no code implementations • ACL 2013 • Ryan McDonald, Joakim Nivre, Yvonne Quirmbach-Brundage, Yoav Goldberg, Dipanjan Das, Kuzman Ganchev, Keith Hall, Slav Petrov, Hao Zhang, Oscar T{\"a}ckstr{\"o}m, Claudia Bedini, N{\'u}ria Bertomeu Castell{\'o}, Jungmee Lee
2 code implementations • 9 Aug 2013 • Binghang Liu, Yujian Shi, Jianying Yuan, Xuesong Hu, Hao Zhang, Nan Li, Zhenyu Li, Yanxiang Chen, Desheng Mu, Wei Fan
Therefore, it is necessary to develop efficient assembly-independent methods for accurate estimation of these genomic characteristics.
no code implementations • 23 Oct 2013 • Hao Zhang, Liqing Zhang
Current studies about motor imagery based rehabilitation training systems for stroke subjects lack an appropriate analytic method, which can achieve a considerable classification accuracy, at the same time detects gradual changes of imagery patterns during rehabilitation process and disinters potential mechanisms about motor function recovery.
no code implementations • CVPR 2014 • Hao Zhang, Wenjun Zhou, Christopher Reardon, Lynne E. Parker
In addition, the results show that our SOD descriptor is a superior individual descriptor for action recognition.
no code implementations • CVPR 2014 • Xiaowu Chen, Dongqing Zou, Jianwei Li, Xiaochun Cao, Qinping Zhao, Hao Zhang
Previous approaches for edit propagation typically employ a global optimization over the whole set of image pixels, incurring a prohibitively high memory and time consumption for high-resolution images.
4 code implementations • 3 Oct 2014 • Zhicheng Yan, Hao Zhang, Robinson Piramuthu, Vignesh Jagadeesh, Dennis Decoste, Wei Di, Yizhou Yu
In this paper, we introduce hierarchical deep CNNs (HD-CNNs) by embedding deep CNNs into a category hierarchy.
Ranked #174 on Image Classification on CIFAR-100
no code implementations • 4 Dec 2014 • Hao Zhang, Jing Wang, Jianhua Ma, Hongbing Lu, Zhengrong Liang
Statistical image reconstruction (SIR) methods have shown potential to substantially improve the image quality of low-dose X-ray computed tomography (CT) as compared to the conventional filtered back-projection (FBP) method for various clinical tasks.
1 code implementation • 24 Dec 2014 • Zhicheng Yan, Hao Zhang, Baoyuan Wang, Sylvain Paris, Yizhou Yu
Many photographic styles rely on subtle adjustments that depend on the image content and even its semantics.
no code implementations • 21 Jul 2015 • Hao Zhang, Yao Ma, Masashi Sugiyama
We consider a task assignment problem in crowdsourcing, which is aimed at collecting as many reliable labels as possible within a limited budget.
no code implementations • 26 Jul 2015 • Hao Zhang, Masashi Sugiyama
Task selection (picking an appropriate labeling task) and worker selection (assigning the labeling task to a suitable worker) are two major challenges in task assignment for crowdsourcing.
no code implementations • 15 Oct 2015 • Yao Ma, Hao Zhang, Masashi Sugiyama
The online Markov decision process (MDP) is a generalization of the classical Markov decision process that incorporates changing reward functions.
no code implementations • ICCV 2015 • Zhicheng Yan, Hao Zhang, Robinson Piramuthu, Vignesh Jagadeesh, Dennis Decoste, Wei Di, Yizhou Yu
In this paper, we introduce hierarchical deep CNNs (HD-CNNs) by embedding deep CNNs into a category hierarchy.
no code implementations • 19 Dec 2015 • Hao Zhang, Zhiting Hu, Jinliang Wei, Pengtao Xie, Gunhee Kim, Qirong Ho, Eric Xing
To investigate how to adapt existing frameworks to efficiently support distributed GPUs, we propose Poseidon, a scalable system architecture for distributed inter-machine communication in existing DL frameworks.
no code implementations • 4 Jan 2016 • Jincheng Mei, Hao Zhang, Bao-liang Lu
The scalability of submodular optimization methods is critical for their usability in practice.
1 code implementation • 5 Jan 2016 • Fei Han, Brian Reily, William Hoff, Hao Zhang
Spatiotemporal human representation based on 3D visual perception data is a rapidly growing research area.
no code implementations • 15 Mar 2016 • Zhicheng Yan, Hao Zhang, Yangqing Jia, Thomas Breuel, Yizhou Yu
State-of-the-art results of semantic segmentation are established by Fully Convolutional neural Networks (FCNs).
no code implementations • 30 Apr 2016 • Xue Yang, Fei Han, Hua Wang, Hao Zhang
Sparse representation has been widely studied in visual tracking, which has shown promising tracking performance.
no code implementations • 16 May 2016 • Fei Han, Christopher Reardon, Lynne E. Parker, Hao Zhang
In order for cooperative robots ("co-robots") to respond to human behaviors accurately and efficiently in human-robot collaboration, interpretation of human actions, awareness of new situations, and appropriate decision making are all crucial abilities for co-robots.
no code implementations • ACL 2016 • Hao Zhang, Zhiting Hu, Yuntian Deng, Mrinmaya Sachan, Zhicheng Yan, Eric P. Xing
We study the problem of automatically building hypernym taxonomies from textual and visual data.
no code implementations • 24 Feb 2017 • Fei Han, Xue Yang, Christopher Reardon, Yu Zhang, Hao Zhang
We formulate FABL as a regression-like optimization problem with structured sparsity-inducing norms to model interrelationships of body parts and features.
no code implementations • 24 Feb 2017 • Fei Han, Xue Yang, Yu Zhang, Hao Zhang
Apprenticeship learning has recently attracted a wide attention due to its capability of allowing robots to learn physical tasks directly from demonstrations provided by human experts.
no code implementations • ICCV 2017 • Xiaodan Liang, Zhiting Hu, Hao Zhang, Chuang Gan, Eric P. Xing
The proposed Recurrent Topic-Transition Generative Adversarial Network (RTT-GAN) builds an adversarial framework between a structured paragraph generator and multi-level paragraph discriminators.
Generative Adversarial Network Image Paragraph Captioning +1
no code implementations • 21 Mar 2017 • Hao Wang, Xiaodan Liang, Hao Zhang, Dit-yan Yeung, Eric P. Xing
We cast this problem as manipulating an input image according to a parametric model whose key parameters can be conditionally generated from any guiding signal (even unseen ones).
no code implementations • 26 Mar 2017 • Wei Dai, Joseph Doyle, Xiaodan Liang, Hao Zhang, Nanqing Dong, Yuan Li, Eric P. Xing
Through this adversarial process the critic network learns the higher order structures and guides the segmentation model to achieve realistic segmentation outcomes.
6 code implementations • ICCV 2017 • Zili Yi, Hao Zhang, Ping Tan, Minglun Gong
Depending on the task complexity, thousands to millions of labeled image pairs are needed to train a conditional GAN.
Ranked #2 on Image-to-Image Translation on Aerial-to-Map
no code implementations • 18 Apr 2017 • Ashwin Mathur, Fei Han, Hao Zhang
We introduce a new dataset Multisensory Omnidirectional Long-term Place recognition (MOLP) comprising omnidirectional intensity and disparity images.
