Search Results for author: Jing Liu

Found 83 papers, 23 papers with code

Learning Progressive Joint Propagation for Human Motion Prediction

no code implementations ECCV 2020 Yujun Cai, Lin Huang, Yiwei Wang, Tat-Jen Cham, Jianfei Cai, Junsong Yuan, Jun Liu, Xu Yang, Yiheng Zhu, Xiaohui Shen, Ding Liu, Jing Liu, Nadia Magnenat Thalmann

Last, in order to incorporate a general motion space for high-quality prediction, we build a memory-based dictionary, which aims to preserve the global motion patterns in training data to guide the predictions.

Human motion prediction motion prediction

Deep Transferring Quantization

1 code implementation ECCV 2020 Zheng Xie, Zhiquan Wen, Jing Liu, Zhi-Qiang Liu, Xixian Wu, Mingkui Tan

Specifically, we propose a method named deep transferring quantization (DTQ) to effectively exploit the knowledge in a pre-trained full-precision model.

Face Recognition Image Classification +2

Exploiting Spatial-Temporal Semantic Consistency for Video Scene Parsing

no code implementations6 Sep 2021 Xingjian He, Weining Wang, Zhiyong Xu, Hao Wang, Jie Jiang, Jing Liu

Compared with image scene parsing, video scene parsing introduces temporal information, which can effectively improve the consistency and accuracy of prediction.

Scene Parsing

PAIR: Leveraging Passage-Centric Similarity Relation for Improving Dense Passage Retrieval

1 code implementation13 Aug 2021 Ruiyang Ren, Shangwen Lv, Yingqi Qu, Jing Liu, Wayne Xin Zhao, Qiaoqiao She, Hua Wu, Haifeng Wang, Ji-Rong Wen

Recently, dense passage retrieval has become a mainstream approach to finding relevant information in various natural language processing tasks.

Knowledge Distillation Passage Retrieval

Elastic Architecture Search for Diverse Tasks with Different Resources

no code implementations3 Aug 2021 Jing Liu, Bohan Zhuang, Mingkui Tan, Xu Liu, Dinh Phung, Yuanqing Li, Jianfei Cai

To this end, we first propose to effectively train the over-parameterized network via a task dropout strategy to disentangle the tasks during training.

Image Classification

Resisting Out-of-Distribution Data Problem in Perturbation of XAI

no code implementations27 Jul 2021 Luyu Qiu, Yi Yang, Caleb Chen Cao, Jing Liu, Yueyuan Zheng, Hilary Hei Ting Ngai, Janet Hsiao, Lei Chen

Besides, our solution also resolves a fundamental problem with the faithfulness indicator, a commonly used evaluation metric of XAI algorithms that appears to be sensitive to the OoD issue.

Explainable artificial intelligence

HANet: Hierarchical Alignment Networks for Video-Text Retrieval

1 code implementation26 Jul 2021 Peng Wu, Xiangteng He, Mingqian Tang, Yiliang Lv, Jing Liu

Based on these, we naturally construct hierarchical representations in the individual-local-global manner, where the individual level focuses on the alignment between frame and word, local level focuses on the alignment between video clip and textual context, and global level focuses on the alignment between the whole video and text.

Text Matching Video-Text Retrieval

OPT: Omni-Perception Pre-Trainer for Cross-Modal Understanding and Generation

no code implementations1 Jul 2021 Jing Liu, Xinxin Zhu, Fei Liu, Longteng Guo, Zijia Zhao, Mingzhen Sun, Weining Wang, Hanqing Lu, Shiyu Zhou, Jiajun Zhang, Jinqiao Wang

In this paper, we propose an Omni-perception Pre-Trainer (OPT) for cross-modal understanding and generation, by jointly modeling visual, text and audio resources.

Tensor networks for unsupervised machine learning

1 code implementation24 Jun 2021 Jing Liu, Sujie Li, Jiang Zhang, Pan Zhang

Modeling the joint distribution of high-dimensional data is a central task in unsupervised machine learning.

Tensor Networks

Exploiting Large-scale Teacher-Student Training for On-device Acoustic Models

no code implementations11 Jun 2021 Jing Liu, Rupak Vignesh Swaminathan, Sree Hari Krishnan Parthasarathi, Chunchuan Lyu, Athanasios Mouchtaris, Siegfried Kunzmann

We present results from Alexa speech teams on semi-supervised learning (SSL) of acoustic models (AM) with experiments spanning over 3000 hours of GPU time, making our study one of the largest of its kind.

