Search Results for author: Hao Yang

Found 87 papers, 20 papers with code

Efficient Transfer Learning for Quality Estimation with Bottleneck Adapter Layer

no code implementations EAMT 2020 Hao Yang, Minghan Wang, Ning Xie, Ying Qin, Yao Deng

Compared with the commonly used NuQE baseline, BAL-QE achieves 47% (En-Ru) and 75% (En-De) of performance promotions.

Transfer Learning

HI-CMLM: Improve CMLM with Hybrid Decoder Input

no code implementations INLG (ACL) 2021 Minghan Wang, Guo Jiaxin, Yuxia Wang, Yimeng Chen, Su Chang, Daimeng Wei, Min Zhang, Shimin Tao, Hao Yang

Mask-predict CMLM (Ghazvininejad et al., 2019) has achieved stunning performance among non-autoregressive NMT models, but we find that the mechanism of predicting all of the target words only depending on the hidden state of [MASK] is not effective and efficient in initial iterations of refinement, resulting in ungrammatical repetitions and slow convergence.

Translation

Make the Blind Translator See The World: A Novel Transfer Learning Solution for Multimodal Machine Translation

no code implementations MTSummit 2021 Minghan Wang, Jiaxin Guo, Yimeng Chen, Chang Su, Min Zhang, Shimin Tao, Hao Yang

Based on large-scale pretrained networks and the liability to be easily overfitting with limited labelled training data of multimodal translation (MMT) is a critical issue in MMT.

Multimodal Machine Translation Transfer Learning +1

HW-TSC’s Submissions to the WMT21 Biomedical Translation Task

no code implementations WMT (EMNLP) 2021 Hao Yang, Zhanglin Wu, Zhengzhe Yu, Xiaoyu Chen, Daimeng Wei, Zongyao Li, Hengchao Shang, Minghan Wang, Jiaxin Guo, Lizhi Lei, Chuanfei Xu, Min Zhang, Ying Qin

This paper describes the submission of Huawei Translation Service Center (HW-TSC) to WMT21 biomedical translation task in two language pairs: Chinese↔English and German↔English (Our registered team name is HuaweiTSC).

Translation

Exploring Entity Interactions for Few-Shot Relation Learning (Student Abstract)

no code implementations4 May 2022 Yi Liang, Shuai Zhao, Bo Cheng, Yuwei Yin, Hao Yang

Few-shot relation learning refers to infer facts for relations with a limited number of observed triples.

Metric Learning

Neighbors Are Not Strangers: Improving Non-Autoregressive Translation under Low-Frequency Lexical Constraints

1 code implementation28 Apr 2022 Chun Zeng, Jiangjie Chen, Tianyi Zhuang, Rui Xu, Hao Yang, Ying Qin, Shimin Tao, Yanghua Xiao

To this end, we propose a plug-in algorithm for this line of work, i. e., Aligned Constrained Training (ACT), which alleviates this problem by familiarizing the model with the source-side context of the constraints.

Translation

Real-Time Neural Character Rendering with Pose-Guided Multiplane Images

no code implementations25 Apr 2022 Hao Ouyang, Bo Zhang, Pan Zhang, Hao Yang, Jiaolong Yang, Dong Chen, Qifeng Chen, Fang Wen

We propose pose-guided multiplane image (MPI) synthesis which can render an animatable character in real scenes with photorealistic quality.

Image-to-Image Translation Novel View Synthesis

Large-Scale Pre-training for Person Re-identification with Noisy Labels

2 code implementations30 Mar 2022 Dengpan Fu, Dongdong Chen, Hao Yang, Jianmin Bao, Lu Yuan, Lei Zhang, Houqiang Li, Fang Wen, Dong Chen

Since theses ID labels automatically derived from tracklets inevitably contain noises, we develop a large-scale Pre-training framework utilizing Noisy Labels (PNL), which consists of three learning modules: supervised Re-ID learning, prototype-based contrastive learning, and label-guided contrastive learning.

