maryada, Hong Liu, Bin Zheng
Then, support vector machine (SVM) models embedded with several feature dimensionality reduction methods are built to predict likelihood of lesions being malignant.
no code implementations • 3 Nov 2020 • Hong Liu, Jeff Z. HaoChen, Colin Wei, Tengyu Ma
Recent works found that fine-tuning and joint training---two popular approaches for transfer learning---do not always improve accuracy on downstream tasks.
1 code implementation • NeurIPS 2020 • Hong Liu, Mingsheng Long, Jianmin Wang, Yu Wang
(2) Since the target data arrive online, the agent should also maintain competence on previous target domains, i. e. to adapt without forgetting.
no code implementations • 3 Dec 2020 • John Haslegrave, JaeHoon Kim, Hong Liu
We prove an asymptotically tight bound on the extremal density guaranteeing subdivisions of bounded-degree bipartite graphs with a mild separability condition.
Combinatorics 05C83, 05C35
no code implementations • 12 Dec 2020 • Can Zhang, Hong Liu, Wei Guo, Mang Ye
RGB-Infrared person re-identification (RGB-IR Re-ID) aims to match persons from heterogeneous images captured by visible and thermal cameras, which is of great significance in the surveillance system under poor light conditions.
no code implementations • 19 Dec 2020 • Hong Liu, Oleg Pikhurko, Maryam Sharifzadeh, Katherine Staden
We present a sufficient condition for the stability property of extremal graph problems that can be solved via Zykov's symmetrisation.
Combinatorics
1 code implementation • NeurIPS 2021 • Hong Liu, Jianmin Wang, Mingsheng Long
In the forward step, CST generates target pseudo-labels with a source-trained classifier.
1 code implementation • 26 Mar 2021 • Wenhao Li, Hong Liu, Runwei Ding, Mengyuan Liu, Pichao Wang, Wenming Yang
The modified VTE is termed as Strided Transformer Encoder (STE), which is built upon the outputs of VTE.
Ranked #2 on 3D Human Pose Estimation on HumanEva-I
no code implementations • 6 Apr 2021 • Yang Chen, Pinhao Song, Hong Liu, Linhui Dai, Xiaochuan Zhang, Runwei Ding, Shengquan Li
Second, for the images with the same semantic content in different domains, their hidden features should be equivalent.
no code implementations • NeurIPS 2021 • Yixu Wang, Jie Li, Hong Liu, Yan Wang, Yongjian Wu, Feiyue Huang, Rongrong Ji
We argue this is due to the lack of rich information in the probability prediction and the overfitting caused by hard labels.
no code implementations • 23 May 2021 • Guoliang Hua, Hong Liu, Wenhao Li, Qian Zhang, Runwei Ding, Xin Xu
Instead, exploiting multi-view information is a practical way to achieve absolute 3D human pose estimation.
Monocular 3D Human Pose Estimation Weakly-supervised 3D Human Pose Estimation +1
no code implementations • 27 May 2021 • Xuxin Chen, Ximin Wang, Ke Zhang, Kar-Ming Fung, Theresa C. Thai, Kathleen Moore, Robert S. Mannel, Hong Liu, Bin Zheng, Yuchen Qiu
Deep learning has received extensive research interest in developing new medical image processing algorithms, and deep learning based models have been remarkably successful in a variety of medical imaging tasks to support disease detection and diagnosis.
1 code implementation • ICLR 2021 • Xinshuai Dong, Anh Tuan Luu, Rongrong Ji, Hong Liu
Robustness against word substitutions has a well-defined and widely acceptable form, i. e., using semantically similar words as substitutions, and thus it is considered as a fundamental stepping-stone towards broader robustness in natural language processing.
1 code implementation • 25 Aug 2021 • Zhisheng Lu, Juncheng Li, Hong Liu, Chaoyan Huang, Linlin Zhang, Tieyong Zeng
LTB is composed of a series of Efficient Transformers (ET), which occupies a small GPU memory occupation, thanks to the specially designed Efficient Multi-Head Attention (EMHA).