Robotics
no code implementations • 5 May 2017 • Jun Li, Kai Xu, Siddhartha Chaudhuri, Ersin Yumer, Hao Zhang, Leonidas Guibas
We introduce a novel neural network architecture for encoding and synthesis of 3D shapes, particularly their structures.
no code implementations • 11 Jun 2017 • Hao Zhang, Zeyu Zheng, Shizhen Xu, Wei Dai, Qirong Ho, Xiaodan Liang, Zhiting Hu, Jinliang Wei, Pengtao Xie, Eric P. Xing
We show that Poseidon enables Caffe and TensorFlow to achieve 15. 5x speed-up on 16 single-GPU machines, even with limited bandwidth (10GbE) and the challenging VGG19-22K network for image classification.
no code implementations • 1 Aug 2017 • Xiaodan Liang, Hao Zhang, Eric P. Xing
Generative Adversarial Networks (GANs) have recently achieved significant improvement on paired/unpaired image-to-image translation, such as photo$\rightarrow$ sketch and artist painting style transfer.
Ranked #4 on Facial Expression Translation on CelebA
no code implementations • 13 Aug 2017 • Quanshi Zhang, Ying Nian Wu, Hao Zhang, Song-Chun Zhu
The loss is defined for nodes in all layers of the AOG, including the generative loss (measuring the likelihood of the images) and the discriminative loss (measuring the fitness to human answers).
2 code implementations • 28 Sep 2017 • Pinxin Long, Tingxiang Fan, Xinyi Liao, Wenxi Liu, Hao Zhang, Jia Pan
We validate the learned sensor-level collision avoidance policy in a variety of simulated scenarios with thorough performance evaluations and show that the final learned policy is able to find time efficient, collision-free paths for a large-scale robot system.
no code implementations • 1 Oct 2017 • Liqun Shao, Hao Zhang, Ming Jia, Jie Wang
We show that the orderings of the ROUGE and WESM scores of our algorithms are highly comparable, suggesting that WESM may serve as a viable alternative for measuring the quality of a summary.
1 code implementation • NeurIPS 2017 • Zhijie Deng, Hao Zhang, Xiaodan Liang, Luona Yang, Shizhen Xu, Jun Zhu, Eric P. Xing
We study the problem of conditional generative modeling based on designated semantics or structures.
no code implementations • 11 Dec 2017 • Hao Zhang, Shizhen Xu, Graham Neubig, Wei Dai, Qirong Ho, Guangwen Yang, Eric P. Xing
Recent deep learning (DL) models have moved beyond static network architectures to dynamic ones, handling data where the network structure changes every example, such as sequences of variable lengths, trees, and graphs.
1 code implementation • 7 Jan 2018 • Hao Zhang, Xinlin Xie, Chunyu Fang, Yicong Yang, Di Jin, Peng Fei
We combine generative adversarial network (GAN) with light microscopy to achieve deep learning super-resolution under a large field of view (FOV).
1 code implementation • ICLR 2018 • Hao Zhang, Bo Chen, Dandan Guo, Mingyuan Zhou
To train an inference network jointly with a deep generative topic model, making it both scalable to big corpora and fast in out-of-sample prediction, we develop Weibull hybrid autoencoding inference (WHAI) for deep latent Dirichlet allocation, which infers posterior samples via a hybrid of stochastic-gradient MCMC and autoencoding variational Bayes.
2 code implementations • 22 Mar 2018 • Zili Yi, Zhiqin Chen, Hao Cai, Wendong Mao, Minglun Gong, Hao Zhang
The key feature of BSD-GAN is that it is trained in multiple branches, progressively covering both the breadth and depth of the network, as resolutions of the training images increase to reveal finer-scale features.
no code implementations • 25 Mar 2018 • Kangxue Yin, Hui Huang, Daniel Cohen-Or, Hao Zhang
We introduce P2P-NET, a general-purpose deep neural network which learns geometric transformations between point-based shape representations from two domains, e. g., meso-skeletons and surfaces, partial and complete scans, etc.
no code implementations • 14 Apr 2018 • Zhi-Qi Cheng, Hao Zhang, Xiao Wu, Chong-Wah Ngo
A principle way of hyperlinking can be carried out by picking centers of clusters as anchors and from there reach out to targets within or outside of clusters with consideration of neighborhood complexity.
no code implementations • 18 Apr 2018 • Fenggen Yu, Yan Zhang, Kai Xu, Ali Mahdavi-Amiri, Hao Zhang
We present a semi-supervised co-analysis method for learning 3D shape styles from projected feature lines, achieving style patch localization with only weak supervision.
no code implementations • CVPR 2018 • Kai Liu, Hua Wang, Feiping Nie, Hao Zhang
To tackle these two challenges, in this paper we propose a novel image representation learning method that can integrate the local patches (the instances) of an input image (the bag) and its holistic representation into one single-vector representation.
1 code implementation • 5 Jul 2018 • Jouri D. S. Bommer, Hao Zhang, Önder Gül, Bas Nijholt, Michael Wimmer, Filipp N. Rybakov, Julien Garaud, Donjan Rodic, Egor Babaev, Matthias Troyer, Diana Car, Sébastien R. Plissard, Erik P. A. M. Bakkers, Kenji Watanabe, Takashi Taniguchi, Leo P. Kouwenhoven
Spin-orbit interaction (SOI) plays a key role in creating Majorana zero modes in semiconductor nanowires proximity coupled to a superconductor.
Mesoscale and Nanoscale Physics
no code implementations • 24 Jul 2018 • Manyi Li, Akshay Gadi Patil, Kai Xu, Siddhartha Chaudhuri, Owais Khan, Ariel Shamir, Changhe Tu, Baoquan Chen, Daniel Cohen-Or, Hao Zhang
We present a generative neural network which enables us to generate plausible 3D indoor scenes in large quantities and varieties, easily and highly efficiently.
Graphics
no code implementations • COLING 2018 • Hao Zhang, Axel Ng, Richard Sproat
Compared to a strong baseline of attention-based RNN, our ITG RNN re-ordering model can reach the same reordering accuracy with only 1/10 of the training data and is 2. 5x faster in decoding.
2 code implementations • ECCV 2018 • Changqing Zou, Qian Yu, Ruofei Du, Haoran Mo, Yi-Zhe Song, Tao Xiang, Chengying Gao, Baoquan Chen, Hao Zhang
We contribute the first large-scale dataset of scene sketches, SketchyScene, with the goal of advancing research on sketch understanding at both the object and scene level.
no code implementations • ECCV 2018 • Xiaodan Liang, Hao Zhang, Liang Lin, Eric Xing
Despite the promising results on paired/unpaired image-to-image translation achieved by Generative Adversarial Networks (GANs), prior works often only transfer the low-level information (e. g. color or texture changes), but fail to manipulate high-level semantic meanings (e. g., geometric structure or content) of different object regions.
1 code implementation • WS 2018 • Andreas Hanselowski, Hao Zhang, Zile Li, Daniil Sorokin, Benjamin Schiller, Claudia Schulz, Iryna Gurevych
The Fact Extraction and VERification (FEVER) shared task was launched to support the development of systems able to verify claims by extracting supporting or refuting facts from raw text.
no code implementations • 8 Sep 2018 • Hao Zhang, Stephen Zahorian, Xiao Chen, Peter Guzewich, Xiaoyu Liu
In this paper, we present a reverberation removal approach for speaker verification, utilizing dual-label deep neural networks (DNNs).
no code implementations • 12 Sep 2018 • Hao Zhang, Jie Wang
We present Semantic WordRank (SWR), an unsupervised method for generating an extractive summary of a single document.
no code implementations • 14 Sep 2018 • Chenyang Zhu, Kai Xu, Siddhartha Chaudhuri, Renjiao Yi, Hao Zhang
The network may significantly alter the geometry and structure of the input parts and synthesize a novel shape structure based on the inputs, while adding or removing parts to minimize a structure plausibility loss.