Measuring Conversational Uptake: A Case Study on Student-Teacher Interactions

1 code implementation ACL 2021 Dorottya Demszky, Jing Liu, Zid Mancenido, Julie Cohen, Heather Hill, Dan Jurafsky, Tatsunori Hashimoto

In conversation, uptake happens when a speaker builds on the contribution of their interlocutor by, for example, acknowledging, repeating or reformulating what they have said.

Question Answering

Large-Scale Data-Driven Airline Market Influence Maximization

no code implementations31 May 2021 Duanshun Li, Jing Liu, Jinsung Jeon, Seoyoung Hong, Thai Le, Dongwon Lee, Noseong Park

On top of the prediction models, we define a budget-constrained flight frequency optimization problem to maximize the market influence over 2, 262 routes.

Boosting the Performance of Video Compression Artifact Reduction with Reference Frame Proposals and Frequency Domain Information

no code implementations31 May 2021 Yi Xu, Minyi Zhao, Jing Liu, Xinjian Zhang, Longwen Gao, Shuigeng Zhou, Huyang Sun

Many deep learning based video compression artifact removal algorithms have been proposed to recover high-quality videos from low-quality compressed videos.

Video Compression

Less is More: Pay Less Attention in Vision Transformers

1 code implementation29 May 2021 Zizheng Pan, Bohan Zhuang, Haoyu He, Jing Liu, Jianfei Cai

Transformers have become one of the dominant architectures in deep learning, particularly as a powerful alternative to convolutional neural networks (CNNs) in computer vision.

Image Classification Instance Segmentation +2

AAformer: Auto-Aligned Transformer for Person Re-Identification

no code implementations2 Apr 2021 Kuan Zhu, Haiyun Guo, Shiliang Zhang, YaoWei Wang, Gaopan Huang, Honglin Qiao, Jing Liu, Jinqiao Wang, Ming Tang

In this paper, we introduce an alignment scheme in Transformer architecture for the first time and propose the Auto-Aligned Transformer (AAformer) to automatically locate both the human parts and non-human ones at patch-level.

Human Parsing Image Classification +2

Scalable Vision Transformers with Hierarchical Pooling

1 code implementation19 Mar 2021 Zizheng Pan, Bohan Zhuang, Jing Liu, Haoyu He, Jianfei Cai

However, the routine of the current ViT model is to maintain a full-length patch sequence during inference, which is redundant and lacks hierarchical representation.

Image Classification

Temporal Memory Attention for Video Semantic Segmentation

1 code implementation17 Feb 2021 Hao Wang, Weining Wang, Jing Liu

Video semantic segmentation requires to utilize the complex temporal relations between frames of the video sequence.

Semantic Segmentation Video Semantic Segmentation

CPTR: Full Transformer Network for Image Captioning

no code implementations26 Jan 2021 Wei Liu, Sihan Chen, Longteng Guo, Xinxin Zhu, Jing Liu

Besides, we provide detailed visualizations of the self-attention between patches in the encoder and the "words-to-patches" attention in the decoder thanks to the full Transformer architecture.

Image Captioning

Global-Local Propagation Network for RGB-D Semantic Segmentation

no code implementations26 Jan 2021 Sihan Chen, Xinxin Zhu, Wei Liu, Xingjian He, Jing Liu

Depth information matters in RGB-D semantic segmentation task for providing additional geometric information to color images.

Scene Segmentation

Fast Sequence Generation with Multi-Agent Reinforcement Learning

no code implementations24 Jan 2021 Longteng Guo, Jing Liu, Xinxin Zhu, Hanqing Lu

These models are autoregressive in that they generate each word by conditioning on previously generated words, which leads to heavy latency during inference.

Image Captioning Machine Translation +1

LBS: Loss-aware Bit Sharing for Automatic Model Compression

no code implementations13 Jan 2021 Jing Liu, Bohan Zhuang, Peng Chen, Yong Guo, Chunhua Shen, Jianfei Cai, Mingkui Tan

Low-bitwidth model compression is an effective method to reduce the model size and computational overhead.

Model Compression Quantization

Magnetic field and gravitational waves from the first-order Phase Transition

no code implementations31 Dec 2020 Yuefeng Di, Jialong Wang, Ruiyu Zhou, Ligong Bian, Rong-Gen Cai, Jing Liu

We perform the three dimensional lattice simulation of the magnetic field and gravitational wave productions from bubble collisions during the first-order electroweak phase transition.

Cosmology and Nongalactic Astrophysics High Energy Physics - Lattice High Energy Physics - Phenomenology

DS-Net: Dynamic Spatiotemporal Network for Video Salient Object Detection

1 code implementation9 Dec 2020 Yuting Su, Weikang Wang, Jing Liu, Peiguang Jing, Xiaokang Yang

In this paper, we investigate the complimentary roles of spatial and temporal information and propose a novel dynamic spatiotemporal network (DS-Net) for more effective fusion of spatiotemporal information.