2 code implementations • 9 Sep 2021 • Hong Liu, Yucheng Cai, Zhenru Lin, Zhijian Ou, Yi Huang, Junlan Feng
In this paper, we propose Variational Latent-State GPT model (VLS-GPT), which is the first to combine the strengths of the two approaches.
no code implementations • 18 Sep 2021 • Qinghui Sun, Jie Gu, Bei Yang, Xiaoxiao Xu, Renjun Xu, Shangde Gao, Hong Liu, Huan Xu
Universal user representation has received many interests recently, with which we can be free from the cumbersome work of training a specific model for each downstream application.
no code implementations • 29 Sep 2021 • Bei Yang, Ke Liu, Xiaoxiao Xu, Renjun Xu, Hong Liu, Huan Xu
However, existing researches have little ability to model universal user representation based on lifelong behavior sequences since user registration.
1 code implementation • 5 Oct 2021 • Zhirong Ye, Xiangdong Wang, Hong Liu, Yueliang Qian, Rui Tao, Long Yan, Kazushige Ouchi
A critical issue with the frame-based model is that it pursues the best frame-level prediction rather than the best event-level prediction.
1 code implementation • ICLR 2022 • Hong Liu, Jeff Z. HaoChen, Adrien Gaidon, Tengyu Ma
Third, inspired by the theoretical insights, we devise a re-weighted regularization technique that consistently improves the SSL representation quality on imbalanced datasets with several evaluation criteria, closing the small gap between balanced and imbalanced datasets with the same number of examples.
Ranked #9 on Long-tail Learning on CIFAR-10-LT (ρ=100)
no code implementations • 20 Oct 2021 • Bei Yang, Jie Gu, Ke Liu, Xiaoxiao Xu, Renjun Xu, Qinghui Sun, Hong Liu
User Modeling plays an essential role in industry.
1 code implementation • 29 Oct 2021 • Nobukatsu Kajiura, Hong Liu, Shin'ichi Satoh
This framework consists of three key components, i. e., a pseudo-edge generator, a pseudo-map generator, and an uncertainty-aware refinement module.
1 code implementation • CVPR 2022 • Wenhao Li, Hong Liu, Hao Tang, Pichao Wang, Luc van Gool
Estimating 3D human poses from monocular videos is a challenging task due to depth ambiguity and self-occlusion.
Ranked #22 on 3D Human Pose Estimation on MPI-INF-3DHP
1 code implementation • 5 Dec 2021 • Tao Wang, Hong Liu, Pinhao Song, Tianyu Guo, Wei Shi
Therefore, we propose a transformer-based Pose-guided Feature Disentangling (PFD) method by utilizing pose information to clearly disentangle semantic components (e. g. human body or joint parts) and selectively match non-occluded parts correspondingly.
1 code implementation • 7 Dec 2021 • Tianyu Guo, Hong Liu, Zhan Chen, Mengyuan Liu, Tao Wang, Runwei Ding
In this paper, to make better use of the movement patterns introduced by extreme augmentations, a Contrastive Learning framework utilizing Abundant Information Mining for self-supervised action Representation (AimCLR) is proposed.
1 code implementation • 14 Dec 2021 • Yidi Li, Hong Liu, Hao Tang
Multi-modal fusion is proven to be an effective method to improve the accuracy and robustness of speaker tracking, especially in complex scenarios.
3 code implementations • 31 Dec 2021 • Deng-Ping Fan, Ziling Huang, Peng Zheng, Hong Liu, Xuebin Qin, Luc van Gool
Besides, we elaborate comprehensive experiments on the existing 19 cutting-edge models.
no code implementations • 25 Jan 2022 • Xuxin Chen, Ximin Wang, Ke Zhang, Kar-Ming Fung, Theresa C. Thai, Kathleen Moore, Robert S. Mannel, Hong Liu, Bin Zheng, Yuchen Qiu
This study aims to develop a novel computer-aided diagnosis (CAD) scheme for mammographic breast mass classification using semi-supervised learning.