1 code implementation • 24 Sep 2018 • Vijay Varma, Davide Gerosa, François Hébert, Leo C. Stein, Hao Zhang
We present accurate fits for the remnant properties of generically precessing binary black holes, trained on large banks of numerical-relativity simulations.
General Relativity and Quantum Cosmology High Energy Astrophysical Phenomena
no code implementations • ICLR 2019 • Haowen Xu, Hao Zhang, Zhiting Hu, Xiaodan Liang, Ruslan Salakhutdinov, Eric Xing
Many machine learning problems involve iteratively and alternately optimizing different task objectives with respect to different sets of parameters.
1 code implementation • 4 Oct 2018 • Haowen Xu, Hao Zhang, Zhiting Hu, Xiaodan Liang, Ruslan Salakhutdinov, Eric Xing
Many machine learning problems involve iteratively and alternately optimizing different task objectives with respect to different sets of parameters.
no code implementations • 7 Oct 2018 • Hao Zhang, Jianwei Ma
In most convolution neural networks (CNNs), downsampling hidden layers is adopted for increasing computation efficiency and the receptive field size.
no code implementations • ICLR 2019 • Wei Dai, Yi Zhou, Nanqing Dong, Hao Zhang, Eric P. Xing
Many distributed machine learning (ML) systems adopt the non-synchronous execution in order to alleviate the network communication bottleneck, resulting in stale parameters that do not reflect the latest updates.
no code implementations • 9 Oct 2018 • Aliaksandr Huminski, Hao Zhang, Gangeshwar Krishnamurthy
Semantic role theory considers roles as a small universal set of unanalyzed entities.
no code implementations • 9 Oct 2018 • Aliaksandr Huminski, Hao Zhang
Semantic role theory is a widely used approach for event representation.
no code implementations • NeurIPS 2018 • Dandan Guo, Bo Chen, Hao Zhang, Mingyuan Zhou
We develop deep Poisson-gamma dynamical systems (DPGDS) to model sequentially observed multivariate count data, improving previously proposed models by not only mining deep hierarchical latent structure from the data, but also capturing both first-order and long-range temporal dependencies.
no code implementations • 31 Oct 2018 • Qiang Hu, Hao Zhang
The developments of deep neural networks (DNN) in recent years have ushered a brand new era of artificial intelligence.
1 code implementation • ICCV 2019 • Nadav Schor, Oren Katzir, Hao Zhang, Daniel Cohen-Or
Data-driven generative modeling has made remarkable progress by leveraging the power of deep neural networks.
1 code implementation • NeurIPS 2018 • Xiaodan Liang, Zhiting Hu, Hao Zhang, Liang Lin, Eric P. Xing
To cooperate with local convolutions, each SGR is constituted by three modules: a) a primal local-to-semantic voting module where the features of all symbolic nodes are generated by voting from local representations; b) a graph reasoning module propagates information over knowledge graph to achieve global semantic coherency; c) a dual semantic-to-local mapping module learns new associations of the evolved symbolic nodes with local representations, and accordingly enhances local features.
Ranked #81 on Semantic Segmentation on ADE20K val
4 code implementations • CVPR 2019 • Zhiqin Chen, Hao Zhang
We advocate the use of implicit fields for learning generative models of shapes and introduce an implicit field decoder, called IM-NET, for shape generation, aimed at improving the visual quality of the generated shapes.
1 code implementation • ICLR 2020 • Liyao Xiang, Haotian Ma, Hao Zhang, Yifan Zhang, Jie Ren, Quanshi Zhang
Previous studies have found that an adversary attacker can often infer unintended input information from intermediate-layer features.
1 code implementation • 27 Feb 2019 • Fangxin Shang, Hao Zhang
Empirically, we demonstrate the effectiveness of alternating training with synthetic and real gradients after periodic warm restarts on language modeling tasks.
1 code implementation • 27 Feb 2019 • Hao Zhang, Xiuyan Yang, Jianwei Ma
We propose a convolutional neural network (CNN) denoising based method for seismic data interpolation.
no code implementations • 25 Mar 2019 • Kangxue Yin, Zhiqin Chen, Hui Huang, Daniel Cohen-Or, Hao Zhang
Our network consists of an autoencoder to encode shapes from the two input domains into a common latent space, where the latent codes concatenate multi-scale shape features, resulting in an overcomplete representation.
no code implementations • CVPR 2020 • Chenyang Zhu, Kai Xu, Siddhartha Chaudhuri, Li Yi, Leonidas Guibas, Hao Zhang
While the part prior network can be trained with noisy and inconsistently segmented shapes, the final output of AdaCoSeg is a consistent part labeling for the input set, with each shape segmented into up to (a user-specified) K parts.
1 code implementation • ICCV 2019 • Zhiqin Chen, Kangxue Yin, Matthew Fisher, Siddhartha Chaudhuri, Hao Zhang
The unsupervised BAE-NET is trained with a collection of un-segmented shapes, using a shape reconstruction loss, without any ground-truth labels.
no code implementations • 29 Mar 2019 • Zihao Bo, Hao Zhang, Junhai Yong, Feng Xu
We propose a real-time DNN-based technique to segment hand and object of interacting motions from depth inputs.
no code implementations • 1 Apr 2019 • Chuyan Deng, Yuzhong Peng, Hongya Li, Daoqing Gong, Hao Zhang, Zhiping Liu
According to the concentration and dispersion of individual fitness values in population, the crossover rate, mutation rate and real number set mutation rate of genetic operation are dynamically adjusted.
no code implementations • 1 Apr 2019 • Hongya Li, Yuzhong Peng, Chuyan Deng, Yonghua Pan, Daoqing Gong, Hao Zhang
Prompt and accurate precipitation forecast is very important for development management of regional water resource, flood disaster prevention and people's daily activity and production plan; however, non-linear and nonstationary characteristics of precipitation data and noise seriously affect forecast accuracy.
no code implementations • ICLR 2019 • Joey Tianyi Zhou, Hao Zhang, Di Jin, Hongyuan Zhu, Rick Siow Mong Goh, Kenneth Kwok
We propose a new architecture termed Dual Adversarial Transfer Network (DATNet) for addressing low-resource Named Entity Recognition (NER).
Low Resource Named Entity Recognition named-entity-recognition +2
no code implementations • ICLR 2019 • Hao Zhang, Bo Chen, Long Tian, Zhengjue Wang, Mingyuan Zhou
To extract and relate visual and linguistic concepts from images and textual descriptions for text-based zero-shot learning (ZSL), we develop variational hetero-encoder (VHE) that decodes text via a deep probabilisitic topic model, the variational posterior of whose local latent variables is encoded from an image via a Weibull distribution based inference network.
no code implementations • 15 May 2019 • Hao Zhang, Xi-Le Zhao, Tai-Xiang Jiang, Michael Kwok-Po Ng
In this paper, we propose a novel low-tubal-rank tensor recovery model, which directly constrains the tubal rank prior for effectively removing the mixed Gaussian and sparse noise in hyperspectral images.
