no code implementations • CVPR 2015 • Pei-Lun Hsieh, Chongyang Ma, Jihun Yu, Hao Li
We introduce a realtime facial tracking system specifically designed for performance capture in unconstrained settings using a consumer-level RGB-D sensor.
no code implementations • CVPR 2016 • Lingyu Wei, Qi-Xing Huang, Duygu Ceylan, Etienne Vouga, Hao Li
We propose a deep learning approach for finding dense correspondences between 3D scans of people.
no code implementations • 10 Apr 2016 • Shunsuke Saito, Tianye Li, Hao Li
We adopt a state-of-the-art regression-based facial tracking framework with segmented face images as training, and demonstrate accurate and uninterrupted facial performance capture in the presence of extreme occlusion and even side views.
no code implementations • 11 Apr 2016 • Ruizhe Wang, Lingyu Wei, Etienne Vouga, Qi-Xing Huang, Duygu Ceylan, Gerard Medioni, Hao Li
We present an end-to-end system for reconstructing complete watertight and textured models of moving subjects such as clothed humans and animals, using only three or four handheld sensors.
21 code implementations • 31 Aug 2016 • Hao Li, Asim Kadav, Igor Durdanovic, Hanan Samet, Hans Peter Graf
However, magnitude-based pruning of weights reduces a significant number of parameters from the fully connected layers and may not adequately reduce the computation costs in the convolutional layers due to irregular sparsity in the pruned networks.
Ranked #1 on Network Pruning on ImageNet
no code implementations • 20 Sep 2016 • Junxuan Chen, Baigui Sun, Hao Li, Hongtao Lu, Xian-Sheng Hua
Click through rate (CTR) prediction of image ads is the core task of online display advertising systems, and logistic regression (LR) has been frequently applied as the prediction model.
1 code implementation • 21 Sep 2016 • Samuli Laine, Tero Karras, Timo Aila, Antti Herva, Shunsuke Saito, Ronald Yu, Hao Li, Jaakko Lehtinen
We present a real-time deep learning framework for video-based facial performance capture -- the dense 3D tracking of an actor's face given a monocular video.
1 code implementation • CVPR 2017 • Chao Yang, Xin Lu, Zhe Lin, Eli Shechtman, Oliver Wang, Hao Li
Recent advances in deep learning have shown exciting promise in filling large holes in natural images with semantically plausible and context aware details, impacting fundamental image manipulation tasks such as object removal.
1 code implementation • CVPR 2017 • Shunsuke Saito, Lingyu Wei, Liwen Hu, Koki Nagano, Hao Li
We present a data-driven inference method that can synthesize a photorealistic texture map of a complete 3D face model given a partial 2D view of a person in the wild.
no code implementations • 18 Feb 2017 • Luo Jiang, Juyong Zhang, Bailin Deng, Hao Li, Ligang Liu
3D face reconstruction from a single image is a classical and challenging problem, with wide applications in many areas.
3 code implementations • 13 Apr 2017 • Sitao Xiang, Hao Li
We further demonstrate the stability of WN on a 21-layer ResNet trained with the CelebA data set.
no code implementations • NeurIPS 2017 • Hao Li, Soham De, Zheng Xu, Christoph Studer, Hanan Samet, Tom Goldstein
Currently, deep neural networks are deployed on low-power portable devices by first training a full-precision model using powerful hardware, and then deriving a corresponding low-precision model for efficient inference on such systems.
no code implementations • ICML 2017 • Zheng Xu, Gavin Taylor, Hao Li, Mario Figueiredo, Xiaoming Yuan, Tom Goldstein
The alternating direction method of multipliers (ADMM) is commonly used for distributed model fitting problems, but its performance and reliability depend strongly on user-defined penalty parameters.
1 code implementation • ICLR 2018 • Zimo Li, Yi Zhou, Shuangjiu Xiao, Chong He, Zeng Huang, Hao Li
We present a real-time method for synthesizing highly complex human motions using a novel training regime we call the auto-conditioned Recurrent Neural Network (acRNN).
no code implementations • 22 Jul 2017 • Julian Zilly, Amit Boyarski, Micael Carvalho, Amir Atapour Abarghouei, Konstantinos Amplianitis, Aleksandr Krasnov, Massimiliano Mancini, Hernán Gonzalez, Riccardo Spezialetti, Carlos Sampedro Pérez, Hao Li
Reviewing this project with modern eyes provides us with the opportunity to reflect on several issues, relevant now as then to the field of computer vision and research in general, that go beyond the technical aspects of the work.
no code implementations • 24 Jul 2017 • Cong Leng, Hao Li, Shenghuo Zhu, Rong Jin
Although deep learning models are highly effective for various learning tasks, their high computational costs prohibit the deployment to scenarios where either memory or computational resources are limited.
no code implementations • 28 Jul 2017 • Boyuan Pan, Hao Li, Zhou Zhao, Bin Cao, Deng Cai, Xiaofei He
Machine comprehension(MC) style question answering is a representative problem in natural language processing.
Ranked #37 on Question Answering on TriviaQA
no code implementations • ICCV 2017 • Ronald Yu, Shunsuke Saito, Haoxiang Li, Duygu Ceylan, Hao Li
To train such a network, we generate a massive dataset of synthetic faces with dense labels using renderings of a morphable face model with variations in pose, expressions, lighting, and occlusions.
no code implementations • 4 Sep 2017 • Shasha Xia, Hao Li, Xueliang Zhang
In this paper, we use the optimal ratio mask as the training target of the deep neural network (DNN) for speech separation.
no code implementations • ICCV 2017 • Kyle Olszewski, Zimo Li, Chao Yang, Yi Zhou, Ronald Yu, Zeng Huang, Sitao Xiang, Shunsuke Saito, Pushmeet Kohli, Hao Li
By retargeting the PCA expression geometry from the source, as well as using the newly inferred texture, we can both animate the face and perform video face replacement on the source video using the target appearance.
no code implementations • 6 Oct 2017 • Hao Li, Zhijian Liu
This Chapter consists of: i) Comparative studies on varieties of machine learning models (artificial neural networks (ANNs), support vector machine (SVM) and extreme learning machine (ELM)) to predict the performances of SWHs; ii) Development of an ANN-based software to assist the quick prediction and iii) Introduction of a computational HTS method to design a high-performance SWH system.
9 code implementations • SIGGRAPH Asia 2017 • Tianye Li, Timo Bolkart, Michael J. Black, Hao Li, Javier Romero
FLAME is low-dimensional but more expressive than the FaceWarehouse model and the Basel Face Model.
Ranked #3 on Face Alignment on FaceScape
no code implementations • 1 Nov 2017 • Boyuan Pan, Hao Li, Zhou Zhao, Deng Cai, Xiaofei He
In this paper, we propose a novel neural network system that consists a Demand Optimization Model based on a passage-attention neural machine translation and a Reader Model that can find the answer given the optimized question.
no code implementations • 15 Nov 2017 • Guowei Wan, Xiaolong Yang, Renlan Cai, Hao Li, Hao Wang, Shiyu Song
We present a robust and precise localization system that achieves centimeter-level localization accuracy in disparate city scenes.
no code implementations • ECCV 2018 • Yuhang Song, Chao Yang, Zhe Lin, Xiaofeng Liu, Qin Huang, Hao Li, C. -C. Jay Kuo
We study the task of image inpainting, which is to fill in the missing region of an incomplete image with plausible contents.