1 code implementation • 4 Mar 2022 • Hong Liu, Dong Wei, Donghuan Lu, Yuexiang Li, Kai Ma, Liansheng Wang, Yefeng Zheng
To the best of our knowledge, this is the first study that attempts 3D retinal layer segmentation in volumetric OCT images based on CNNs.
no code implementations • 15 Mar 2022 • Hong Liu, Wen-Dong Xu, Zi-Hao Shang, Xiang-Dong Wang, Hai-Yan Zhou, Ke-Wen Ma, Huan Zhou, Jia-Lin Qi, Jia-Rui Jiang, Li-Lan Tan, Hui-Min Zeng, Hui-Juan Cai, Kuan-Song Wang, Yue-Liang Qian
A weakly supervised learning framework based on discriminative patch selecting and multi-instance learning was proposed for breast cancer molecular subtype prediction from H&E WSIs.
2 code implementations • 13 Apr 2022 • Hong Liu, Yucheng Cai, Zhijian Ou, Yi Huang, Junlan Feng
Recently, Transformer based pretrained language models (PLMs), such as GPT2 and T5, have been leveraged to build generative task-oriented dialog (TOD) systems.
1 code implementation • 25 May 2022 • Linhui Dai, Hong Liu, Hao Tang, Zhiwei Wu, Pinhao Song
Comprehensive experiments on several challenging datasets show that our method achieves superior performance on the AOOD task.
1 code implementation • 13 Jun 2022 • Wenhao Li, Hong Liu, Tianyu Guo, Runwei Ding, Hao Tang
To the best of our knowledge, this is the first MLP-Like architecture for 3D human pose estimation in a single frame and a video sequence.
Ranked #53 on 3D Human Pose Estimation on Human3.6M
no code implementations • 21 Jun 2022 • Xuxin Chen, Ke Zhang, Neman Abdoli, Patrik W. Gilley, Ximin Wang, Hong Liu, Bin Zheng, Yuchen Qiu
For this purpose, we employ local Transformer blocks to separately learn patch relationships within four mammograms acquired from two-view (CC/MLO) of two-side (right/left) breasts.
1 code implementation • 27 Jun 2022 • Zhan Chen, Sicheng Li, Bing Yang, Qinghan Li, Hong Liu
To solve this problem, we present a multi-scale spatial graph convolution (MS-GC) module and a multi-scale temporal graph convolution (MT-GC) module to enrich the receptive field of the model in spatial and temporal dimensions.
1 code implementation • 6 Jul 2022 • Zhijian Ou, Junlan Feng, Juanzi Li, Yakun Li, Hong Liu, Hao Peng, Yi Huang, Jiangjiang Zhao
A challenge on Semi-Supervised and Reinforced Task-Oriented Dialog Systems, Co-located with EMNLP2022 SereTOD Workshop.
1 code implementation • 7 Jul 2022 • Zhan Chen, Hong Liu, Tianyu Guo, Zhengyan Chen, Pinhao Song, Hao Tang
First, SkeleMix utilizes the topological information of skeleton data to mix two skeleton sequences by randomly combing the cropped skeleton fragments (the trimmed view) with the remaining skeleton sequences (the truncated view).
1 code implementation • 14 Jul 2022 • Yuankai Wu, Hongyu Yang, Yi Lin, Hong Liu
By this means, STPN allows cross-talk of spatial and temporal factors for modeling delay propagation.
1 code implementation • SIGDIAL (ACL) 2022 • Yucheng Cai, Hong Liu, Zhijian Ou, Yi Huang, Junlan Feng
In this paper, we propose to apply JSA to semi-supervised learning of the latent state TOD models, which is referred to as JSA-TOD.