1 code implementation • ICLR 2020 • Hao Zhang, Bo Chen, Long Tian, Zhengjue Wang, Mingyuan Zhou
For bidirectional joint image-text modeling, we develop variational hetero-encoder (VHE) randomized generative adversarial network (GAN), a versatile deep generative model that integrates a probabilistic text decoder, probabilistic image encoder, and GAN into a coherent end-to-end multi-modality learning framework.
no code implementations • 20 May 2019 • Hao Zhang, Dong E. Liu, Michael Wimmer, Leo P. Kouwenhoven
Majorana zero modes are localized quasiparticles that obey non-Abelian exchange statistics.
Mesoscale and Nanoscale Physics
no code implementations • CL 2019 • Hao Zhang, Richard Sproat, Axel H. Ng, Felix Stahlberg, Xiaochang Peng, Kyle Gorman, Brian Roark
One problem that has been somewhat resistant to effective machine learning solutions is text normalization for speech applications such as text-to-speech synthesis (TTS).
1 code implementation • 10 Jun 2019 • Haotian Ma, Hao Zhang, Fan Zhou, Yinqing Zhang, Quanshi Zhang
We define two types of entropy-based metrics, i. e. (1) the discarding of pixel-wise information used in the forward propagation, and (2) the uncertainty of the input reconstruction, to measure input information contained by a specific layer from two perspectives.
no code implementations • 1 Jul 2019 • Cal Peyser, Hao Zhang, Tara N. Sainath, Zelin Wu
This out-of-vocabulary (OOV) issue is addressed in conventional ASR systems by training part of the model on spoken domain utterances (e. g.
no code implementations • ACL 2019 • Joey Tianyi Zhou, Hao Zhang, Di Jin, Hongyuan Zhu, Meng Fang, Rick Siow Mong Goh, Kenneth Kwok
We propose a new neural transfer method termed Dual Adversarial Transfer Network (DATNet) for addressing low-resource Named Entity Recognition (NER).
2 code implementations • 2 Jul 2019 • Peng Lu, Hao Zhang, Xujun Peng, Xiaofu Jin
In this paper, we primarily focus on improving the accuracy of automatic image cropping, and on further exploring its potential in public datasets with high efficiency.
no code implementations • 13 Aug 2019 • Lin Gao, Jie Yang, Tong Wu, Yu-Jie Yuan, Hongbo Fu, Yu-Kun Lai, Hao Zhang
At the structural level, we train a Structured Parts VAE (SP-VAE), which jointly learns the part structure of a shape collection and the part geometries, ensuring a coherence between global shape structure and surface details.
no code implementations • 17 Aug 2019 • Jingwen Wang, Hao Zhang, Cheng Zhang, Wenjing Yang, Liqun Shao, Jie Wang
To overcome this obstacle, we present NDORGS (Numerous Documents' Overview Report Generation Scheme) that integrates text filtering, keyword scoring, single-document summarization (SDS), topic modeling, MDS, and title generation to generate a coherent, well-structured ORPT.
no code implementations • 25 Sep 2019 • Mufei Li, Hao Zhang, Xingjian Shi, Minjie Wang, Yixing Guan, Zheng Zhang
Does attention matter and, if so, when and how?
no code implementations • 22 Oct 2019 • Haodi Zhang, Zihang Gao, Yi Zhou, Hao Zhang, Kaishun Wu, Fangzhen Lin
Deep reinforcement learning has been successfully used in many dynamic decision making domains, especially those with very large state spaces.
3 code implementations • CVPR 2020 • Zhiqin Chen, Andrea Tagliasacchi, Hao Zhang
The network is trained to reconstruct a shape using a set of convexes obtained from a BSP-tree built on a set of planes.
no code implementations • 20 Nov 2019 • Hao Zhang, Jiayi Chen, Haotian Xue, Quanshi Zhang
This paper proposes a set of criteria to evaluate the objectiveness of explanation methods of neural networks, which is crucial for the development of explainable AI, but it also presents significant challenges.
no code implementations • ECCV 2020 • Jiongchao Jin, Akshay Gadi Patil, Zhang Xiong, Hao Zhang
We introduce a differential visual similarity metric to train deep neural networks for 3D reconstruction, aimed at improving reconstruction quality.
3 code implementations • CVPR 2020 • Rundi Wu, Yixin Zhuang, Kai Xu, Hao Zhang, Baoquan Chen
We introduce PQ-NET, a deep neural network which represents and generates 3D shapes via sequential part assembly.
no code implementations • 11 Dec 2019 • Tianying Wang, Wei Qi Toh, Hao Zhang, Xiuchao Sui, Shaohua Li, Yong liu, Wei Jing
The proposed RoboCoDraw system takes a real human face image as input, converts it to a stylized avatar, then draws it with a robotic arm.
Robotics Graphics
no code implementations • 11 Dec 2019 • Tianying Wang, Hao Zhang, Wei Qi Toh, Hongyuan Zhu, Cheston Tan, Yan Wu, Yong liu, Wei Jing
The proposed method is able to efficiently generalize the previously learned task by model fusion to solve the environment adaptation problem.
no code implementations • 20 Dec 2019 • Deheng Ye, Zhao Liu, Mingfei Sun, Bei Shi, Peilin Zhao, Hao Wu, Hongsheng Yu, Shaojie Yang, Xipeng Wu, Qingwei Guo, Qiaobo Chen, Yinyuting Yin, Hao Zhang, Tengfei Shi, Liang Wang, Qiang Fu, Wei Yang, Lanxiao Huang
We study the reinforcement learning problem of complex action control in the Multi-player Online Battle Arena (MOBA) 1v1 games.
no code implementations • 18 Jan 2020 • Kangfei Zhao, Yu Rong, Jeffrey Xu Yu, Junzhou Huang, Hao Zhang
However, regardless of the fruitful progress, for some kind of graph applications, such as graph compression and edge partition, it is very hard to reduce them to some graph representation learning tasks.
1 code implementation • ECCV 2020 • Wallace Lira, Johannes Merz, Daniel Ritchie, Daniel Cohen-Or, Hao Zhang
Instead of executing translation directly, we steer the translation by requiring the network to produce in-between images that resemble weighted hybrids between images from the input domains.
no code implementations • 4 Mar 2020 • Jun Chen, Yong liu, Hao Zhang, Shengnan Hou, Jian Yang
Meanwhile, we propose a M-bit Inputs and N-bit Weights Network (MINW-Net) trained by AQE, a quantized neural network with 1-3 bits weights and activations.
no code implementations • 16 Mar 2020 • Carole-Jean Wu, Robin Burke, Ed H. Chi, Joseph Konstan, Julian McAuley, Yves Raimond, Hao Zhang
Deep learning-based recommendation models are used pervasively and broadly, for example, to recommend movies, products, or other information most relevant to users, in order to enhance the user experience.
no code implementations • 18 Mar 2020 • Hao Zhang, Yi-Ting Chen, Liyao Xiang, Haotian Ma, Jie Shi, Quanshi Zhang
We propose a method to revise the neural network to construct the quaternion-valued neural network (QNN), in order to prevent intermediate-layer features from leaking input information.
no code implementations • 20 Mar 2020 • Xin-Yu Zhang, Yang Zhao, Hao Zhang
A wealth of angle problems occur when facial recognition is performed: At present, the feature extraction network presents eigenvectors with large differences between the frontal face and profile face recognition of the same person in many cases.
no code implementations • 26 Mar 2020 • Brian Reily, Qingzhao Zhu, Christopher Reardon, Hao Zhang
Real-time human activity recognition plays an essential role in real-world human-centered robotics applications, such as assisted living and human-robot collaboration.
no code implementations • 26 Apr 2020 • Li-ya Xu, Bin Liao, Hao Zhang, Peng Xiao, Jian-jun Huang
Therefore, it is a challenge for target detection in the ocean reverberation with sensor failure.
no code implementations • 27 Apr 2020 • Hao Zhang, Zhan Li, Zhixing Ren
There are lots of sensors in computer rooms for the DC monitoring system, and they are inherently related.
no code implementations • 27 Apr 2020 • Ruizhen Hu, Zeyu Huang, Yuhan Tang, Oliver van Kaick, Hao Zhang, Hui Huang
The core component of our learning framework is a deep neural network, Graph2Plan, which converts a layout graph, along with a building boundary, into a floorplan that fulfills both the layout and boundary constraints.
no code implementations • 28 Apr 2020 • Hao Zhang, Jie Wang
It applies two variants of article-structure-biased PageRank to score phrases and words on the first graph and sentences on the second graph.