11 code implementations • ICLR 2018 • Hao Li, Zheng Xu, Gavin Taylor, Christoph Studer, Tom Goldstein
Neural network training relies on our ability to find "good" minimizers of highly non-convex loss functions.
no code implementations • 2 Jan 2018 • Liuyuan Deng, Ming Yang, Hao Li, Tianyi Li, Bing Hu, Chunxiang Wang
Finally, an RDC based semantic segmentation model is built; the model is trained for real-world surround view images through a multi-task learning architecture by combining real-world images with transformed images.
no code implementations • 3 Mar 2018 • Zhehuai Chen, Qi Liu, Hao Li, Kai Yu
Finally, modules are integrated into an acousticsto-word model (A2W) and jointly optimized using acoustic data to retain the advantage of sequence modeling.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
no code implementations • CVPR 2018 • Tao Yu, Zerong Zheng, Kaiwen Guo, Jianhui Zhao, Qionghai Dai, Hao Li, Gerard Pons-Moll, Yebin Liu
We further propose a joint motion tracking method based on the double layer representation to enable robust and fast motion tracking performance.
no code implementations • 19 May 2018 • Qi Qian, Shenghuo Zhu, Jiasheng Tang, Rong Jin, Baigui Sun, Hao Li
Hence, we propose to learn the model and the adversarial distribution simultaneously with the stochastic algorithm for efficiency.
no code implementations • 21 May 2018 • Sitao Xiang, Hao Li
Deep learning-based style transfer between images has recently become a popular area of research.
no code implementations • CVPR 2018 • Qi Qian, Jiasheng Tang, Hao Li, Shenghuo Zhu, Rong Jin
Furthermore, we can show that the metric is learned from latent examples only, but it can preserve the large margin property even for the original data.
no code implementations • CVPR 2018 • Loc Huynh, Weikai Chen, Shunsuke Saito, Jun Xing, Koki Nagano, Andrew Jones, Paul Debevec, Hao Li
We present a learning-based approach for synthesizing facial geometry at medium and fine scales from diffusely-lit facial texture maps.
no code implementations • ACL 2018 • Hao Li, Wei Lu
We report an empirical study on the task of negation scope extraction given the negation cue.
no code implementations • ECCV 2018 • Zerong Zheng, Tao Yu, Hao Li, Kaiwen Guo, Qionghai Dai, Lu Fang, Yebin Liu
We propose a light-weight and highly robust real-time human performance capture method based on a single depth camera and sparse inertial measurement units (IMUs).
no code implementations • ECCV 2018 • Zeng Huang, Tianye Li, Weikai Chen, Yajie Zhao, Jun Xing, Chloe LeGendre, Linjie Luo, Chongyang Ma, Hao Li
We present a deep learning-based volumetric capture approach for performance capture using a passive and highly sparse multi-view capture system.
no code implementations • ECCV 2018 • Lingyu Wei, Liwen Hu, Vladimir Kim, Ersin Yumer, Hao Li
To handle the diversity of hairstyles and its appearance complexity, we disentangle hair structure, color, and illumination properties using a sequential GAN architecture and a semi-supervised training approach.
no code implementations • 1 Nov 2018 • Hao Li, Yang Wang, Xinyu Liu, Zhichao Sheng, Si Wei
We propose a nested recurrent neural network (nested RNN) model for English spelling error correction and generate pseudo data based on phonetic similarity to train it.
no code implementations • 15 Nov 2018 • Baichuan Yuan, Hao Li, Andrea L. Bertozzi, P. Jeffrey Brantingham, Mason A. Porter
There is often latent network structure in spatial and temporal data and the tools of network analysis can yield fascinating insights into such data.
no code implementations • 11 Dec 2018 • Weikai Chen, Xiaoguang Han, Guanbin Li, Chao Chen, Jun Xing, Yajie Zhao, Hao Li
Three-dimensional object recognition has recently achieved great progress thanks to the development of effective point cloud-based learning frameworks, such as PointNet and its extensions.
5 code implementations • CVPR 2019 • Yi Zhou, Connelly Barnes, Jingwan Lu, Jimei Yang, Hao Li
Thus, widely used representations such as quaternions and Euler angles are discontinuous and difficult for neural networks to learn.
1 code implementation • CVPR 2019 • Ryota Natsume, Shunsuke Saito, Zeng Huang, Weikai Chen, Chongyang Ma, Hao Li, Shigeo Morishima
The synthesized silhouettes which are the most consistent with the input segmentation are fed into a deep visual hull algorithm for robust 3D shape prediction.
no code implementations • 17 Jan 2019 • Shichen Liu, Weikai Chen, Tianye Li, Hao Li
We also show that our soft rasterizer can achieve comparable results to the cutting-edge supervised learning method and in various cases even better ones, especially for real-world data.
no code implementations • 3 Mar 2019 • Jun Li, Xiaozhu Lin, Hui Che, Hao Li, Xiaohua Qian
To alleviate these problems, we propose a probabilistic-map-guided bi-directional recurrent UNet (PBR-UNet) architecture, which fuses intra-slice information and inter-slice probabilistic maps into a local 3D hybrid regularization scheme, which is followed by bi-directional recurrent network optimization.
no code implementations • 3 Mar 2019 • Hao Li, Jun Li, Xiaozhu Lin, Xiaohua Qian
The irregular geometry and high inter-slice variability in computerized tomography (CT) scans of the human pancreas make an accurate segmentation of this crucial organ a challenging task for existing data-driven deep learning methods.
2 code implementations • ICCV 2019 • Shichen Liu, Tianye Li, Weikai Chen, Hao Li
Rendering bridges the gap between 2D vision and 3D scenes by simulating the physical process of image formation.
Ranked #1 on 3D Object Reconstruction on ShapeNet
1 code implementation • ICCV 2019 • Kyle Olszewski, Sergey Tulyakov, Oliver Woodford, Hao Li, Linjie Luo
We propose a novel approach to performing fine-grained 3D manipulation of image content via a convolutional neural network, which we call the Transformable Bottleneck Network (TBN).
no code implementations • 19 Apr 2019 • Honglin Chen, Hao Li, Alexander Song, Matt Haberland, Osman Akar, Adam Dhillon, Tiankuang Zhou, Andrea L. Bertozzi, P. Jeffrey Brantingham
Body-worn cameras are now commonly used for logging daily life, sports, and law enforcement activities, creating a large volume of archived footage.
1 code implementation • ICCV 2019 • Shunsuke Saito, Zeng Huang, Ryota Natsume, Shigeo Morishima, Angjoo Kanazawa, Hao Li
We introduce Pixel-aligned Implicit Function (PIFu), a highly effective implicit representation that locally aligns pixels of 2D images with the global context of their corresponding 3D object.
Ranked #1 on 3D Object Reconstruction on RenderPeople
no code implementations • ICCV 2019 • Yajie Zhao, Zeng Huang, Tianye Li, Weikai Chen, Chloe LeGendre, Xinglei Ren, Jun Xing, Ari Shapiro, Hao Li
In contrast to the previous state-of-the-art approach, our method handles even portraits with extreme perspective distortion, as we avoid the inaccurate and error-prone step of first fitting a 3D face model.
no code implementations • 26 May 2019 • Sitao Xiang, Hao Li
We propose a novel Generative Adversarial Disentanglement Network which can disentangle two complementary factors of variations when only one of them is labelled in general, and fully decompose complex anime illustrations into style and content in particular.
no code implementations • NAACL 2019 • Hao Li, Wei Lu, Pengjun Xie, Linlin Li
This paper introduces a new task {--} Chinese address parsing {--} the task of mapping Chinese addresses into semantically meaningful chunks.
no code implementations • 3 Jun 2019 • Ming Lin, Xiaomin Song, Qi Qian, Hao Li, Liang Sun, Shenghuo Zhu, Rong Jin
We validate the superiority of the proposed method in our real-time high precision positioning system against several popular state-of-the-art robust regression methods.
no code implementations • 7 Jun 2019 • Jian-Wu Lin, Hao Li
Most video surveillance systems use both RGB and infrared cameras, making it a vital technique to re-identify a person cross the RGB and infrared modalities.
Cross-Modality Person Re-identification Person Re-Identification
no code implementations • NeurIPS 2018 • Boyuan Pan, Yazheng Yang, Hao Li, Zhou Zhao, Yueting Zhuang, Deng Cai, Xiaofei He
In this paper, we transfer knowledge learned from machine comprehension to the sequence-to-sequence tasks to deepen the understanding of the text.