1 code implementation • 25 Aug 2022 • Jianbing Wu, Hong Liu, Wei Shi, Hao Tang, Jingwen Guo
To mitigate the resolution degradation issue and mine identity-sensitive cues from human faces, we propose to restore the missing facial details using prior facial knowledge, which is then propagated to a smaller network.
1 code implementation • 27 Sep 2022 • Hong Liu, Hao Peng, Zhijian Ou, Juanzi Li, Yi Huang, Junlan Feng
Recently, there have merged a class of task-oriented dialogue (TOD) datasets collected through Wizard-of-Oz simulated games.
no code implementations • 13 Oct 2022 • Hong Liu, Zhijian Ou, Yi Huang, Junlan Feng
Recently, there has been progress in supervised funetuning pretrained GPT-2 to build end-to-end task-oriented dialog (TOD) systems.
1 code implementation • 17 Oct 2022 • Hong Liu, Yucheng Cai, Zhijian Ou, Yi Huang, Junlan Feng
Second, an important ingredient in a US is that the user goal can be effectively incorporated and tracked; but how to flexibly integrate goal state tracking and develop an end-to-end trainable US for multi-domains has remained to be a challenge.
1 code implementation • 18 Oct 2022 • Yiming Li, Zhifang Guo, Zhirong Ye, Xiangdong Wang, Hong Liu, Yueliang Qian, Rui Tao, Long Yan, Kazushige Ouchi
For the frame-wise model, the ICT-TOSHIBA system of DCASE 2021 Task 4 is used.
no code implementations • 25 Oct 2022 • Hong Liu, Sang Michael Xie, Zhiyuan Li, Tengyu Ma
Toward understanding this implicit bias, we prove that SGD with standard mini-batch noise implicitly prefers flatter minima in language models, and empirically observe a strong correlation between flatness and downstream performance among models with the same minimal pre-training loss.
1 code implementation • 14 Nov 2022 • Zelong Zeng, Fan Yang, Hong Liu, Shin'ichi Satoh
However, this type of method normally ignores the crucial knowledge hidden in the data (e. g., intra-class information variation), which is harmful to the generalization of the trained model.
no code implementations • 28 Nov 2022 • Yuzhou Zhuang, Hong Liu, Enmin Song, Coskun Cetinkaya, Chih-Cheng Hung
We adopt two data augmentation methods for effectively learning the semantic information and generating realistic target domain scans: generative and online data augmentation.
1 code implementation • 16 Dec 2022 • Yizhou Dang, Enneng Yang, Guibing Guo, Linying Jiang, Xingwei Wang, Xiaoxiao Xu, Qinghui Sun, Hong Liu
However, we observe that the time interval in a sequence may vary significantly different, and thus result in the ineffectiveness of user modeling due to the issue of \emph{preference drift}.
no code implementations • ICCV 2023 • Jianbing Wu, Hong Liu, Yuxin Su, Wei Shi, Hao Tang
Owing to the large distribution gap between the heterogeneous data in Visible-Infrared Person Re-identification (VI Re-ID), we point out that existing paradigms often suffer from the inter-modal semantic misalignment issue and thus fail to align and compare local details properly.
1 code implementation • 3 Feb 2023 • Coen de Vente, Koenraad A. Vermeer, Nicolas Jaccard, He Wang, Hongyi Sun, Firas Khader, Daniel Truhn, Temirgali Aimyshev, Yerkebulan Zhanibekuly, Tien-Dung Le, Adrian Galdran, Miguel Ángel González Ballester, Gustavo Carneiro, Devika R G, Hrishikesh P S, Densen Puthussery, Hong Liu, Zekang Yang, Satoshi Kondo, Satoshi Kasai, Edward Wang, Ashritha Durvasula, Jónathan Heras, Miguel Ángel Zapata, Teresa Araújo, Guilherme Aresta, Hrvoje Bogunović, Mustafa Arikan, Yeong Chan Lee, Hyun Bin Cho, Yoon Ho Choi, Abdul Qayyum, Imran Razzak, Bram van Ginneken, Hans G. Lemij, Clara I. Sánchez
Artificial intelligence (AI) can be used to analyze color fundus photographs (CFPs) in a cost-effective manner, making glaucoma screening more accessible.