1 code implementation • ACL 2020 • Hao Zhang, Aixin Sun, Wei Jing, Joey Tianyi Zhou
Given an untrimmed video and a text query, natural language video localization (NLVL) is to locate a matching span from the video that semantically corresponds to the query.
1 code implementation • 9 May 2020 • Yanran Guan, Han Liu, Kun Liu, Kangxue Yin, Ruizhen Hu, Oliver van Kaick, Yan Zhang, Ersin Yumer, Nathan Carr, Radomir Mech, Hao Zhang
Our tool supports constrained modeling, allowing users to restrict or steer the model evolution with functionality labels.
Graphics
no code implementations • 15 Jun 2020 • Hao Zhang, Bo Chen, Yulai Cong, Dandan Guo, Hongwei Liu, Mingyuan Zhou
Given a posterior sample of the global parameters, in order to efficiently infer the local latent representations of a document under DATM across all stochastic layers, we propose a Weibull upward-downward variational encoder that deterministically propagates information upward via a deep neural network, followed by a Weibull distribution based stochastic downward generative model.
no code implementations • 21 Jun 2020 • Hao Zhang, Yiting Chen, Haotian Ma, Xu Cheng, Qihan Ren, Liyao Xiang, Jie Shi, Quanshi Zhang
Compared to the traditional neural network, the RENN uses d-ary vectors/tensors as features, in which each element is a d-ary number.
1 code implementation • 22 Jun 2020 • Shijing Si, Rui Wang, Jedrek Wosik, Hao Zhang, David Dov, Guoyin Wang, Ricardo Henao, Lawrence Carin
Small and imbalanced datasets commonly seen in healthcare represent a challenge when training classifiers based on deep learning models.
1 code implementation • 26 Jun 2020 • Zihao Yan, Ruizhen Hu, Xingguang Yan, Luanmin Chen, Oliver van Kaick, Hao Zhang, Hui Huang
We show results of simultaneous motion and part predictions from synthetic and real scans of 3D objects exhibiting a variety of part mobilities, possibly involving multiple movable parts.
1 code implementation • 28 Jun 2020 • Ruizhen Hu, Zihao Yan, Jingwen Zhang, Oliver van Kaick, Ariel Shamir, Hao Zhang, Hui Huang
Given a 3D object in isolation, our functional similarity network (fSIM-NET), a variation of the triplet network, is trained to predict the functionality of the object by inferring functionality-revealing interaction contexts.
no code implementations • 29 Jun 2020 • Die Zhang, Huilin Zhou, Hao Zhang, Xiaoyi Bao, Da Huo, Ruizhao Chen, Xu Cheng, Mengyue Wu, Quanshi Zhang
This paper proposes a method to disentangle and quantify interactions among words that are encoded inside a DNN for natural language processing.
no code implementations • ACL 2020 • Ming Yan, Hao Zhang, Di Jin, Joey Tianyi Zhou
Multiple-choice question answering (MCQA) is one of the most challenging tasks in machine reading comprehension since it requires more advanced reading comprehension skills such as logical reasoning, summarization, and arithmetic operations.
1 code implementation • 5 Jul 2020 • Hao Xu, Ka Hei Hui, Chi-Wing Fu, Hao Zhang
To start, we reformulate tiling as a graph problem by modeling candidate tile locations in the target shape as graph nodes and connectivity between tile locations as edges.
no code implementations • NeurIPS 2020 • Xiaogang Wang, Yuelang Xu, Kai Xu, Andrea Tagliasacchi, Bin Zhou, Ali Mahdavi-Amiri, Hao Zhang
We introduce an end-to-end learnable technique to robustly identify feature edges in 3D point cloud data.
no code implementations • 25 Jul 2020 • Rinon Gal, Amit Bermano, Hao Zhang, Daniel Cohen-Or
Our network encourages disentangled generation of semantic parts via two key ingredients: a root-mixing training strategy which helps decorrelate the different branches to facilitate disentanglement, and a set of loss terms designed with part disentanglement and shape semantics in mind.
no code implementations • 5 Aug 2020 • Kangxue Yin, Zhiqin Chen, Siddhartha Chaudhuri, Matthew Fisher, Vladimir G. Kim, Hao Zhang
We introduce COALESCE, the first data-driven framework for component-based shape assembly which employs deep learning to synthesize part connections.
2 code implementations • 27 Aug 2020 • Aurick Qiao, Sang Keun Choe, Suhas Jayaram Subramanya, Willie Neiswanger, Qirong Ho, Hao Zhang, Gregory R. Ganger, Eric P. Xing
Some recent schedulers choose job resources for users, but do so without awareness of how DL training can be re-optimized to better utilize the provided resources.
no code implementations • 3 Sep 2020 • Ruizhen Hu, Juzhan Xu, Bin Chen, Minglun Gong, Hao Zhang, Hui Huang
Using a learning-based approach, a trained network can learn and encode solution patterns to guide the solution of new problem instances instead of executing an expensive online search.
1 code implementation • 22 Sep 2020 • Hao Zhang, Joey Tianyi Zhou, Tianying Wang, Ivor W. Tsang, Rick Siow Mong Goh
To facilitate the training of N-ary ECOC with deep learning base learners, we further propose three different variants of parameter sharing architectures for deep N-ary ECOC.
no code implementations • 23 Sep 2020 • Hao Zhang, Xu Ma, Xianhong Zhao, Gonzalo R. Arce
The accuracy of classification is effectively improved by exploiting the synergy between the deep learning network and coded apertures.
no code implementations • 24 Sep 2020 • Hao Zhang, Sen Li, Yinchao Ma, Mingjie Li, Yichen Xie, Quanshi Zhang
This paper aims to understand and improve the utility of the dropout operation from the perspective of game-theoretic interactions.
no code implementations • 26 Sep 2020 • Tai-Xiang Jiang, Xi-Le Zhao, Hao Zhang, Michael K. Ng
In this paper, we propose a novel tensor learning and coding model for third-order data completion.
no code implementations • 28 Sep 2020 • Zhijie Deng, Xiao Yang, Hao Zhang, Yinpeng Dong, Jun Zhu
Despite their theoretical appealingness, Bayesian neural networks (BNNs) are falling far behind in terms of adoption in real-world applications compared with normal NNs, mainly due to their limited scalability in training, and low fidelity in their uncertainty estimates.