Contrastive Learning Multi-Object Tracking +3

Omni-DETR: Omni-Supervised Object Detection with Transformers

no code implementations30 Mar 2022 Pei Wang, Zhaowei Cai, Hao Yang, Gurumurthy Swaminathan, Nuno Vasconcelos, Bernt Schiele, Stefano Soatto

This is enabled by a unified architecture, Omni-DETR, based on the recent progress on student-teacher framework and end-to-end transformer based object detection.

Object Detection Semi-Supervised Object Detection

Sentiment Word Aware Multimodal Refinement for Multimodal Sentiment Analysis with ASR Errors

1 code implementation Findings (ACL) 2022 Yang Wu, Yanyan Zhao, Hao Yang, Song Chen, Bing Qin, Xiaohuan Cao, Wenting Zhao

Through further analysis of the ASR outputs, we find that in some cases the sentiment words, the key sentiment elements in the textual modality, are recognized as other words, which makes the sentiment of the text change and hurts the performance of multimodal sentiment models directly.

Automatic Speech Recognition Multimodal Sentiment Analysis +1

Rethinking Feature Uncertainty in Stochastic Neural Networks for Adversarial Robustness

no code implementations1 Jan 2022 Hao Yang, Min Wang, Zhengfei Yu, Yun Zhou

Extensive experiments on well-known white- and black-box attacks show that MFDV-SNN achieves a significant improvement over existing methods, which indicates that it is a simple but effective method to improve model robustness.

Adversarial Robustness

Self-Distillation Mixup Training for Non-autoregressive Neural Machine Translation

no code implementations22 Dec 2021 Jiaxin Guo, Minghan Wang, Daimeng Wei, Hengchao Shang, Yuxia Wang, Zongyao Li, Zhengzhe Yu, Zhanglin Wu, Yimeng Chen, Chang Su, Min Zhang, Lizhi Lei, Shimin Tao, Hao Yang

An effective training strategy to improve the performance of AT models is Self-Distillation Mixup (SDM) Training, which pre-trains a model on raw data, generates distilled data by the pre-trained model itself and finally re-trains a model on the combination of raw data and distilled data.

Knowledge Distillation Machine Translation +1

Joint-training on Symbiosis Networks for Deep Nueral Machine Translation models

no code implementations22 Dec 2021 Zhengzhe Yu, Jiaxin Guo, Minghan Wang, Daimeng Wei, Hengchao Shang, Zongyao Li, Zhanglin Wu, Yuxia Wang, Yimeng Chen, Chang Su, Min Zhang, Lizhi Lei, Shimin Tao, Hao Yang

Deep encoders have been proven to be effective in improving neural machine translation (NMT) systems, but it reaches the upper bound of translation quality when the number of encoder layers exceeds 18.

14 Machine Translation +1

General Facial Representation Learning in a Visual-Linguistic Manner

1 code implementation6 Dec 2021 Yinglin Zheng, Hao Yang, Ting Zhang, Jianmin Bao, Dongdong Chen, Yangyu Huang, Lu Yuan, Dong Chen, Ming Zeng, Fang Wen

In this paper, we study the transfer performance of pre-trained models on face analysis tasks and introduce a framework, called FaRL, for general Facial Representation Learning in a visual-linguistic manner.

 Ranked #1 on Face Parsing on CelebAMask-HQ (using extra training data)

Face Alignment Face Parsing +1

Delayed Propagation Transformer: A Universal Computation Engine towards Practical Control in Cyber-Physical Systems

1 code implementation NeurIPS 2021 Wenqing Zheng, Qiangqiang Guo, Hao Yang, Peihao Wang, Zhangyang Wang

This paper presents the Delayed Propagation Transformer (DePT), a new transformer-based model that specializes in the global modeling of CPS while taking into account the immutable constraints from the physical world.

Few-shot graph link prediction with domain adaptation

no code implementations29 Sep 2021 Hao Zhu, Mahashweta Das, Mangesh Bendre, Fei Wang, Hao Yang, Soha Hassoun

In this work, we propose an adversarial training based modification to the current state-of-the-arts link prediction method to solve this problem.