1 code implementation • 20 Feb 2023 • Jialun Cai, Hong Liu, Runwei Ding, Wenhao Li, Jianbing Wu, Miaoju Ban
3D human pose estimation errors would propagate along the human body topology and accumulate at the end joints of limbs.
Ranked #34 on 3D Human Pose Estimation on MPI-INF-3DHP (AUC metric)
no code implementations • 3 Mar 2023 • Tao Wang, Mengyuan Liu, Hong Liu, Wenhao Li, Miaoju Ban, Tuanyu Guo, Yidi Li
In this paper, different from most previous works that discard the occluded region, we propose a Feature Completion Transformer (FCFormer) to implicitly complement the semantic information of occluded parts in the feature space.
1 code implementation • 9 Mar 2023 • Hong Liu, Dong Wei, Donghuan Lu, Jinghan Sun, Liansheng Wang, Yefeng Zheng
In the first stage, a multimodal masked autoencoder (M3AE) is proposed, where both random modalities (i. e., modality dropout) and random patches of the remaining modalities are masked for a reconstruction task, for self-supervised learning of robust multimodal representations against missing modalities.
1 code implementation • 10 Mar 2023 • Yingxuan You, Hong Liu, Xia Li, Wenhao Li, Ti Wang, Runwei Ding
3D human mesh recovery from a 2D pose plays an important role in various applications.
Ranked #146 on 3D Human Pose Estimation on Human3.6M
1 code implementation • 29 Mar 2023 • Xingbin Liu, Huafeng Kuang, Hong Liu, Xianming Lin, Yongjian Wu, Rongrong Ji
Deep neural networks have been applied in many computer vision tasks and achieved state-of-the-art performance.
1 code implementation • journal 2023 • Zizhen Zhang, Hong Liu, Mengchu Zhou, Jiahai Wang
This brings in a dynamic version of the traveling salesman problem (DTSP), which takes into account the information of real-time traffic and customer requests.
1 code implementation • 27 Apr 2023 • Ti Wang, Hong Liu, Runwei Ding, Wenhao Li, Yingxuan You, Xia Li
Despite substantial progress in 3D human pose estimation from a single-view image, prior works rarely explore global and local correlations, leading to insufficient learning of human skeleton representations.
1 code implementation • 7 May 2023 • Sheng Yan, Yang Liu, Haoqiang Wang, Xin Du, Mengyuan Liu, Hong Liu
On the latest HumanML3D dataset, we achieve a recall of 62. 9% for motion retrieval and 71. 5% for text retrieval (both based on R@10).
1 code implementation • 22 May 2023 • Hong Liu, Zhaobiao Lv, Zhijian Ou, Wenbo Zhao, Qing Xiao
Energy-based language models (ELMs) parameterize an unnormalized distribution for natural sentences and are radically different from popular autoregressive language models (ALMs).
1 code implementation • 22 May 2023 • Yucheng Cai, Hong Liu, Zhijian Ou, Yi Huang, Junlan Feng
Most existing task-oriented dialog (TOD) systems track dialog states in terms of slots and values and use them to query a database to get relevant knowledge to generate responses.
3 code implementations • 23 May 2023 • Hong Liu, Zhiyuan Li, David Hall, Percy Liang, Tengyu Ma
Given the massive cost of language model pre-training, a non-trivial improvement of the optimization algorithm would lead to a material reduction on the time and cost of training.
no code implementations • 1 Jun 2023 • Linhui Dai, Hong Liu, Pinhao Song, Hao Tang, Runwei Ding, Shengquan Li
The key to addressing these challenges is to focus the model on obtaining more discriminative information.