1 code implementation • CVPR 2020 • Qi Qian, Lei Chen, Hao Li, Rong Jin
This architecture is efficient but can suffer from the imbalance issue with respect to two aspects: the inter-class imbalance between the number of candidates from foreground and background classes and the intra-class imbalance in the hardness of background candidates, where only a few candidates are hard to be identified.
no code implementations • 29 Jul 2019 • Hao-Ran Wei, Yue Zhang, Bing Wang, Yang Yang, Hao Li, Hongqi Wang
Motivated by the development of deep convolution neural networks (DCNNs), tremendous progress has been gained in the field of aircraft detection.
1 code implementation • ACL 2019 • Boyuan Pan, Hao Li, Ziyu Yao, Deng Cai, Huan Sun
This paper investigates a new task named Conversational Question Generation (CQG) which is to generate a question based on a passage and a conversation history (i. e., previous turns of question-answer pairs).
2 code implementations • ICCV 2019 • Hao Li, Hong Zhang, Xiaojuan Qi, Ruigang Yang, Gao Huang
Adaptive inference is a promising technique to improve the computational efficiency of deep models at test time.
5 code implementations • ICCV 2019 • Qi Qian, Lei Shang, Baigui Sun, Juhua Hu, Hao Li, Rong Jin
The set of triplet constraints has to be sampled within the mini-batch.
Ranked #21 on Metric Learning on CUB-200-2011 (using extra training data)
no code implementations • IJCNLP 2019 • Hao Li, Wei Lu
In this work, we argue that both types of information (implicit and explicit structural information) are crucial for building a successful targeted sentiment analysis model.
no code implementations • NeurIPS 2019 • Shichen Liu, Shunsuke Saito, Weikai Chen, Hao Li
The representation of 3D surfaces itself is a key factor for the quality and resolution of the 3D output.
no code implementations • CVPR 2020 • Qi Qian, Juhua Hu, Hao Li
Experiments on benchmark data sets demonstrate the effectiveness of the robust deep representations.
1 code implementation • 19 Dec 2019 • Xiao Xiang Zhu, Jingliang Hu, Chunping Qiu, Yilei Shi, Jian Kang, Lichao Mou, Hossein Bagheri, Matthias Häberle, Yuansheng Hua, Rong Huang, Lloyd Hughes, Hao Li, Yao Sun, Guichen Zhang, Shiyao Han, Michael Schmitt, Yuanyuan Wang
This is especially true for an automated analysis of remote sensing images on a global scale, which enables us to address global challenges such as urbanization and climate change using state-of-the-art machine learning techniques.
BIG-bench Machine Learning Cultural Vocal Bursts Intensity Prediction +1
no code implementations • 23 Dec 2019 • Hao-Ran Wei, Yue Zhang, Zhonghan Chang, Hao Li, Hongqi Wang, Xian Sun
It is noteworthy that the objects in COCO can be regard as a special form of oriented objects with an angle of 90 degrees.
Ranked #13 on Oriented Object Detection on DOTA 1.0
no code implementations • 9 Jan 2020 • Lin Zhou, Hao-Ran Wei, Hao Li, Wenzhe Zhao, Yi Zhang, Yue Zhang
In this article, we introduce the polar coordinate system to the deep learning detector for the first time, and propose an anchor free Polar Remote Sensing Object Detector (P-RSDet), which can achieve competitive detection accuracy via uses simpler object representation model and less regression parameters.
1 code implementation • ICLR 2020 • Hao Li, Pratik Chaudhari, Hao Yang, Michael Lam, Avinash Ravichandran, Rahul Bhotika, Stefano Soatto
Our findings challenge common practices of fine-tuning and encourages deep learning practitioners to rethink the hyperparameters for fine-tuning.
1 code implementation • CVPR 2020 • Ruilong Li, Karl Bladin, Yajie Zhao, Chinmay Chinara, Owen Ingraham, Pengda Xiang, Xinglei Ren, Pratusha Prasad, Bipin Kishore, Jun Xing, Hao Li
Based on a combined data set of 4000 high resolution facial scans, we introduce a non-linear morphable face model, capable of producing multifarious face geometry of pore-level resolution, coupled with material attributes for use in physically-based rendering.
1 code implementation • 6 Apr 2020 • Hao Li, Xiaopeng Zhang, Hongkai Xiong, Qi Tian
In this paper, we propose Attribute Mix, a data augmentation strategy at attribute level to expand the fine-grained samples.
Ranked #22 on Fine-Grained Image Classification on CUB-200-2011
no code implementations • 7 Apr 2020 • Bing Bai, Guanhua Zhang, Ye Lin, Hao Li, Kun Bai, Bo Luo
Recurrent Neural Network (RNN)-based sequential recommendation is a popular approach that utilizes users' recent browsing history to predict future items.
1 code implementation • CVPR 2020 • Zeng Huang, Yuanlu Xu, Christoph Lassner, Hao Li, Tony Tung
In this paper, we propose ARCH (Animatable Reconstruction of Clothed Humans), a novel end-to-end framework for accurate reconstruction of animation-ready 3D clothed humans from a monocular image.
Ranked #3 on 3D Object Reconstruction From A Single Image on BUFF
3D Object Reconstruction From A Single Image 3D Reconstruction
1 code implementation • CVPR 2020 • Kyle Olszewski, Duygu Ceylan, Jun Xing, Jose Echevarria, Zhili Chen, Weikai Chen, Hao Li
We present an interactive approach to synthesizing realistic variations in facial hair in images, ranging from subtle edits to existing hair to the addition of complex and challenging hair in images of clean-shaven subjects.
no code implementations • 19 Apr 2020 • Hao Li, Aozhou Wu, Wen Fang, Qingqing Zhang, Mingqing Liu, Qingwen Liu, Wei Chen
The proposed approach makes the object detection much easier to be transplanted on mobile devices and reduce the burden of hardware computation.
2 code implementations • 22 Apr 2020 • Shuting He, Hao Luo, Weihua Chen, Miao Zhang, Yuqi Zhang, Fan Wang, Hao Li, Wei Jiang
Our solution is based on a strong baseline with bag of tricks (BoT-BS) proposed in person ReID.
no code implementations • 26 Apr 2020 • Sitao Xiang, Yuming Gu, Pengda Xiang, Mingming He, Koki Nagano, Haiwei Chen, Hao Li
This is achieved by a novel landmark disentanglement network (LD-Net), which predicts personalized facial landmarks that combine the identity of the target with expressions and poses from a different subject.
5 code implementations • 5 May 2020 • Andreas Lugmayr, Martin Danelljan, Radu Timofte, Namhyuk Ahn, Dongwoon Bai, Jie Cai, Yun Cao, Junyang Chen, Kaihua Cheng, SeYoung Chun, Wei Deng, Mostafa El-Khamy, Chiu Man Ho, Xiaozhong Ji, Amin Kheradmand, Gwantae Kim, Hanseok Ko, Kanghyu Lee, Jungwon Lee, Hao Li, Ziluan Liu, Zhi-Song Liu, Shuai Liu, Yunhua Lu, Zibo Meng, Pablo Navarrete Michelini, Christian Micheloni, Kalpesh Prajapati, Haoyu Ren, Yong Hyeok Seo, Wan-Chi Siu, Kyung-Ah Sohn, Ying Tai, Rao Muhammad Umer, Shuangquan Wang, Huibing Wang, Timothy Haoning Wu, Hao-Ning Wu, Biao Yang, Fuzhi Yang, Jaejun Yoo, Tongtong Zhao, Yuanbo Zhou, Haijie Zhuo, Ziyao Zong, Xueyi Zou
This paper reviews the NTIRE 2020 challenge on real world super-resolution.
no code implementations • 18 May 2020 • Yi Zhou, Jingwan Lu, Connelly Barnes, Jimei Yang, Sitao Xiang, Hao Li
We introduce a biomechanically constrained generative adversarial network that performs long-term inbetweening of human motions, conditioned on keyframe constraints.
1 code implementation • ICCV 2021 • Yuanhong Xu, Qi Qian, Hao Li, Rong Jin, Juhua Hu
To mitigate this challenge, we propose an algorithm to learn the fine-grained patterns for the target task, when only its coarse-class labels are available.