Optical Flow Estimation Saliency Detection +2

Conditional Automated Channel Pruning for Deep Neural Networks

no code implementations21 Sep 2020 Yixin Liu, Yong Guo, Zichang Liu, Haohua Liu, Jingjie Zhang, Zejun Chen, Jing Liu, Jian Chen

To address this issue, given a target compression rate for the whole model, one can search for the optimal compression rate for each layer.

Model Compression

Robust Mean Estimation in High Dimensions via $\ell_0$ Minimization

no code implementations21 Aug 2020 Jing Liu, Aditya Deshmukh, Venugopal V. Veeravalli

We study the robust mean estimation problem in high dimensions, where $\alpha <0. 5$ fraction of the data points can be arbitrarily corrupted.

Compressive Sensing

Scene Segmentation with Dual Relation-aware Attention Network

1 code implementation TNNLS 2020 Jun Fu, Jing Liu, Jie Jiang, Yong Li, Yongjun Bao, Hanqing Lu

We conduct extensive experiments to validate the effectiveness of our network and achieve new state-of-the-art segmentation performance on four challenging scene segmentation data sets, i. e., Cityscapes, ADE20K, PASCAL Context, and COCO Stuff data sets.

Scene Segmentation

AQD: Towards Accurate Quantized Object Detection

no code implementations CVPR 2021 Peng Chen, Jing Liu, Bohan Zhuang, Mingkui Tan, Chunhua Shen

Network quantization allows inference to be conducted using low-precision arithmetic for improved inference efficiency of deep neural networks on edge devices.

Image Classification Object Detection +1

NROWAN-DQN: A Stable Noisy Network with Noise Reduction and Online Weight Adjustment for Exploration

no code implementations19 Jun 2020 Shuai Han, Wenbo Zhou, Jing Liu, Shuai Lü

Effective exploration for noisy networks is one of the most important issues in deep reinforcement learning.

Non-Autoregressive Image Captioning with Counterfactuals-Critical Multi-Agent Learning

no code implementations10 May 2020 Longteng Guo, Jing Liu, Xinxin Zhu, Xingjian He, Jie Jiang, Hanqing Lu

In this paper, we propose a Non-Autoregressive Image Captioning (NAIC) model with a novel training paradigm: Counterfactuals-critical Multi-Agent Learning (CMAL).

Image Captioning Machine Translation +1

Gumbel-softmax-based Optimization: A Simple General Framework for Optimization Problems on Graphs

no code implementations14 Apr 2020 Yaoxin Li, Jing Liu, Guozheng Lin, Yueyuan Hou, Muyun Mou, Jiang Zhang

In computer science, there exist a large number of optimization problems defined on graphs, that is to find a best node state configuration or a network structure such that the designed objective function is optimized under some constraints.

Combinatorial Optimization

Minor Constraint Disturbances for Deep Semi-supervised Learning

no code implementations13 Mar 2020 Jielei Chu, Jing Liu, Hongjun Wang, Zhiguo Gong, Tianrui Li

The semi-supervised strategy based on the KL divergence of the MCD significantly reduces the reliance on the labels and improves the stability of the semi-supervised feature learning in high-dimensional space simultaneously.

Generative Low-bitwidth Data Free Quantization

2 code implementations ECCV 2020 Shoukai Xu, Haokun Li, Bohan Zhuang, Jing Liu, JieZhang Cao, Chuangrun Liang, Mingkui Tan

More critically, our method achieves much higher accuracy on 4-bit quantization than the existing data free quantization method.

Quantization

Learn to Generate Time Series Conditioned Graphs with Generative Adversarial Nets

no code implementations3 Mar 2020 Shanchao Yang, Jing Liu, Kai Wu, Mingming Li

Differently, in this paper, we are interested in a novel problem named Time Series Conditioned Graph Generation: given an input multivariate time series, we aim to infer a target relation graph modeling the underlying interrelationships between time series with each node corresponding to each time series.

Graph Generation Time Series

Discrimination-aware Network Pruning for Deep Model Compression

1 code implementation4 Jan 2020 Jing Liu, Bohan Zhuang, Zhuangwei Zhuang, Yong Guo, Junzhou Huang, Jinhui Zhu, Mingkui Tan

In this paper, we propose a simple-yet-effective method called discrimination-aware channel pruning (DCP) to choose the channels that actually contribute to the discriminative power.