1 code implementation • 5 Oct 2020 • Or Patashnik, Dov Danon, Hao Zhang, Daniel Cohen-Or
State-of-the-art image-to-image translation methods tend to struggle in an imbalanced domain setting, where one image domain lacks richness and diversity.
no code implementations • 6 Oct 2020 • Sicheng Yu, Hao Zhang, Wei Jing, Jing Jiang
In addition to the effective reduction of human efforts of our approach compared, through extensive experiments on OpenbookQA, we show that the proposed approach outperforms the models that use the same backbone and more training data; and our parameter analysis also demonstrates the interpretability of our approach.
no code implementations • 10 Oct 2020 • Hao Zhang, Yichen Xie, Longjie Zheng, Die Zhang, Quanshi Zhang
In this paper, we define and quantify the significance of interactions among multiple input variables of the DNN.
no code implementations • 13 Oct 2020 • Lin Gao, Tong Wu, Yu-Jie Yuan, Ming-Xian Lin, Yu-Kun Lai, Hao Zhang
We introduce a conditional autoregressive model for texture generation, which can be conditioned on both part geometry and textures already generated for other parts to achieve texture compatibility.
Graphics
no code implementations • 14 Oct 2020 • Hao Zhang
This DBBPF is excited by a pair of U-shape feed lines, which are designed on G6 to fully excite the resonators and to introduce source/load TZs at the same time.
no code implementations • 28 Oct 2020 • Hao Zhang, Xu Cheng, Yiting Chen, Quanshi Zhang
In this study, we define interaction components of different orders between two input variables based on game theory.
no code implementations • 1 Nov 2020 • Fengying Che, Ruichuan Shi, Jian Wu, Haoran Li, Shuqin Li, Weixing Chen, Hao Zhang, Zhi Li, Xiaoyu Cui
The feature extraction methods of radiomics are mainly based on static tomographic images at a certain moment, while the occurrence and development of disease is a dynamic process that cannot be fully reflected by only static characteristics.
no code implementations • 2 Nov 2020 • Yang Zhao, Hao Zhang, Xiuyuan Hu
Identifying the role of network units in deep neural networks (DNNs) is critical in many aspects including giving understandings on the mechanisms of DNNs and building basic connections between deep learning and neuroscience.
1 code implementation • 5 Nov 2020 • Hao Zhang, Jae Ro, Richard Sproat
Breaking domain names such as openresearch into component words open and research is important for applications like Text-to-Speech synthesis and web search.
no code implementations • 16 Nov 2020 • Peng Gao, Rui Guo, HongSheng Lu, Hao Zhang
Collaborative object localization aims to collaboratively estimate locations of objects observed from multiple views or perspectives, which is a critical ability for multi-agent systems such as connected vehicles.
no code implementations • ICCV 2021 • Huan Fu, Bowen Cai, Lin Gao, LingXiao Zhang, Jiaming Wang Cao Li, Zengqi Xun, Chengyue Sun, Rongfei Jia, Binqiang Zhao, Hao Zhang
Currently, 3D-FRONT contains 18, 968 rooms diversely furnished by 3D objects, far surpassing all publicly available scene datasets.
1 code implementation • COLING 2020 • Hao Zhang, Jae Ro, Richard Sproat
Breaking domain names such as openresearch into component words open and research is important for applications like Text-to-Speech synthesis and web search.
1 code implementation • NeurIPS 2020 • Wenchao Chen, Chaojie Wang, Bo Chen, Yicheng Liu, Hao Zhang, Mingyuan Zhou
Incorporating the natural document-sentence-word structure into hierarchical Bayesian modeling, we propose convolutional Poisson gamma dynamical systems (PGDS) that introduce not only word-level probabilistic convolutions, but also sentence-level stochastic temporal transitions.
no code implementations • NeurIPS 2020 • Chaojie Wang, Hao Zhang, Bo Chen, Dongsheng Wang, Zhengjue Wang, Mingyuan Zhou
To analyze a collection of interconnected documents, relational topic models (RTMs) have been developed to describe both the link structure and document content, exploring their underlying relationships via a single-layer latent representation with limited expressive capability.
no code implementations • NeurIPS 2020 • Hao Zhang, Yuan Li, Zhijie Deng, Xiaodan Liang, Lawrence Carin, Eric Xing
Synchronization is a key step in data-parallel distributed machine learning (ML).
no code implementations • 7 Dec 2020 • Gengwei Zhang, Yiming Gao, Hang Xu, Hao Zhang, Zhenguo Li, Xiaodan Liang
Panoptic segmentation that unifies instance segmentation and semantic segmentation has recently attracted increasing attention.
Ranked #17 on Panoptic Segmentation on COCO test-dev
no code implementations • 11 Dec 2020 • Manyi Li, Hao Zhang
We present the first single-view 3D reconstruction network aimed at recovering geometric details from an input image which encompass both topological shape structures and surface features.
1 code implementation • CVPR 2021 • Akshay Gadi Patil, Manyi Li, Matthew Fisher, Manolis Savva, Hao Zhang
In particular, retrieval results by our network better match human judgement of structural layout similarity compared to both IoUs and other baselines including a state-of-the-art method based on graph neural networks and image convolution.
no code implementations • 11 Dec 2020 • Liqiang Lin, Pengdi Huang, Chi-Wing Fu, Kai Xu, Hao Zhang, Hui Huang
We present a novel attention-based mechanism to learn enhanced point features for point cloud processing tasks, e. g., classification and segmentation.
1 code implementation • 12 Dec 2020 • Fuzhao Xue, Aixin Sun, Hao Zhang, Eng Siong Chng
Recent advances on RE task are from BERT-based sequence modeling and graph-based modeling of relationships among the tokens in the sequence.
Ranked #4 on Dialog Relation Extraction on DialogRE (F1c (v1) metric)
no code implementations • 16 Dec 2020 • Zhichao Wu, Lei Guo, Hao Zhang, Dan Xu
Unsupervised image segmentation aims at assigning the pixels with similar feature into a same cluster without annotation, which is an important task in computer vision.
1 code implementation • CVPR 2021 • Zhiqin Chen, Vladimir G. Kim, Matthew Fisher, Noam Aigerman, Hao Zhang, Siddhartha Chaudhuri
During testing, a style code is fed into the generator to condition the refinement.
no code implementations • 17 Dec 2020 • Brian Reily, Hao Zhang
In this paper, we propose a novel approach to collaborative multi-robot perception that simultaneously integrates view selection, feature selection, and object recognition into a unified regularized optimization formulation, which uses sparsity-inducing norms to identify the robots with the most representative views and the modalities with the most discriminative features.
1 code implementation • CVPR 2021 • Yiming Qian, Hao Zhang, Yasutaka Furukawa
This paper presents Roof-GAN, a novel generative adversarial network that generates structured geometry of residential roof structures as a set of roof primitives and their relationships.
1 code implementation • 27 Dec 2020 • Fuzhao Xue, Aixin Sun, Hao Zhang, Jinjie Ni, Eng Siong Chng
Dialogue relation extraction (RE) is to predict the relation type of two entities mentioned in a dialogue.
Ranked #9 on Dialog Relation Extraction on DialogRE
no code implementations • ICLR 2021 • Hao Zhang, Sen Li, Yinchao Ma, Mingjie Li, Yichen Xie, Quanshi Zhang
Experimental results on various DNNs and datasets have shown that the interaction loss can effectively improve the utility of dropout and boost the performance of DNNs.
no code implementations • 2 Jan 2021 • Yehua Wei, Lei Zhang, Ruiyi Zhang, Shijing Si, Hao Zhang, Lawrence Carin
Flexibility design problems are a class of problems that appear in strategic decision-making across industries, where the objective is to design a ($e. g.$, manufacturing) network that affords flexibility and adaptivity.
no code implementations • 20 Jan 2021 • Mustafa Ridvan Cantas, Arpita Chand, Hao Zhang, Gopi Chandra Surnilla, Levent Guvenc
The connectivity between vehicles, infrastructure, and other traffic participants brings a new dimension to automotive safety applications.