Domain Adaptation Few-Shot Learning +1

ADNet: Leveraging Error-Bias Towards Normal Direction in Face Alignment

no code implementations ICCV 2021 Yangyu Huang, Hao Yang, Chong Li, Jongyoo Kim, Fangyun Wei

On the other hand, AAM is an attention module which can get anisotropic attention mask focusing on the region of point and its local edge connected by adjacent points, it has a stronger response in tangent than in normal, which means relaxed constraints in the tangent.

Face Alignment

How Does Adversarial Fine-Tuning Benefit BERT?

no code implementations31 Aug 2021 Javid Ebrahimi, Hao Yang, Wei zhang

Adversarial training (AT) is one of the most reliable methods for defending against adversarial attacks in machine learning.

Continual Learning Dependency Parsing +2

Event2Graph: Event-driven Bipartite Graph for Multivariate Time-series Anomaly Detection

no code implementations15 Aug 2021 Yuhang Wu, Mengting Gu, Lan Wang, Yusan Lin, Fei Wang, Hao Yang

Modeling inter-dependencies between time-series is the key to achieve high performance in anomaly detection for multivariate time-series data.

Anomaly Detection Time Series

Task and Situation Structures for Service Agent Planning

no code implementations27 Jul 2021 Hao Yang, Tavan Eftekhar, Chad Esselink, Yan Ding, Shiqi Zhang

Everyday tasks are characterized by their varieties and variations, and frequently are not clearly specified to service agents.

Patch-Wise Spatial-Temporal Quality Enhancement for HEVC Compressed Video

1 code implementation journal 2021 Qing Ding, Liquan Shen, Liangwei Yu, Hao Yang, Mai Xu

To overcome these limitations, we propose a patch-wise spatial-temporal quality enhancement network which firstly extracts spatial and temporal features, then recalibrates and fuses the obtained spatial and temporal features.

Frame Quantization +1

Normalization of Language Embeddings for Cross-Lingual Alignment

1 code implementation NeurIPS 2021 Prince Osei Aboagye, Jeff Phillips, Yan Zheng, Chin-Chia Michael Yeh, Junpeng Wang, Wei zhang, Liang Wang, Hao Yang

Learning a good transfer function to map the word vectors from two languages into a shared cross-lingual word vector space plays a crucial role in cross-lingual NLP.

Translation

Pick and Choose: A GNN-based Imbalanced Learning Approach for Fraud Detection

1 code implementation The Web Conference 2021 Yang Liu1, Xiang Ao, Zidi Qin, Jianfeng Chi, Jinghua Feng, Hao Yang, Qing He

Graph-based fraud detection approaches have escalated lots of attention recently due to the abundant relational information of graph-structured data, which may be beneficial for the detection of fraudsters.

Fraud Detection Node Classification

Integrating Subgraph-aware Relation and DirectionReasoning for Question Answering

no code implementations1 Apr 2021 Xu Wang, Shuai Zhao, Bo Cheng, Jiale Han, Yingting Li, Hao Yang, Ivan Sekulic, Guoshun Nan

Question Answering (QA) models over Knowledge Bases (KBs) are capable of providing more precise answers by utilizing relation information among entities.

Question Answering

Learning from Noisy Labels via Dynamic Loss Thresholding

no code implementations1 Apr 2021 Hao Yang, Youzhi Jin, Ziyin Li, Deng-Bao Wang, Lei Miao, Xin Geng, Min-Ling Zhang

During the training process, DLT records the loss value of each sample and calculates dynamic loss thresholds.

Style-based Point Generator with Adversarial Rendering for Point Cloud Completion

1 code implementation CVPR 2021 Chulin Xie, Chuxin Wang, Bo Zhang, Hao Yang, Dong Chen, Fang Wen

In this paper, we proposed a novel Style-based Point Generator with Adversarial Rendering (SpareNet) for point cloud completion.