1 code implementation • NeurIPS 2020 • Yi Zhou, Chenglei Wu, Zimo Li, Chen Cao, Yuting Ye, Jason Saragih, Hao Li, Yaser Sheikh
Learning latent representations of registered meshes is useful for many 3D tasks.
no code implementations • 10 Jun 2020 • Bing Bai, Jian Liang, Guanhua Zhang, Hao Li, Kun Bai, Fei Wang
In this paper, we demonstrate that one root cause of this phenomenon is the combinatorial shortcuts, which means that, in addition to the highlighted parts, the attention weights themselves may carry extra information that could be utilized by downstream models after attention layers.
no code implementations • 11 Jun 2020 • Sitao Xiang, Hao Li
In this paper, we provide some careful analysis of certain pathological behavior of Euler angles and unit quaternions encountered in previous works related to rotation representation in neural networks.
no code implementations • 20 Jun 2020 • Yi Xu, Yuanhong Xu, Qi Qian, Hao Li, Rong Jin
Label smoothing regularization (LSR) has a great success in training deep neural networks by stochastic algorithms such as stochastic gradient descent and its variants.
2 code implementations • 24 Jun 2020 • Ming Lin, Hesen Chen, Xiuyu Sun, Qi Qian, Hao Li, Rong Jin
To address this issue, we propose a general principle for designing GPU-efficient networks based on extensive empirical studies.
no code implementations • 21 Jul 2020 • Kevin Miller, Hao Li, Andrea L. Bertozzi
We present a novel adaptation of active learning to graph-based semi-supervised learning (SSL) under non-Gaussian Bayesian models.
no code implementations • 25 Jul 2020 • Andrea L. Bertozzi, Bamdad Hosseini, Hao Li, Kevin Miller, Andrew M. Stuart
Graph-based semi-supervised regression (SSR) is the problem of estimating the value of a function on a weighted graph from its values (labels) on a small subset of the vertices.
1 code implementation • ECCV 2020 • Ruilong Li, Yuliang Xiu, Shunsuke Saito, Zeng Huang, Kyle Olszewski, Hao Li
We present the first approach to volumetric performance capture and novel-view rendering at real-time speed from monocular video, eliminating the need for expensive multi-view systems or cumbersome pre-acquisition of a personalized template model.
no code implementations • 18 Aug 2020 • Jiaman Li, Yihang Yin, Hang Chu, Yi Zhou, Tingwu Wang, Sanja Fidler, Hao Li
We also introduce new evaluation metrics for the quality of synthesized dance motions, and demonstrate that our system can outperform state-of-the-art methods.
1 code implementation • SIGKDD International Conference on Knowledge Discovery & Data Mining 2020 • Linxia Gong, Xiaochuan Feng, Dezhi Ye, Hao Li, Runze Wu, Jianrong Tao, Changjie Fan, Peng Cui
OptMatch contains an offline learning stage and an online planning stage.
no code implementations • 20 Aug 2020 • Hao Li, Ajay Ram Srimath Kandada, Carlos Silva, Eric R. Bittner
In this paper we present a quantum stochastic model for spectroscopic line-shapes in the presence of a co-evolving and non-stationary background population of excitations.
Chemical Physics Mesoscale and Nanoscale Physics
no code implementations • 25 Aug 2020 • Mingkai Huang, Hao Li, Bing Bai, Chang Wang, Kun Bai, Fei Wang
Federated Learning(FL) is a newly developed privacy-preserving machine learning paradigm to bridge data repositories without compromising data security and privacy.
no code implementations • 6 Sep 2020 • Chang Wang, Jian Liang, Mingkai Huang, Bing Bai, Kun Bai, Hao Li
We present HDP-VFL, the first hybrid differentially private (DP) framework for vertical federated learning (VFL) to demonstrate that it is possible to jointly learn a generalized linear model (GLM) from vertically partitioned data with only a negligible cost, w. r. t.
no code implementations • 10 Sep 2020 • Lei Chen, Qi Qian, Hao Li
The anchor-free strategy benefits the classification task but can lead to sup-optimum for the regression task due to the lack of prior bounding boxes.
no code implementations • 25 Sep 2020 • Pengxu Wei, Hannan Lu, Radu Timofte, Liang Lin, WangMeng Zuo, Zhihong Pan, Baopu Li, Teng Xi, Yanwen Fan, Gang Zhang, Jingtuo Liu, Junyu Han, Errui Ding, Tangxin Xie, Liang Cao, Yan Zou, Yi Shen, Jialiang Zhang, Yu Jia, Kaihua Cheng, Chenhuan Wu, Yue Lin, Cen Liu, Yunbo Peng, Xueyi Zou, Zhipeng Luo, Yuehan Yao, Zhenyu Xu, Syed Waqas Zamir, Aditya Arora, Salman Khan, Munawar Hayat, Fahad Shahbaz Khan, Tongtong Zhao, Shanshan Zhao, Yoseob Han, Byung-Hoon Kim, JaeHyun Baek, HaoNing Wu, Dejia Xu, Bo Zhou, Wei Guan, Xiaobo Li, Chen Ye, Hao Li, Yukai Shi, Zhijing Yang, Xiaojun Yang, Haoyu Zhong, Xin Li, Xin Jin, Yaojun Wu, Yingxue Pang, Sen Liu, Zhi-Song Liu, Li-Wen Wang, Chu-Tak Li, Marie-Paule Cani, Wan-Chi Siu, Yuanbo Zhou, Rao Muhammad Umer, Christian Micheloni, Xiaofeng Cong, Rajat Gupta, Keon-Hee Ahn, Jun-Hyuk Kim, Jun-Ho Choi, Jong-Seok Lee, Feras Almasri, Thomas Vandamme, Olivier Debeir
This paper introduces the real image Super-Resolution (SR) challenge that was part of the Advances in Image Manipulation (AIM) workshop, held in conjunction with ECCV 2020.
1 code implementation • 30 Sep 2020 • Qi Qian, Hao Li, Juhua Hu
Recently, a number of works propose to transfer the pairwise similarity between examples to distill relative information.
no code implementations • 1 Oct 2020 • Jiaman Li, Zheng-Fei Kuang, Yajie Zhao, Mingming He, Karl Bladin, Hao Li
We also model the joint distribution between identities and expressions, enabling the inference of the full set of personalized blendshapes with dynamic appearances from a single neutral input scan.
no code implementations • 3 Oct 2020 • Yi Xu, Asaf Noy, Ming Lin, Qi Qian, Hao Li, Rong Jin
To this end, we develop two novel algorithms, termed "AugDrop" and "MixLoss", to correct the data bias in the data augmentation.
4 code implementations • EMNLP 2020 • Lu Xu, Hao Li, Wei Lu, Lidong Bing
Our observation is that the three elements within a triplet are highly related to each other, and this motivates us to build a joint model to extract such triplets using a sequence tagging approach.
Ranked #3 on Aspect Sentiment Triplet Extraction on SemEval
no code implementations • 11 Oct 2020 • Jian Liang, Yuren Cao, Shuang Li, Bing Bai, Hao Li, Fei Wang, Kun Bai
We further extend our method to a meta-learning framework to pursue more thorough domain-difference elimination.
1 code implementation • ICLR 2021 • Hao Li, Chenxin Tao, Xizhou Zhu, Xiaogang Wang, Gao Huang, Jifeng Dai
In this paper, we propose to automate the design of metric-specific loss functions by searching differentiable surrogate losses for each metric.
2 code implementations • ICLR 2021 • Yichen Qian, Zhiyu Tan, Xiuyu Sun, Ming Lin, Dongyang Li, Zhenhong Sun, Hao Li, Rong Jin
In this work, we propose a novel Global Reference Model for image compression to effectively leverage both the local and the global context information, leading to an enhanced compression rate.
no code implementations • 25 Oct 2020 • Shulin He, Hao Li, Xueliang Zhang
This paper introduces an improved target speaker extractor, referred to as Speakerfilter-Pro, based on our previous Speakerfilter model.
no code implementations • 4 Nov 2020 • Chenpeng Du, Hao Li, Yizhou Lu, Lan Wang, Yanmin Qian
Training a code-switching end-to-end automatic speech recognition (ASR) model normally requires a large amount of data, while code-switching data is often limited.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +4
no code implementations • 5 Nov 2020 • Hao Li, Xiaopeng Zhang, Hongkai Xiong
Contrastive learning based on instance discrimination trains model to discriminate different transformations of the anchor sample from other samples, which does not consider the semantic similarity among samples.