Decision Making Robotics Systems and Control Systems and Control
no code implementations • 27 Jan 2021 • Hao Zhang, Xinyi Wang, Hai-Bin Yu, Jack F. Douglas
We investigate the Johari-Goldstein (JG) $\beta$-relaxation process in a model metallic glass-forming (GF) material (Al90Sm10), previously studied extensively by both frequency-dependent mechanical measurements and simulation studies devoted to equilibrium properties, by molecular dynamics simulations based on validated and optimized interatomic potentials with the primary aim of better understanding the nature of this universal relaxation process from a dynamic heterogeneity (DH) perspective.
Materials Science
no code implementations • 27 Jan 2021 • Hao Zhang, Michiel W. A. de Moor, Jouri D. S. Bommer, Di Xu, Guanzhong Wang, Nick van Loo, Chun-Xiao Liu, Sasa Gazibegovic, John A. Logan, Diana Car, Roy L. M. Op het Veld, Petrus J. van Veldhoven, Sebastian Koelling, Marcel A. Verheijen, Mihir Pendharkar, Daniel J. Pennachio, Borzoyeh Shojaei, Joon Sue Lee, Chris J. Palmstrøm, Erik P. A. M. Bakkers, S. Das Sarma, Leo P. Kouwenhoven
We report electron transport studies on InSb-Al hybrid semiconductor-superconductor nanowire devices.
Mesoscale and Nanoscale Physics
no code implementations • 28 Jan 2021 • Hao Zhang, Xinyi Wang, Hai-Bin Yu, Jack F. Douglas
We investigate the fast $\beta$- and Johari-Goldstein (JG) $\beta$-relaxation processes, along with the elastic scattering response of glass-forming (GF) liquids and the Boson peak, in a simulated Al-Sm GF material exhibiting a fragile-strong (FS) transition.
Materials Science
1 code implementation • 16 Feb 2021 • Zhuohan Li, Siyuan Zhuang, Shiyuan Guo, Danyang Zhuo, Hao Zhang, Dawn Song, Ion Stoica
With this key idea, we design TeraPipe, a high-performance token-level pipeline parallel algorithm for synchronous model-parallel training of Transformer-based language models.
no code implementations • 26 Feb 2021 • Hao Zhang, Aixin Sun, Wei Jing, Liangli Zhen, Joey Tianyi Zhou, Rick Siow Mong Goh
Our study suggests that the span-based QA framework is an effective strategy to solve the NLVL problem.
2 code implementations • CVPR 2021 • Zhengjue Wang, Hao Zhang, Ziheng Cheng, Bo Chen, Xin Yuan
To capture high-speed videos using a two-dimensional detector, video snapshot compressive imaging (SCI) is a promising system, where the video frames are coded by different masks and then compressed to a snapshot measurement.
no code implementations • 3 Mar 2021 • Hao Zhang, DeLiang Wang
Building on the deep learning based acoustic echo cancellation (AEC) in the single-loudspeaker (single-channel) and single-microphone setup, this paper investigates multi-channel AEC (MCAEC) and multi-microphone AEC (MMAEC).
2 code implementations • CVPR 2021 • Ziheng Cheng, Bo Chen, Guanliang Liu, Hao Zhang, Ruiying Lu, Zhengjue Wang, Xin Yuan
With the knowledge of masks, optimization algorithms or deep learning methods are employed to reconstruct the desired high-speed video frames from this snapshot measurement.
no code implementations • 11 Mar 2021 • Roy L. M. Op het Veld, Di Xu, Vanessa Schaller, Marcel A. Verheijen, Stan M. E. Peters, Jason Jung, Chuyao Tong, Qingzhen Wang, Michiel W. A. de Moor, Bart Hesselmann, Kiefer Vermeulen, Jouri D. S. Bommer, Joon Sue Lee, Andrey Sarikov, Mihir Pendharkar, Anna Marzegalli, Sebastian Koelling, Leo P. Kouwenhoven, Leo Miglio, Chris J. Palmstrøm, Hao Zhang, Erik P. A. M. Bakkers
Strong spin-orbit semiconductor nanowires coupled to a superconductor are predicted to host Majorana zero modes.
Mesoscale and Nanoscale Physics
no code implementations • ICLR 2022 • Yang Zhao, Hao Zhang
We show that by investigating the feature entropy of units on only training data, it could give discrimination between networks with different generalization ability from the view of the effectiveness of feature representations.
no code implementations • 19 Mar 2021 • Honghong Zhou, Caili Guo, Hao Zhang, Yanjun Wang
We evaluate our approach on two standard benchmark datasets for human motion prediction: Human3. 6M and CMU motion capture dataset.
no code implementations • 2 Apr 2021 • Yang Zhao, Hao Zhang
By training DNNs with a wide range of generalization gap on popular datasets, we show that our key quantities and linear model could be efficient tools for estimating the generalization gap of DNNs.
no code implementations • 9 Apr 2021 • Jiongchao Jin, Arezou Fatemi, Wallace Lira, Fenggen Yu, Biao Leng, Rui Ma, Ali Mahdavi-Amiri, Hao Zhang
We introduce RaidaR, a rich annotated image dataset of rainy street scenes, to support autonomous driving research.
no code implementations • CVPR 2022 • Fenggen Yu, Zhiqin Chen, Manyi Li, Aditya Sanghi, Hooman Shayani, Ali Mahdavi-Amiri, Hao Zhang
We introduce CAPRI-Net, a neural network for learning compact and interpretable implicit representations of 3D computer-aided design (CAD) models, in the form of adaptive primitive assemblies.
1 code implementation • 8 May 2021 • Huangjie Zheng, Xu Chen, Jiangchao Yao, Hongxia Yang, Chunyuan Li, Ya zhang, Hao Zhang, Ivor Tsang, Jingren Zhou, Mingyuan Zhou
We realize this strategy with contrastive attraction and contrastive repulsion (CACR), which makes the query not only exert a greater force to attract more distant positive samples but also do so to repel closer negative samples.
no code implementations • 11 May 2021 • Qiang Hu, Feifei Gao, Hao Zhang, Geoffrey Y. Li, Zongben Xu
We demonstrate that data-driven DL detector asymptotically approaches to the maximum a posterior (MAP) detector in various scenarios but requires enough training samples to converge in time-varying channels.
1 code implementation • 13 May 2021 • Hao Zhang, Aixin Sun, Wei Jing, Guoshun Nan, Liangli Zhen, Joey Tianyi Zhou, Rick Siow Mong Goh
We adopt the first approach and introduce two contrastive learning objectives to refine video encoder and text encoder to learn video and text representations separately but with better alignment for VCMR.
no code implementations • Findings (ACL) 2021 • Hao Zhang, Aixin Sun, Wei Jing, Liangli Zhen, Joey Tianyi Zhou, Rick Siow Mong Goh
In this work, we propose a Parallel Attention Network with Sequence matching (SeqPAN) to address the challenges in this task: multi-modal representation learning, and target moment boundary prediction.
1 code implementation • 24 May 2021 • Tianming Liang, Yang Liu, Xiaoyan Liu, Hao Zhang, Gaurav Sharma, Maozu Guo
On top of that, we further propose a novel constraint graph-based relation extraction framework(CGRE) to handle the two challenges simultaneously.