1 code implementation • CVPR 2023 • Zhenglin Zhou, Huaxia Li, Hong Liu, Nanyang Wang, Gang Yu, Rongrong Ji
To solve this problem, we propose a Self-adapTive Ambiguity Reduction (STAR) loss by exploiting the properties of semantic ambiguity.
Ranked #1 on Face Alignment on 300W
no code implementations • 12 Jun 2023 • Hong Liu
In this paper, we propose a novel unsupervised hashing method, termed Sparsity-Induced Generative Adversarial Hashing (SiGAH), to encode large-scale high-dimensional features into binary codes, which well solves the two problems through a generative adversarial training framework.
no code implementations • 13 Jun 2023 • Hong Liu
In this paper, we delve into the essential components of adversarial training which is a pioneering defense technique against adversarial attacks.
no code implementations • ICCV 2023 • Jingwen Guo, Hong Liu, Shitong Sun, Tianyu Guo, Min Zhang, Chenyang Si
Existing skeleton-based action recognition methods typically follow a centralized learning paradigm, which can pose privacy concerns when exposing human-related videos.
1 code implementation • 25 Jun 2023 • Linhui Dai, Hong Liu, Pinhao Song, Mengyuan Liu
Firstly, a real-time UIE method is employed to generate enhanced images, which can improve the visibility of objects in low-contrast areas.
1 code implementation • 15 Jul 2023 • Tianyu Guo, Mengyuan Liu, Hong Liu, Wenhao Li, Jingwen Guo, Tao Wang, Yidi Li
Considering the instance-level discriminative ability, contrastive learning methods, including MoCo and SimCLR, have been adapted from the original image representation learning task to solve the self-supervised skeleton-based action recognition task.
no code implementations • 18 Jul 2023 • Jinghan Sun, Dong Wei, Zhe Xu, Donghuan Lu, Hong Liu, Liansheng Wang, Yefeng Zheng
Inversely, we also use the prediction of the vision detection model for abnormality-guided pseudo classification label refinement (APCLR) in the auxiliary report classification task, and propose a co-evolution strategy where the vision and report models mutually promote each other with RPDLR and APCLR performed alternatively.
no code implementations • 19 Jul 2023 • Qifang Zhao, Tianyu Li, Meng Du, Yu Jiang, Qinghui Sun, Zhongyao Wang, Hong Liu, Huan Xu
When doing private domain marketing with cloud services, the merchants usually have to purchase different machine learning models for the multiple marketing purposes, leading to a very high cost.
1 code implementation • 29 Jul 2023 • Ke Feng, Dahai Liu, Yongxin Liu, Hong Liu, Houbing Song
The current National Airspace System (NAS) is reaching capacity due to increased air traffic, and is based on outdated pre-tactical planning.
1 code implementation • ICCV 2023 • Yingxuan You, Hong Liu, Ti Wang, Wenhao Li, Runwei Ding, Xia Li
Despite significant progress in single image-based 3D human mesh recovery, accurately and smoothly recovering 3D human motion from a video remains challenging.
no code implementations • 22 Aug 2023 • Hualei Wang, Jianguo Mao, Zhifang Guo, Jiarui Wan, Hong Liu, Xiangdong Wang
Recently, the ability of language models (LMs) has attracted increasing attention in visual cross-modality.
no code implementations • 23 Aug 2023 • Zhifang Guo, Jianguo Mao, Rui Tao, Long Yan, Kazushige Ouchi, Hong Liu, Xiangdong Wang
To address this issue, we propose a novel model that enhances the controllability of existing pre-trained text-to-audio models by incorporating additional conditions including content (timestamp) and style (pitch contour and energy contour) as supplements to the text.