 Ranked #1 on Point Cloud Completion on ShapeNet (Earth Mover's Distance metric)

Point Cloud Completion

Adversarial Example Detection Using Latent Neighborhood Graph

no code implementations ICCV 2021 Ahmed Abusnaina, Yuhang Wu, Sunpreet Arora, Yizhen Wang, Fei Wang, Hao Yang, David Mohaisen

We present the first graph-based adversarial detection method that constructs a Latent Neighborhood Graph (LNG) around an input example to determine if the input example is adversarial.

Adversarial Attack Graph Attention

On Position Embeddings in BERT

no code implementations ICLR 2021 Benyou Wang, Lifeng Shang, Christina Lioma, Xin Jiang, Hao Yang, Qun Liu, Jakob Grue Simonsen

Various Position Embeddings (PEs) have been proposed in Transformer based architectures~(e. g. BERT) to model word order.

General Classification Translation

Beating Attackers At Their Own Games: Adversarial Example Detection Using Adversarial Gradient Directions

no code implementations31 Dec 2020 Yuhang Wu, Sunpreet S. Arora, Yanhong Wu, Hao Yang

Adversarial examples are input examples that are specifically crafted to deceive machine learning classifiers.

Unsupervised Pre-training for Person Re-identification

1 code implementation CVPR 2021 Dengpan Fu, Dongdong Chen, Jianmin Bao, Hao Yang, Lu Yuan, Lei Zhang, Houqiang Li, Dong Chen

In this paper, we present a large scale unlabeled person re-identification (Re-ID) dataset "LUPerson" and make the first attempt of performing unsupervised pre-training for improving the generalization ability of the learned person Re-ID feature representation.

Ranked #2 on Person Re-Identification on Market-1501 (using extra training data)

Data Augmentation Person Re-Identification +1

Gaussian State-Based Quantum Illumination with Simple Photodetection

no code implementations27 Nov 2020 Hao Yang, Wojciech Roga, Jonathan D. Pritchard, John Jeffers

We use the continuous-variable Gaussian quantum information formalism to show that quantum illumination is better for object detection compared with coherent states of the same mean photon number, even for simple direct photodetection.

Object Detection Quantum Physics

A coarse-to-fine framework for unsupervised multi-contrast MR image deformable registration with dual consistency constraint

no code implementations5 Aug 2020 Weijian Huang, Hao Yang, Xinfeng Liu, Cheng Li, Ian Zhang, Rongpin Wang, Hairong Zheng, Shan-Shan Wang

Multi-contrast magnetic resonance (MR) image registration is useful in the clinic to achieve fast and accurate imaging-based disease diagnosis and treatment planning.

Image Registration

Edge Computing for Real-Time Near-Crash Detection for Smart Transportation Applications

no code implementations2 Aug 2020 Ruimin Ke, Zhiyong Cui, Yanlong Chen, Meixin Zhu, Hao Yang, Yinhai Wang

It is among the first efforts in applying edge computing for real-time traffic video analytics and is expected to benefit multiple sub-fields in smart transportation research and applications.

Autonomous Driving Edge-computing +1

Category-Specific CNN for Visual-aware CTR Prediction at JD.com

no code implementations18 Jun 2020 Hu Liu, Jing Lu, Hao Yang, Xiwei Zhao, Sulong Xu, Hao Peng, Zehua Zhang, Wenjie Niu, Xiaokun Zhu, Yongjun Bao, Weipeng Yan

Existing algorithms usually extract visual features using off-the-shelf Convolutional Neural Networks (CNNs) and late fuse the visual and non-visual features for the finally predicted CTR.

Click-Through Rate Prediction

GroupIM: A Mutual Information Maximization Framework for Neural Group Recommendation

1 code implementation5 Jun 2020 Aravind Sankar, Yanhong Wu, Yuhang Wu, Wei zhang, Hao Yang, Hari Sundaram

We study the problem of making item recommendations to ephemeral groups, which comprise users with limited or no historical activities together.