2 code implementations • 6 Nov 2020 • Hao Li, Huai Yu, Wen Yang, Lei Yu, Sebastian Scherer
Targeting at the unified line segment detection (ULSD) for both distorted and undistorted images, we propose to represent line segments with the Bezier curve model.
Ranked #5 on Line Segment Detection on wireframe dataset (sAP10 metric)
no code implementations • 19 Nov 2020 • Xinyue Huo, Lingxi Xie, Longhui Wei, Xiaopeng Zhang, Hao Li, Zijie Yang, Wengang Zhou, Houqiang Li, Qi Tian
Contrastive learning has achieved great success in self-supervised visual representation learning, but existing approaches mostly ignored spatial information which is often crucial for visual representation.
no code implementations • IEEE Access 2020 • Lin Zhou, Haoran Wei, Hao Li, Wenzhe Zhao, Yi Zhang, Yue Zhang
In this article, we introduce the polar coordinate system to the deep learning detector for the first time, and propose an anchor free Polar Remote Sensing Object Detector (P-RSDet), which can achieve competitive detection accuracy via using simpler object representation model and less regression parameters.
Ranked #12 on Oriented Object Detection on DOTA 1.0
no code implementations • 4 Dec 2020 • Haohang Xu, Xiaopeng Zhang, Hao Li, Lingxi Xie, Hongkai Xiong, Qi Tian
In this paper, we propose a hierarchical semantic alignment strategy via expanding the views generated by a single image to \textbf{Cross-samples and Multi-level} representation, and models the invariance to semantically similar images in a hierarchical way.
no code implementations • 10 Dec 2020 • Hao Li, Huan Wang, Guanghua Liu
To improve the detection performance of fake news, we take advantage of the event correlations of news and propose an event correlation filtering method (ECFM) for fake news detection, mainly consisting of the news characterizer, the pseudo label annotator, the event credibility updater, and the news entropy selector.
no code implementations • CUHK Course IERG5350 2020 • Tong Wu, Hao Li
The long-tail distributed data in the real world has always been a great challenge for deep learning.
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.
Facial Expression Recognition Facial Expression Recognition (FER)
no code implementations • 21 Dec 2020 • Chenchen Zhao, Hao Li
Existing pixel-level adversarial attacks on neural networks may be deficient in real scenarios, since pixel-level changes on the data cannot be fully delivered to the neural network after camera capture and multiple image preprocessing steps.
no code implementations • 21 Dec 2020 • Chenchen Zhao, Hao Li
Existing deep-learning based monocular orientation estimation algorithms faces the problem of confusion between the anterior and posterior parts of the objects, caused by the feature similarity of such parts in typical objects in traffic scenes such as cars and pedestrians.
no code implementations • 21 Dec 2020 • Chenchen Zhao, Hao Li
Then an attack method based on Strict Pooling Manipulation (SPM) which is an instantiation of the SLOM spirit is designed to effectively realize both type I and type II adversarial attacks on a target CNN.
no code implementations • 24 Dec 2020 • Zedong Tang, Fenlong Jiang, Junke Song, Maoguo Gong, Hao Li, Fan Yu, Zidong Wang, Min Wang
Optimizers that further adjust the scale of gradient, such as Adam, Natural Gradient (NG), etc., despite widely concerned and used by the community, are often found poor generalization performance, compared with Stochastic Gradient Descent (SGD).
1 code implementation • 25 Dec 2020 • Jianyang Gu, Hao Luo, Weihua Chen, Yiqi Jiang, Yuqi Zhang, Shuting He, Fan Wang, Hao Li, Wei Jiang
Considering the large gap between the source domain and target domain, we focused on solving two biases that influenced the performance on domain adaptive pedestrian Re-ID and proposed a two-stage training procedure.
no code implementations • 31 Dec 2020 • Haoran Ji, Yanzhao Liu, He Wang, Jiawei Luo, Jiaheng Li, Hao Li, Yang Wu, Yong Xu, Jian Wang
An essential ingredient to realize these quantum states is the magnetic gap in the topological surface states induced by the out-of-plane ferromagnetism on the surface of MnBi2Te4.
Materials Science
2 code implementations • ICCV 2021 • Ming Lin, Pichao Wang, Zhenhong Sun, Hesen Chen, Xiuyu Sun, Qi Qian, Hao Li, Rong Jin
To address this issue, instead of using an accuracy predictor, we propose a novel zero-shot index dubbed Zen-Score to rank the architectures.
Neural Architecture Search Vocal Bursts Intensity Prediction
1 code implementation • 20 Jan 2021 • Fei Du, Bo Xu, Jiasheng Tang, Yuqi Zhang, Fan Wang, Hao Li
We extend the classical tracking-by-detection paradigm to this tracking-any-object task.
Ranked #7 on Multi-Object Tracking on TAO (using extra training data)
1 code implementation • 25 Jan 2021 • Hao Li
The split covariance intersection filter (split CIF) is a useful tool for general data fusion and has the potential to be applied in a variety of engineering tasks.
no code implementations • 28 Jan 2021 • Qiang Zhou, Chaohui Yu, Chunhua Shen, Zhibin Wang, Hao Li
On the COCO dataset, our simple design achieves superior performance compared to both the FCOS baseline detector with NMS post-processing and the recent end-to-end NMS-free detectors.
1 code implementation • CVPR 2021 • Chenghao Chen, Hao Li
Unlike existing image deraining methods that embed low-quality features into the model directly, we replace low-quality features by latent high-quality features.
no code implementations • 29 Jan 2021 • Aditya Deshpande, Alessandro Achille, Avinash Ravichandran, Hao Li, Luca Zancato, Charless Fowlkes, Rahul Bhotika, Stefano Soatto, Pietro Perona
Since all model selection algorithms in the literature have been tested on different use-cases and never compared directly, we introduce a new comprehensive benchmark for model selection comprising of: i) A model zoo of single and multi-domain models, and ii) Many target tasks.
2 code implementations • 1 Feb 2021 • Ming Lin, Pichao Wang, Zhenhong Sun, Hesen Chen, Xiuyu Sun, Qi Qian, Hao Li, Rong Jin
Comparing with previous NAS methods, the proposed Zen-NAS is magnitude times faster on multiple server-side and mobile-side GPU platforms with state-of-the-art accuracy on ImageNet.
Ranked #2 on Neural Architecture Search on ImageNet
4 code implementations • ICCV 2021 • Shuting He, Hao Luo, Pichao Wang, Fan Wang, Hao Li, Wei Jiang
Extracting robust feature representation is one of the key challenges in object re-identification (ReID).
Ranked #1 on Person Re-Identification on Market-1501-C
2 code implementations • CVPR 2022 • Yang Liu, Fei Wang, Jiankang Deng, Zhipeng Zhou, Baigui Sun, Hao Li
As a result, practical solutions on label assignment, scale-level data augmentation, and reducing false alarms are necessary for advancing face detectors.
Ranked #13 on Face Detection on WIDER Face (Easy)
1 code implementation • CVPR 2021 • Qiang Zhou, Chaohui Yu, Zhibin Wang, Qi Qian, Hao Li
To alleviate the confirmation bias problem and improve the quality of pseudo annotations, we further propose a co-rectify scheme based on Instant-Teaching, denoted as Instant-Teaching$^*$.
Ranked #12 on Semi-Supervised Object Detection on COCO 100% labeled data (using extra training data)
no code implementations • CVPR 2022 • Hao Li, Tianwen Fu, Jifeng Dai, Hongsheng Li, Gao Huang, Xizhou Zhu
However, the automatic design of loss functions for generic tasks with various evaluation metrics remains under-investigated.