1 code implementation • 27 Aug 2023 • Peini Guo, Hong Liu, Jianbing Wu, Guoquan Wang, Tao Wang
Despite recent progress in CC-ReID, existing approaches are still hindered by the interference of clothing variations since they lack effective constraints to keep the model consistently focused on clothing-irrelevant regions.
no code implementations • 15 Sep 2023 • Yiming Li, Xiangdong Wang, Hong Liu
Contrastive Language-Audio Pretraining (CLAP) is pre-trained to associate audio features with human language, making it a natural zero-shot classifier to recognize unseen sound categories.
no code implementations • 15 Sep 2023 • Yiming Li, Xiangdong Wang, Hong Liu, Rui Tao, Long Yan, Kazushige Ouchi
Then, the local consistency is adopted to encourage the model to leverage local features for frame-level predictions, and the global consistency is applied to force features to align with global prototypes through a specially designed contrastive loss.
1 code implementation • 20 Sep 2023 • Chen Jiang, Hong Liu, Xuzheng Yu, Qing Wang, Yuan Cheng, Jia Xu, Zhongyi Liu, Qingpei Guo, Wei Chu, Ming Yang, Yuan Qi
We thereby present a new Triplet Partial Margin Contrastive Learning (TPM-CL) module to construct partial order triplet samples by automatically generating fine-grained hard negatives for matched text-video pairs.
Ranked #4 on Video Retrieval on MSR-VTT-1kA
1 code implementation • 17 Nov 2023 • Hong Liu, Yucheng Cai, Yuan Zhou, Zhijian Ou, Yi Huang, Junlan Feng
Inspired by the recently emerging prompt tuning method that performs well on dialog systems, we propose to use the prompt pool method, where we maintain a pool of key-value paired prompts and select prompts from the pool according to the distance between the dialog history and the prompt keys.
1 code implementation • 20 Nov 2023 • Wenhao Li, Mengyuan Liu, Hong Liu, Pichao Wang, Jialun Cai, Nicu Sebe
Transformers have been successfully applied in the field of video-based 3D human pose estimation.
1 code implementation • 4 Dec 2023 • Hong Liu, Dong Wei, Donghuan Lu, Xiaoying Tang, Liansheng Wang, Yefeng Zheng
Experiments on a synthetic dataset and three public clinical datasets show that our framework can effectively align the B-scans for potential motion correction, and achieves superior performance to state-of-the-art 2D deep learning methods in terms of both layer segmentation accuracy and cross-B-scan 3D continuity in both fully and semi-supervised settings, thus offering more clinical values than previous works.
1 code implementation • 20 Dec 2023 • Yuhao Yi, Ronghui You, Hong Liu, Changxin Liu, YuAn Wang, Jiancheng Lv
Our analysis show that constant approximations to the 1-center and 1-mean clustering problems with outliers provide near-optimal resilient aggregators for metric-based criteria, which have been proven to be crucial in the homogeneous and heterogeneous cases respectively.
1 code implementation • 31 Dec 2023 • Qifang Zhao, Weidong Ren, Tianyu Li, Xiaoxiao Xu, Hong Liu
We introduce \textit{GraphGPT}, a novel model for Graph learning by self-supervised Generative Pre-training Transformers.
no code implementations • 4 Feb 2024 • Mengyuan Liu, Chen Chen, Songtao Wu, Fanyang Meng, Hong Liu
Recognizing interactive actions, including hand-to-hand interaction and human-to-human interaction, has attracted increasing attention for various applications in the field of video analysis and human-robot interaction.
no code implementations • 4 Feb 2024 • Ti Wang, Mengyuan Liu, Hong Liu, Bin Ren, Yingxuan You, Wenhao Li, Nicu Sebe, Xia Li
We observe that previous optimization-based methods commonly rely on projection constraint, which only ensures alignment in 2D space, potentially leading to the overfitting problem.