Transfer Learning via Contextual Invariants for One-to-Many Cross-Domain Recommendation

no code implementations21 May 2020 Adit Krishnan, Mahashweta Das, Mangesh Bendre, Hao Yang, Hari Sundaram

The rapid proliferation of new users and items on the social web has aggravated the gray-sheep user/long-tail item challenge in recommender systems.

Collaborative Filtering Recommendation Systems +1

Fashion Recommendation and Compatibility Prediction Using Relational Network

no code implementations13 May 2020 Maryam Moosaei, Yusan Lin, Hao Yang

There are a few approaches that consider an entire outfit, but these approaches have limitations such as requiring rich semantic information, category labels, and fixed order of items.

Adversarial Light Projection Attacks on Face Recognition Systems: A Feasibility Study

no code implementations24 Mar 2020 Dinh-Luan Nguyen, Sunpreet S. Arora, Yuhang Wu, Hao Yang

While feasible, digital attacks have limited applicability in attacking deployed systems, including face recognition systems, where an adversary typically has access to the input and not the transmission channel.

Face Recognition

Feedback Graph Convolutional Network for Skeleton-based Action Recognition

no code implementations17 Mar 2020 Hao Yang, Dan Yan, Li Zhang, Dong Li, YunDa Sun, ShaoDi You, Stephen J. Maybank

It transmits the high-level semantic features to the low-level layers and flows temporal information stage by stage to progressively model global spatial-temporal features for action recognition; (3) The FGCN model provides early predictions.

Action Recognition Skeleton Based Action Recognition

Rethinking the Hyperparameters for Fine-tuning

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.

Transfer Learning

Multi-Task Incremental Learning for Object Detection

no code implementations13 Feb 2020 Xialei Liu, Hao Yang, Avinash Ravichandran, Rahul Bhotika, Stefano Soatto

For the difficult cases, where the domain gaps and especially category differences are large, we explore three different exemplar sampling methods and show the proposed adaptive sampling method is effective to select diverse and informative samples from entire datasets, to further prevent forgetting.

Incremental Learning Object Detection

Face X-ray for More General Face Forgery Detection

3 code implementations CVPR 2020 Lingzhi Li, Jianmin Bao, Ting Zhang, Hao Yang, Dong Chen, Fang Wen, Baining Guo

For this reason, face X-ray provides an effective way for detecting forgery generated by most existing face manipulation algorithms.

DeepFake Detection Face Swapping

FaceShifter: Towards High Fidelity And Occlusion Aware Face Swapping

8 code implementations31 Dec 2019 Lingzhi Li, Jianmin Bao, Hao Yang, Dong Chen, Fang Wen

We propose a novel attributes encoder for extracting multi-level target face attributes, and a new generator with carefully designed Adaptive Attentional Denormalization (AAD) layers to adaptively integrate the identity and the attributes for face synthesis.

Face Generation Face Swapping

motif2vec: Motif Aware Node Representation Learning for Heterogeneous Networks

no code implementations22 Aug 2019 Manoj Reddy Dareddy, Mahashweta Das, Hao Yang

Supervised machine learning tasks in networks such as node classification and link prediction require us to perform feature engineering that is known and agreed to be the key to success in applied machine learning.

Feature Engineering Link Prediction +2

Detecting 11K Classes: Large Scale Object Detection without Fine-Grained Bounding Boxes

no code implementations ICCV 2019 Hao Yang, Hao Wu, Hao Chen

However, these methods require fully annotated object bounding boxes for training, which are incredibly hard to scale up due to the high annotation cost.

Object Detection Re-Ranking

Position Focused Attention Network for Image-Text Matching

1 code implementation23 Jul 2019 Yaxiong Wang, Hao Yang, Xueming Qian, Lin Ma, Jing Lu, Biao Li, Xin Fan

Then, an attention mechanism is proposed to model the relations between the image region and blocks and generate the valuable position feature, which will be further utilized to enhance the region expression and model a more reliable relationship between the visual image and the textual sentence.