5 code implementations • ICCV 2021 • Alex Yu, RuiLong Li, Matthew Tancik, Hao Li, Ren Ng, Angjoo Kanazawa
We introduce a method to render Neural Radiance Fields (NeRFs) in real time using PlenOctrees, an octree-based 3D representation which supports view-dependent effects.
1 code implementation • CVPR 2021 • Haiwei Chen, Shichen Liu, Weikai Chen, Hao Li
Features that are equivariant to a larger group of symmetries have been shown to be more discriminative and powerful in recent studies.
no code implementations • 26 Mar 2021 • Hao Li, Xueliang Zhang, Guanglai Gao
Another way is to use an anchor speech, a short speech of the target speaker, to model the speaker identity.
no code implementations • 30 Mar 2021 • Shuning Chang, Pichao Wang, Fan Wang, Hao Li, Jiashi Feng
Temporal action proposal generation (TAPG) is a fundamental and challenging task in video understanding, especially in temporal action detection.
no code implementations • 8 Apr 2021 • Yi Xu, Qi Qian, Hao Li, Rong Jin
Noisy labels are very common in deep supervised learning.
1 code implementation • 13 Apr 2021 • Zhenhong Sun, Zhiyu Tan, Xiuyu Sun, Fangyi Zhang, Dongyang Li, Yichen Qian, Hao Li
The framework of dominant learned video compression methods is usually composed of motion prediction modules as well as motion vector and residual image compression modules, suffering from its complex structure and error propagation problem.
1 code implementation • ICCV 2021 • Jianlong Yuan, Yifan Liu, Chunhua Shen, Zhibin Wang, Hao Li
Previous works [3, 27] fail to employ strong augmentation in pseudo label learning efficiently, as the large distribution change caused by strong augmentation harms the batch normalisation statistics.
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 • IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 2021 • Hao Li, Maoguo Gong, Mingyang Zhang, Yue Wu
Change detection in heterogeneous remote sensing images is a challenging problem because it is hard to make a direct comparison in the original observation spaces, and most methods rely on a set of manually labeled samples.
no code implementations • 13 May 2021 • Yi Xu, Qi Qian, Hao Li, Rong Jin
Stochastic gradient descent (SGD) has become the most attractive optimization method in training large-scale deep neural networks due to its simplicity, low computational cost in each updating step, and good performance.
1 code implementation • 14 May 2021 • Cangning Fan, Fangyi Zhang, Peng Liu, Xiuyu Sun, Hao Li, Ting Xiao, Wei Zhao, Xianglong Tang
In this way, an obvious gap can be produced between the distributions of normal and abnormal data in the target domain, therefore enabling the anomaly detection in the domain.
1 code implementation • 14 May 2021 • Chong Liu, Yuqi Zhang, Hao Luo, Jiasheng Tang, Weihua Chen, Xianzhe Xu, Fan Wang, Hao Li, Yi-Dong Shen
Multi-Target Multi-Camera Tracking has a wide range of applications and is the basis for many advanced inferences and predictions.
1 code implementation • 14 May 2021 • Xiaolong Fan, Maoguo Gong, Yue Wu, Hao Li
Specifically, we first utilize a multi-view representation learning module to better capture both local and global information content across feature and topology views on graphs.
1 code implementation • 20 May 2021 • Hao Luo, Weihua Chen, Xianzhe Xu, Jianyang Gu, Yuqi Zhang, Chong Liu, Yiqi Jiang, Shuting He, Fan Wang, Hao Li
We mainly focus on four points, i. e. training data, unsupervised domain-adaptive (UDA) training, post-processing, model ensembling in this challenge.
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)
1 code implementation • CVPR 2022 • Qi Qian, Yuanhong Xu, Juhua Hu, Hao Li, Rong Jin
Clustering is to assign each instance a pseudo label that will be used to learn representations in discrimination.
Ranked #5 on Unsupervised Image Classification on CIFAR-10
1 code implementation • 28 May 2021 • Pichao Wang, Xue Wang, Fan Wang, Ming Lin, Shuning Chang, Hao Li, Rong Jin
A key component in vision transformers is the fully-connected self-attention which is more powerful than CNNs in modelling long range dependencies.
1 code implementation • Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition 2021 • Zedong Tang, Fenlong Jiang, Maoguo Gong, Hao Li, Yue Wu, Fan Yu, Zidong Wang, Min Wang
For the fully connected layers, by utilizing the low-rank property of Kronecker factors of Fisher information matrix, our method only requires inverting a small matrix to approximate the curvature with desirable accuracy.
no code implementations • 7 Jun 2021 • Jiaman Li, Ruben Villegas, Duygu Ceylan, Jimei Yang, Zhengfei Kuang, Hao Li, Yajie Zhao
We demonstrate the effectiveness of our hierarchical motion variational autoencoder in a variety of tasks including video-based human pose estimation, motion completion from partial observations, and motion synthesis from sparse key-frames.
Ranked #4 on Motion Synthesis on LaFAN1
1 code implementation • CVPR 2021 • Zedong Tang, Fenlong Jiang, Maoguo Gong, Hao Li, Yue Wu, Fan Yu, Zidong Wang, Min Wang
For the fully connected layers, by utilizing the low-rank property of Kronecker factors of Fisher information matrix, our method only requires inverting a small matrix to approximate the curvature with desirable accuracy.
no code implementations • CVPR 2021 • Huiwen Luo, Koki Nagano, Han-Wei Kung, Mclean Goldwhite, Qingguo Xu, Zejian Wang, Lingyu Wei, Liwen Hu, Hao Li
Cutting-edge 3D face reconstruction methods use non-linear morphable face models combined with GAN-based decoders to capture the likeness and details of a person but fail to produce neutral head models with unshaded albedo textures which is critical for creating relightable and animation-friendly avatars for integration in virtual environments.
1 code implementation • 5 Jul 2021 • Yuqi Zhang, Qian Qi, Chong Liu, Weihua Chen, Fan Wang, Hao Li, Rong Jin
In this work, we propose a graph-based re-ranking method to improve learned features while still keeping Euclidean distance as the similarity metric.
no code implementations • 9 Jul 2021 • Dewei Hu, Can Cui, Hao Li, Kathleen E. Larson, Yuankai K. Tao, Ipek Oguz
We then construct the local intensity fusion encoder (LIFE) to map a given OCT-A volume and its LIF counterpart to a shared latent space.
no code implementations • 11 Jul 2021 • Zheyi Ma, Hao Li, Wen Fang, Qingwen Liu, Bin Zhou, Zhiyong Bu
Then, a mobile detection model based on a multi-task cascaded convolutional network (MTCNN) is proposed to realize face alignment and mask detection on the RGB images.
no code implementations • 12 Jul 2021 • Ya Wang, Hesen Chen, Fangyi Zhang, Yaohua Wang, Xiuyu Sun, Ming Lin, Hao Li
Data augmentation is a commonly used approach to improving the generalization of deep learning models.
no code implementations • 23 Aug 2021 • Yiqi Jiang, Weihua Chen, Xiuyu Sun, Xiaoyu Shi, Fan Wang, Hao Li
Recently, GAN based method has demonstrated strong effectiveness in generating augmentation data for person re-identification (ReID), on account of its ability to bridge the gap between domains and enrich the data variety in feature space.
1 code implementation • ICCV 2021 • Hongbin Xu, Zhipeng Zhou, Yali Wang, Wenxiong Kang, Baigui Sun, Hao Li, Yu Qiao
Specially, the limitations can be categorized into two types: ambiguious supervision in foreground and invalid supervision in background.
no code implementations • 1 Sep 2021 • Yi Xu, Lei Shang, Jinxing Ye, Qi Qian, Yu-Feng Li, Baigui Sun, Hao Li, Rong Jin
In this work we develop a simple yet powerful framework, whose key idea is to select a subset of training examples from the unlabeled data when performing existing SSL methods so that only the unlabeled examples with pseudo labels related to the labeled data will be used to train models.
no code implementations • 8 Sep 2021 • Pichao Wang, Xue Wang, Hao Luo, Jingkai Zhou, Zhipeng Zhou, Fan Wang, Hao Li, Rong Jin
In this paper, we further investigate this problem and extend the above conclusion: only early convolutions do not help for stable training, but the scaled ReLU operation in the \textit{convolutional stem} (\textit{conv-stem}) matters.