1 code implementation • 11 Feb 2024 • Mengmei Zhang, Mingwei Sun, Peng Wang, Shen Fan, Yanhu Mo, Xiaoxiao Xu, Hong Liu, Cheng Yang, Chuan Shi
Large language models (LLMs) like ChatGPT, exhibit powerful zero-shot and instruction-following capabilities, have catalyzed a revolutionary transformation across diverse fields, especially for open-ended tasks.
no code implementations • 20 Feb 2024 • Zhiyuan Li, Hong Liu, Denny Zhou, Tengyu Ma
Given input length $n$, previous works have shown that constant-depth transformers with finite precision $\mathsf{poly}(n)$ embedding size can only solve problems in $\mathsf{TC}^0$ without CoT.
no code implementations • 4 Mar 2024 • Yue Yang, Yuqi Lin, Hong Liu, Wenqi Shao, Runjian Chen, Hailong Shang, Yu Wang, Yu Qiao, Kaipeng Zhang, Ping Luo
We call for increased attention to the potential and risks of implicit prompts in the T2I community and further investigation into the capabilities and impacts of implicit prompts, advocating for a balanced approach that harnesses their benefits while mitigating their risks.
no code implementations • 13 Mar 2024 • Peini Guo, Mengyuan Liu, Hong Liu, Ruijia Fan, Guoquan Wang, Bin He
In addition, a Multi-scale Constraint Block (MCB) is designed, which extracts fine-grained identity-related features and effectively transfers cloth-irrelevant knowledge.
no code implementations • 14 Mar 2024 • Hao Zhang, Wenqi Shao, Hong Liu, Yongqiang Ma, Ping Luo, Yu Qiao, Kaipeng Zhang
To bridge this gap, we introduce AVIBench, a framework designed to analyze the robustness of LVLMs when facing various adversarial visual-instructions (AVIs), including four types of image-based AVIs, ten types of text-based AVIs, and nine types of content bias AVIs (such as gender, violence, cultural, and racial biases, among others).
no code implementations • 14 Mar 2024 • Hong Liu, Haosen Yang, Paul J. van Diest, Josien P. W. Pluim, Mitko Veta
In particular, our model outperforms SAM by 4. 1 and 2. 5 percent points on a ductal carcinoma in situ (DCIS) segmentation tasks and breast cancer metastasis segmentation task (CAMELYON16 dataset).
1 code implementation • 18 Mar 2024 • Qian Dai, Dong Wei, Hong Liu, Jinghan Sun, Liansheng Wang, Yefeng Zheng
In practice, it is not uncommon that some FL participants only possess a subset of the complete imaging modalities, posing inter-modal heterogeneity as a challenge to effectively training a global model on all participants' data.
1 code implementation • 21 Apr 2024 • Sheng Yan, Mengyuan Liu, Yong Wang, Yang Liu, Chen Chen, Hong Liu
In this paper, we address the unexplored question of temporal sentence localization in human motions (TSLM), aiming to locate a target moment from a 3D human motion that semantically corresponds to a text query.
no code implementations • COLING 2022 • Jianguo Mao, Jiyuan Zhang, Zengfeng Zeng, Weihua Peng, Wenbin Jiang, Xiangdong Wang, Hong Liu, Yajuan Lyu
It then performs dynamic reasoning based on the hierarchical representations of evidences to solve complex biomedical problems.
no code implementations • NAACL 2022 • Jianguo Mao, Wenbin Jiang, Xiangdong Wang, Zhifan Feng, Yajuan Lyu, Hong Liu, Yong Zhu
Then, it performs multistep reasoning for better answer decision between the representations of the question and the video, and dynamically integrate the reasoning results.
1 code implementation • ECCV 2020 • Xinshuai Dong, Hong Liu, Rongrong Ji, Liujuan Cao, Qixiang Ye, Jianzhuang Liu, Qi Tian
On the contrary, a discriminative classifier only models the conditional distribution of labels given inputs, but benefits from effective optimization owing to its succinct structure.