3 code implementations • 31 May 2021 • Fuxiang Tan, YuTing Kong, Yingying Fan, Feng Liu, Daxin Zhou, Hao Zhang, Long Chen, Liang Gao, Yurong Qian
The former implements the basic rain pattern feature extraction, while the latter fuses different features to further extract and process the image features.
no code implementations • 31 May 2021 • Hao Zhang, Fuhui Zhou, Qihui Wu, Wei Wu, Rose Qingyang Hu
Moreover, a novel loss function that combines the center loss and the cross entropy loss is exploited to learn both discriminative and separable features in order to further improve the classification performance.
no code implementations • CVPR 2021 • Manyi Li, Hao Zhang
We present the first single-view 3D reconstruction network aimed at recovering geometric details from an input image which encompass both topological shape structures and surface features.
1 code implementation • CVPR 2021 • Guoshun Nan, Rui Qiao, Yao Xiao, Jun Liu, Sicong Leng, Hao Zhang, Wei Lu
2) Meanwhile, we introduce a dual contrastive learning approach (DCL) to better align the text and video by maximizing the mutual information (MI) between query and video clips, and the MI between start/end frames of a target moment and the others within a video to learn more informative visual representations.
1 code implementation • 21 Jun 2021 • Zhiqin Chen, Hao Zhang
To tackle these challenges, we re-cast MC from a deep learning perspective, by designing tessellation templates more apt at preserving geometric features, and learning the vertex positions and mesh topologies from training meshes, to account for contextual information from nearby cubes.
1 code implementation • 27 Jun 2021 • Zhiqin Chen, Andrea Tagliasacchi, Hao Zhang
The network is trained to reconstruct a shape using a set of convexes obtained from a BSP-tree built over a set of planes, where the planes and convexes are both defined by learned network weights.
no code implementations • ACL 2021 • Xiaoxue Zang, Lijuan Liu, Maria Wang, Yang song, Hao Zhang, Jindong Chen
Based on this dataset, we propose two tasks to facilitate research on image-text modeling: a photo-sharing intent prediction task that predicts whether one intends to share a photo in the next conversation turn, and a photo retrieval task that retrieves the most relevant photo according to the dialogue context.
Ranked #5 on Image Retrieval on PhotoChat
no code implementations • 13 Jul 2021 • Haocheng Ren, Hao Zhang, Jia Zheng, Jiaxiang Zheng, Rui Tang, Yuchi Huo, Hujun Bao, Rui Wang
With the rapid development of data-driven techniques, data has played an essential role in various computer vision tasks.
no code implementations • 14 Jul 2021 • Hao Zhang, Deyang Duan
There is a consensus that turbulence-free images cannot be obtained by conventional computational ghost imaging (CGI) because the CGI is only a classic simulation, which does not satisfy the conditions of turbulence-free imaging.
no code implementations • 16 Jul 2021 • Quanshi Zhang, Tian Han, Lixin Fan, Zhanxing Zhu, Hang Su, Ying Nian Wu, Jie Ren, Hao Zhang
This workshop pays a special interest in theoretic foundations, limitations, and new application trends in the scope of XAI.
1 code implementation • ACL 2021 • Sicheng Yu, Hao Zhang, Yulei Niu, Qianru Sun, Jing Jiang
Pre-trained multilingual language models, e. g., multilingual-BERT, are widely used in cross-lingual tasks, yielding the state-of-the-art performance.
1 code implementation • ACL 2021 • Zhibin Duan, Hao Zhang, Chaojie Wang, Zhengjue Wang, Bo Chen, Mingyuan Zhou
As a result, the backbone learns the shared knowledge among all clusters while modulated weights extract the cluster-specific features.
3 code implementations • 5 Aug 2021 • Hao Zhang, Yanbin Hao, Chong-Wah Ngo
It is worth noticing that our TokShift transformer is a pure convolutional-free video transformer pilot with computational efficiency for video understanding.
no code implementations • ICCV 2021 • Xin Wang, Shuyun Lin, Hao Zhang, Yufei Zhu, Quanshi Zhang
This paper aims to explain adversarial attacks in terms of how adversarial perturbations contribute to the attacking task.
no code implementations • 23 Aug 2021 • Hao Zhang, Lu Yuan, Guangyu Wu, Fuhui Zhou, Qihui Wu
Automatic modulation classification (AMC) is of crucial importance for realizing wireless intelligence communications.
no code implementations • 24 Aug 2021 • Qingcai Wang, Hao Zhang, Xianggong Hong, Qinqin Zhou
Small objects have relatively low resolution, the unobvious visual features which are difficult to be extracted, so the existing object detection methods cannot effectively detect small objects, and the detection speed and stability are poor.
no code implementations • 25 Aug 2021 • Hao Zhang, Xianggong Hong, Li Zhu
In this paper, we proposed DDSSD (Dilation and Deconvolution Single Shot Multibox Detector), an enhanced SSD with a novel feature fusion module which can improve the performance over SSD for small object detection.
no code implementations • 26 Aug 2021 • Hao Zhang, You-Chi Cheng, Shankar Kumar, Mingqing Chen, Rajiv Mathews
Truecasing is the task of restoring the correct case (uppercase or lowercase) of noisy text generated either by an automatic system for speech recognition or machine translation or by humans.
no code implementations • 29 Sep 2021 • Yilin He, Chaojie Wang, Hao Zhang, Bo Chen, Mingyuan Zhou
In this paper, we introduce a relational graph generative process to model how the observed edges are generated by aggregating the node interactions over multiple overlapping node communities, each of which represents a particular type of relation that contributes to the edges via a logical OR mechanism.
1 code implementation • NeurIPS 2021 • Korawat Tanwisuth, Xinjie Fan, Huangjie Zheng, Shujian Zhang, Hao Zhang, Bo Chen, Mingyuan Zhou
Existing methods for unsupervised domain adaptation often rely on minimizing some statistical distance between the source and target samples in the latent space.
no code implementations • 31 Oct 2021 • BoJian Hou, Hao Zhang, Gur Ladizhinsky, Stephen Yang, Volodymyr Kuleshov, Fei Wang, Qian Yang
As a result, clinicians cannot easily or rapidly scrutinize the CDSS recommendation when facing a difficult diagnosis or treatment decision in practice.
no code implementations • 5 Nov 2021 • Peng Gao, Brian Reily, Rui Guo, HongSheng Lu, Qingzhao Zhu, Hao Zhang
In this paper, we introduce a novel approach that integrates uncertainty-aware spatiotemporal graph learning and model-based state estimation for a team of robots to collaboratively localize objects.
no code implementations • 8 Nov 2021 • Hao Zhang, Aixin Sun, Wei Jing, Joey Tianyi Zhou
In this paper, we propose two debiasing strategies, data debiasing and model debiasing, to "force" a TSGV model to capture cross-modal interactions.
1 code implementation • ICLR 2022 • Huiqi Deng, Qihan Ren, Hao Zhang, Quanshi Zhang
This paper explores the bottleneck of feature representations of deep neural networks (DNNs), from the perspective of the complexity of interactions between input variables encoded in DNNs.
no code implementations • 12 Nov 2021 • Sriram Siva, Maggie Wigness, John G. Rogers, Long Quang, Hao Zhang
Ground robots require the crucial capability of traversing unstructured and unprepared terrains and avoiding obstacles to complete tasks in real-world robotics applications such as disaster response.