2 code implementations • ICLR 2022 • Tongkun Xu, Weihua Chen, Pichao Wang, Fan Wang, Hao Li, Rong Jin
Along with the pseudo labels, a weight-sharing triple-branch transformer framework is proposed to apply self-attention and cross-attention for source/target feature learning and source-target domain alignment, respectively.
Ranked #3 on Domain Adaptation on Office-31
1 code implementation • ICCV 2021 • Sitao Xiang, Yuming Gu, Pengda Xiang, Menglei Chai, Hao Li, Yajie Zhao, Mingming He
In this paper, we adopt a general setting where all factors that are hard to label or identify are encapsulated as a single unknown factor.
1 code implementation • 20 Sep 2021 • Zhenhong Sun, Zhiyu Tan, Xiuyu Sun, Fangyi Zhang, Yichen Qian, Dongyang Li, Hao Li
Compression standards have been used to reduce the cost of image storage and transmission for decades.
no code implementations • 24 Sep 2021 • Hao Li, Dewei Hu, Qibang Zhu, Kathleen E. Larson, Huahong Zhang, Ipek Oguz
To overcome this problem, domain adaptation is an effective way to leverage information from source domain to obtain accurate segmentations without requiring manual labels in target domain.
1 code implementation • 27 Sep 2021 • Shizhou Zhang, De Cheng, Wenlong Luo, Yinghui Xing, Duo Long, Hao Li, Kai Niu, Guoqiang Liang, Yanning Zhang
Finding target persons in full scene images with a query of text description has important practical applications in intelligent video surveillance. However, different from the real-world scenarios where the bounding boxes are not available, existing text-based person retrieval methods mainly focus on the cross modal matching between the query text descriptions and the gallery of cropped pedestrian images.
no code implementations • 29 Sep 2021 • Yang Liu, Zhipeng Zhou, Lei Shang, Baigui Sun, Hao Li, Rong Jin
Unsupervised domain adaptation (UDA) aims to transfer the knowledge from a labeled source domain to an unlabeled target domain.
no code implementations • 29 Sep 2021 • Hanlin Chen, Ming Lin, Xiuyu Sun, Hao Li
Based on these new discoveries, we propose i) a novel hybrid zero-shot proxy which outperforms existing ones by a large margin and is transferable among popular search spaces; ii) a new index for better measuring the true performance of ZS-NAS proxies in constrained NAS.
2 code implementations • NeurIPS 2021 • Shiming Chen, Guo-Sen Xie, Yang Liu, Qinmu Peng, Baigui Sun, Hao Li, Xinge You, Ling Shao
Specifically, HSVA aligns the semantic and visual domains by adopting a hierarchical two-step adaptation, i. e., structure adaptation and distribution adaptation.
no code implementations • ICCV 2021 • Tianye Li, Shichen Liu, Timo Bolkart, Jiayi Liu, Hao Li, Yajie Zhao
We propose ToFu, Topologically consistent Face from multi-view, a geometry inference framework that can produce topologically consistent meshes across facial identities and expressions using a volumetric representation instead of an explicit underlying 3DMM.
2 code implementations • 23 Nov 2021 • Hao Luo, Pichao Wang, Yi Xu, Feng Ding, Yanxin Zhou, Fan Wang, Hao Li, Rong Jin
We first investigate self-supervised learning (SSL) methods with Vision Transformer (ViT) pretrained on unlabelled person images (the LUPerson dataset), and empirically find it significantly surpasses ImageNet supervised pre-training models on ReID tasks.
Ranked #1 on Unsupervised Person Re-Identification on Market-1501 (using extra training data)
no code implementations • ICCV 2021 • Weitao Chen, Zhibin Wang, Hao Li
Percentage of image size is often used as the threshold of PCK.
no code implementations • 24 Nov 2021 • Ziquan Liu, Yi Xu, Yuanhong Xu, Qi Qian, Hao Li, Xiangyang Ji, Antoni Chan, Rong Jin
The generalization result of using pre-training data shows that the excess risk bound on a target task can be improved when the appropriate pre-training data is included in fine-tuning.
1 code implementation • 26 Nov 2021 • Zhenhong Sun, Ming Lin, Xiuyu Sun, Zhiyu Tan, Hao Li, Rong Jin
Recent researches attempt to reduce this cost by optimizing the backbone architecture with the help of Neural Architecture Search (NAS).
Ranked #88 on Object Detection on COCO minival
no code implementations • 28 Nov 2021 • Hao Li, Jianan Liu
We also analyzed several down-sampling strategies based on the acceleration factor, including multiple combinations of in-plane and through-plane down-sampling, and developed a controllable and quantifiable motion artifact generation method.
1 code implementation • 2 Dec 2021 • Zhaoyuan Yin, Pichao Wang, Fan Wang, Xianzhe Xu, Hanling Zhang, Hao Li, Rong Jin
Unsupervised semantic segmentation aims to obtain high-level semantic representation on low-level visual features without manual annotations.
Ranked #2 on Unsupervised Semantic Segmentation on COCO-Stuff-171 (using extra training data)
1 code implementation • CVPR 2022 • Xizhou Zhu, Jinguo Zhu, Hao Li, Xiaoshi Wu, Xiaogang Wang, Hongsheng Li, Xiaohua Wang, Jifeng Dai
The model is pre-trained on several uni-modal and multi-modal tasks, and evaluated on a variety of downstream tasks, including novel tasks that did not appear in the pre-training stage.
1 code implementation • 3 Dec 2021 • Shiming Chen, Ziming Hong, Yang Liu, Guo-Sen Xie, Baigui Sun, Hao Li, Qinmu Peng, Ke Lu, Xinge You
Although some attention-based models have attempted to learn such region features in a single image, the transferability and discriminative attribute localization of visual features are typically neglected.
no code implementations • 9 Dec 2021 • Fengyun Zhang, Li Yang, Yuhuan Liu, Yulong Ding, Shuang-Hua Yang, Hao Li
The challenges of indoor localization include inadequate localization accuracy, unreasonable anchor deployment in complex scenarios, lack of stability, and high cost.
no code implementations • 10 Dec 2021 • Fengyun Zhang, Hao Li, Yulong Ding, Shuang-Hua Yang, Li Yang
The paper aims to reveal the relationship between the performance of moving object tracking algorithms and the tracking anchors (station) deployment.
1 code implementation • CVPR 2022 • Benjia Zhou, Pichao Wang, Jun Wan, Yanyan Liang, Fan Wang, Du Zhang, Zhen Lei, Hao Li, Rong Jin
Decoupling spatiotemporal representation refers to decomposing the spatial and temporal features into dimension-independent factors.
Ranked #1 on Hand Gesture Recognition on NVGesture
1 code implementation • 21 Dec 2021 • Shruti Agarwal, Liwen Hu, Evonne Ng, Trevor Darrell, Hao Li, Anna Rohrbach
In today's era of digital misinformation, we are increasingly faced with new threats posed by video falsification techniques.
1 code implementation • 23 Dec 2021 • Jingkai Zhou, Pichao Wang, Fan Wang, Qiong Liu, Hao Li, Rong Jin
Self-attention is powerful in modeling long-range dependencies, but it is weak in local finer-level feature learning.
Ranked #46 on Semantic Segmentation on ADE20K val
no code implementations • 4 Jan 2022 • Xu Wang, Huan Zhao, WeiWei Tu, Hao Li, Yu Sun, Xiaochen Bo
Double-strand DNA breaks (DSBs) are a form of DNA damage that can cause abnormal chromosomal rearrangements.