Text Matching

CLCI-Net: Cross-Level fusion and Context Inference Networks for Lesion Segmentation of Chronic Stroke

2 code implementations16 Jul 2019 Hao Yang, Weijian Huang, Kehan Qi, Cheng Li, Xinfeng Liu, Meiyun Wang, Hairong Zheng, Shan-Shan Wang

To address these challenges, this paper proposes a Cross-Level fusion and Context Inference Network (CLCI-Net) for the chronic stroke lesion segmentation from T1-weighted MR images.

Lesion Segmentation Semantic Segmentation

Face Parsing with RoI Tanh-Warping

1 code implementation CVPR 2019 Jinpeng Lin, Hao Yang, Dong Chen, Ming Zeng, Fang Wen, Lu Yuan

It uses hierarchical local based method for inner facial components and global methods for outer facial components.

Face Parsing

Real-Time Steganalysis for Stream Media Based on Multi-channel Convolutional Sliding Windows

no code implementations4 Feb 2019 Zhongliang Yang, Hao Yang, Yuting Hu, Yongfeng Huang, Yu-Jin Zhang

To solve these two challenges, in this paper, combined with the sliding window detection algorithm and Convolution Neural Network we propose a real-time VoIP steganalysis method which based on multi-channel convolution sliding windows.

Window Detection

Dynamic Graph Representation Learning via Self-Attention Networks

2 code implementations22 Dec 2018 Aravind Sankar, Yanhong Wu, Liang Gou, Wei zhang, Hao Yang

Learning latent representations of nodes in graphs is an important and ubiquitous task with widespread applications such as link prediction, node classification, and graph visualization.

General Classification Graph Embedding +3

An End-to-End Multi-task Learning Model for Fact Checking

no code implementations WS 2018 Sizhen Li, Shuai Zhao, Bo Cheng, Hao Yang

With huge amount of information generated every day on the web, fact checking is an important and challenging task which can help people identify the authenticity of most claims as well as providing evidences selected from knowledge source like Wikipedia.

Common Sense Reasoning Entity Linking +4

Exploiting Web Images for Weakly Supervised Object Detection

no code implementations27 Jul 2017 Qingyi Tao, Hao Yang, Jianfei Cai

Object detection without bounding box annotations, i. e, weakly supervised detection methods, are still lagging far behind.

Ranked #15 on Weakly Supervised Object Detection on PASCAL VOC 2012 test (using extra training data)

Transfer Learning Weakly Supervised Object Detection

MIML-FCN+: Multi-instance Multi-label Learning via Fully Convolutional Networks with Privileged Information

no code implementations CVPR 2017 Hao Yang, Joey Tianyi Zhou, Jianfei Cai, Yew Soon Ong

As the proposed PI loss is convex and SGD compatible and the framework itself is a fully convolutional network, MIML-FCN+ can be easily integrated with state of-the-art deep learning networks.

Image Captioning Multi-Label Learning +1

Improving Multi-label Learning with Missing Labels by Structured Semantic Correlations

no code implementations4 Aug 2016 Hao Yang, Joey Tianyi Zhou, Jianfei Cai

Experimental results demonstrate the effectiveness of the proposed semantic descriptor and the usefulness of incorporating the structured semantic correlations.

Multi-Label Learning Object Recognition

A Comparative Study of Object Trackers for Infrared Flying Bird Tracking

no code implementations18 Jan 2016 Ying Huang, Hong Zheng, Haibin Ling, Erik Blasch, Hao Yang

Bird strikes present a huge risk for aircraft, especially since traditional airport bird surveillance is mainly dependent on inefficient human observation.

A Parallel Way to Select the Parameters of SVM Based on the Ant Optimization Algorithm

no code implementations19 May 2014 Chao Zhang, Hong-cen Mei, Hao Yang

A large number of experimental data shows that Support Vector Machine (SVM) algorithm has obvious advantages in text classification, handwriting recognition, image classification, bioinformatics, and some other fields.

Classification General Classification +3

Cannot find the paper you are looking for? You can Submit a new open access paper.