3 code implementations • 8 Jan 2022 • Reuben Dorent, Aaron Kujawa, Marina Ivory, Spyridon Bakas, Nicola Rieke, Samuel Joutard, Ben Glocker, Jorge Cardoso, Marc Modat, Kayhan Batmanghelich, Arseniy Belkov, Maria Baldeon Calisto, Jae Won Choi, Benoit M. Dawant, Hexin Dong, Sergio Escalera, Yubo Fan, Lasse Hansen, Mattias P. Heinrich, Smriti Joshi, Victoriya Kashtanova, Hyeon Gyu Kim, Satoshi Kondo, Christian N. Kruse, Susana K. Lai-Yuen, Hao Li, Han Liu, Buntheng Ly, Ipek Oguz, Hyungseob Shin, Boris Shirokikh, Zixian Su, Guotai Wang, Jianghao Wu, Yanwu Xu, Kai Yao, Li Zhang, Sebastien Ourselin, Jonathan Shapey, Tom Vercauteren
The aim was to automatically perform unilateral VS and bilateral cochlea segmentation on hrT2 as provided in the testing set (N=137).
no code implementations • 18 Jan 2022 • Hao Li, Cor-Paul Bezemer
Our study shows that the vast majority of the studied bindings cover only a small portion of the source library releases, and the delay for receiving support for a source library release is large.
no code implementations • 21 Jan 2022 • Pichao Wang, Fan Wang, Hao Li
During the KD process, the TCL loss transfers the local structure, exploits the higher order information, and mitigates the misalignment of the heterogeneous output of teacher and student networks.
2 code implementations • ICLR 2022 • Yiqi Jiang, Zhiyu Tan, Junyan Wang, Xiuyu Sun, Ming Lin, Hao Li
This heavy-backbone design paradigm is mostly due to the historical legacy when transferring image recognition models to object detection rather than an end-to-end optimized design for object detection.
1 code implementation • 15 Feb 2022 • Hao Li
This note complements the author's recent paper "Robust representation learning with feedback for single image deraining" by providing heuristically theoretical explanations on the mechanism of representation learning with feedback, namely an essential merit of the works presented in this recent article.
1 code implementation • 7 Mar 2022 • Han Liu, Yubo Fan, Hao Li, Jiacheng Wang, Dewei Hu, Can Cui, Ho Hin Lee, Huahong Zhang, Ipek Oguz
Previously, a training strategy termed Modality Dropout (ModDrop) has been applied to MS lesion segmentation to achieve the state-of-the-art performance with missing modality.
no code implementations • 16 Mar 2022 • Jing Lu, Yunxu Xu, Hao Li, Zhanzhan Cheng, Yi Niu
Accordingly, the embedding space can be better optimized to discriminate therein the predefined classes and between known and unknowns.
1 code implementation • CVPR 2022 • Hansheng Chen, Pichao Wang, Fan Wang, Wei Tian, Lu Xiong, Hao Li
The 2D-3D coordinates and corresponding weights are treated as intermediate variables learned by minimizing the KL divergence between the predicted and target pose distribution.
Ranked #6 on 6D Pose Estimation using RGB on LineMOD
1 code implementation • CVPR 2022 • Matthew Wallingford, Hao Li, Alessandro Achille, Avinash Ravichandran, Charless Fowlkes, Rahul Bhotika, Stefano Soatto
TAPS solves a joint optimization problem which determines which layers to share with the base model and the value of the task-specific weights.
no code implementations • CVPR 2022 • Evonne Ng, Hanbyul Joo, Liwen Hu, Hao Li, Trevor Darrell, Angjoo Kanazawa, Shiry Ginosar
We present a framework for modeling interactional communication in dyadic conversations: given multimodal inputs of a speaker, we autoregressively output multiple possibilities of corresponding listener motion.
no code implementations • 6 May 2022 • Yue Wu, Yibo Liu, Maoguo Gong, Peiran Gong, Hao Li, Zedong Tang, Qiguang Miao, Wenping Ma
The modeling of multi-view point cloud registration as multi-task optimization are twofold.
no code implementations • 9 May 2022 • Hao Li, Xu Li, Belhal Karimi, Jie Chen, Mingming Sun
Modeling visual question answering(VQA) through scene graphs can significantly improve the reasoning accuracy and interpretability.
2 code implementations • 11 May 2022 • Yawei Li, Kai Zhang, Radu Timofte, Luc van Gool, Fangyuan Kong, Mingxi Li, Songwei Liu, Zongcai Du, Ding Liu, Chenhui Zhou, Jingyi Chen, Qingrui Han, Zheyuan Li, Yingqi Liu, Xiangyu Chen, Haoming Cai, Yu Qiao, Chao Dong, Long Sun, Jinshan Pan, Yi Zhu, Zhikai Zong, Xiaoxiao Liu, Zheng Hui, Tao Yang, Peiran Ren, Xuansong Xie, Xian-Sheng Hua, Yanbo Wang, Xiaozhong Ji, Chuming Lin, Donghao Luo, Ying Tai, Chengjie Wang, Zhizhong Zhang, Yuan Xie, Shen Cheng, Ziwei Luo, Lei Yu, Zhihong Wen, Qi Wu1, Youwei Li, Haoqiang Fan, Jian Sun, Shuaicheng Liu, Yuanfei Huang, Meiguang Jin, Hua Huang, Jing Liu, Xinjian Zhang, Yan Wang, Lingshun Long, Gen Li, Yuanfan Zhang, Zuowei Cao, Lei Sun, Panaetov Alexander, Yucong Wang, Minjie Cai, Li Wang, Lu Tian, Zheyuan Wang, Hongbing Ma, Jie Liu, Chao Chen, Yidong Cai, Jie Tang, Gangshan Wu, Weiran Wang, Shirui Huang, Honglei Lu, Huan Liu, Keyan Wang, Jun Chen, Shi Chen, Yuchun Miao, Zimo Huang, Lefei Zhang, Mustafa Ayazoğlu, Wei Xiong, Chengyi Xiong, Fei Wang, Hao Li, Ruimian Wen, Zhijing Yang, Wenbin Zou, Weixin Zheng, Tian Ye, Yuncheng Zhang, Xiangzhen Kong, Aditya Arora, Syed Waqas Zamir, Salman Khan, Munawar Hayat, Fahad Shahbaz Khan, Dandan Gaoand Dengwen Zhouand Qian Ning, Jingzhu Tang, Han Huang, YuFei Wang, Zhangheng Peng, Haobo Li, Wenxue Guan, Shenghua Gong, Xin Li, Jun Liu, Wanjun Wang, Dengwen Zhou, Kun Zeng, Hanjiang Lin, Xinyu Chen, Jinsheng Fang
The aim was to design a network for single image super-resolution that achieved improvement of efficiency measured according to several metrics including runtime, parameters, FLOPs, activations, and memory consumption while at least maintaining the PSNR of 29. 00dB on DIV2K validation set.
no code implementations • 13 May 2022 • Jianan Liu, Hao Li, Tao Huang, Euijoon Ahn, Kang Han, Adeel Razi, Wei Xiang, Jinman Kim, David Dagan Feng
However, the difference in degradation representations between synthetic and authentic LR images suppresses the quality of SR images reconstructed from authentic LR images.
no code implementations • 25 May 2022 • Ziquan Liu, Yi Xu, Yuanhong Xu, Qi Qian, Hao Li, Rong Jin, Xiangyang Ji, Antoni B. Chan
With our empirical result obtained from 1, 330 models, we provide the following main observations: 1) ERM combined with data augmentation can achieve state-of-the-art performance if we choose a proper pre-trained model respecting the data property; 2) specialized algorithms further improve the robustness on top of ERM when handling a specific type of distribution shift, e. g., GroupDRO for spurious correlation and CORAL for large-scale out-of-distribution data; 3) Comparing different pre-training modes, architectures and data sizes, we provide novel observations about pre-training on distribution shift, which sheds light on designing or selecting pre-training strategy for different kinds of distribution shifts.
no code implementations • 26 May 2022 • Yuan Hu, Lei Chen, Zhibin Wang, Hao Li
We also compare four categories of perturbation methods for ensemble forecasting, i. e. fixed distribution perturbation, learned distribution perturbation, MC dropout, and multi model ensemble.
no code implementations • 28 May 2022 • Qiang Zhou, Chaohui Yu, Zhibin Wang, Hao Li
To tackle this problem, we propose a purely angle-free framework for rotated object detection, called Point RCNN, which mainly consists of PointRPN and PointReg.