Face Recognition Image Classification +2

Semantic-Aware Label Placement for Augmented Reality in Street View

no code implementations15 Dec 2019 Jianqing Jia, Semir Elezovikj, Heng Fan, Shuojin Yang, Jing Liu, Wei Guo, Chiu C. Tan, Haibin Ling

Our solution encodes the constraints for placing labels in an optimization problem to obtain the final label layout, and the labels will be placed in appropriate positions to reduce the chances of overlaying important real-world objects in street view AR scenarios.

CoKE: Contextualized Knowledge Graph Embedding

2 code implementations6 Nov 2019 Quan Wang, Pingping Huang, Haifeng Wang, Songtai Dai, Wenbin Jiang, Jing Liu, Yajuan Lyu, Yong Zhu, Hua Wu

This work presents Contextualized Knowledge Graph Embedding (CoKE), a novel paradigm that takes into account such contextual nature, and learns dynamic, flexible, and fully contextualized entity and relation embeddings.

Knowledge Graph Embedding Link Prediction

Adaptive Context Network for Scene Parsing

no code implementations ICCV 2019 Jun Fu, Jing Liu, Yuhang Wang, Yong Li, Yongjun Bao, Jinhui Tang, Hanqing Lu

Recent works attempt to improve scene parsing performance by exploring different levels of contexts, and typically train a well-designed convolutional network to exploit useful contexts across all pixels equally.

Scene Parsing Semantic Segmentation

D-NET: A Pre-Training and Fine-Tuning Framework for Improving the Generalization of Machine Reading Comprehension

no code implementations WS 2019 Hongyu Li, Xiyuan Zhang, Yibing Liu, Yiming Zhang, Quan Wang, Xiangyang Zhou, Jing Liu, Hua Wu, Haifeng Wang

In this paper, we introduce a simple system Baidu submitted for MRQA (Machine Reading for Question Answering) 2019 Shared Task that focused on generalization of machine reading comprehension (MRC) models.

Machine Reading Comprehension Multi-Task Learning +1

Flash X-ray diffraction imaging in 3D: a proposed analysis pipeline

no code implementations30 Oct 2019 Jing Liu, Stefan Engblom, Carl Nettelblad

Modern Flash X-ray diffraction Imaging (FXI) acquires diffraction signals from single biomolecules at a high repetition rate from X-ray Free Electron Lasers (XFELs), easily obtaining millions of 2D diffraction patterns from a single experiment.

Vatex Video Captioning Challenge 2020: Multi-View Features and Hybrid Reward Strategies for Video Captioning

no code implementations17 Oct 2019 Xinxin Zhu, Longteng Guo, Peng Yao, Shichen Lu, Wei Liu, Jing Liu

This report describes our solution for the VATEX Captioning Challenge 2020, which requires generating descriptions for the videos in both English and Chinese languages.

Video Captioning

Gumbel-softmax Optimization: A Simple General Framework for Combinatorial Optimization Problems on Graphs

no code implementations16 Sep 2019 Jing Liu, Fei Gao, Jiang Zhang

Many problems in real life can be converted to combinatorial optimization problems (COPs) on graphs, that is to find a best node state configuration or a network structure such that the designed objective function is optimized under some constraints.

Combinatorial Optimization

Effective Training of Convolutional Neural Networks with Low-bitwidth Weights and Activations

no code implementations10 Aug 2019 Bohan Zhuang, Jing Liu, Mingkui Tan, Lingqiao Liu, Ian Reid, Chunhua Shen

Furthermore, we propose a second progressive quantization scheme which gradually decreases the bit-width from high-precision to low-precision during training.

Knowledge Distillation Quantization

Aligning Linguistic Words and Visual Semantic Units for Image Captioning

1 code implementation6 Aug 2019 Longteng Guo, Jing Liu, Jinhui Tang, Jiangwei Li, Wei Luo, Hanqing Lu

Image captioning attempts to generate a sentence composed of several linguistic words, which are used to describe objects, attributes, and interactions in an image, denoted as visual semantic units in this paper.

Image Captioning

Quantum Fisher information matrix and multiparameter estimation

no code implementations18 Jul 2019 Jing Liu, Haidong Yuan, Xiao-Ming Lu, Xiaoguang Wang

Quantum Fisher information matrix (QFIM) is a core concept in theoretical quantum metrology due to the significant importance of quantum Cram\'{e}r-Rao bound in quantum parameter estimation.

Quantum Physics

UCRDNet: Unsupervised Collaborative Representation Deep Network for Clustering

no code implementations12 Jun 2019 Jielei Chu, Hongjun Wang, Jing Liu, Zeng Yu, Zhiguo Gong, Tianrui Li

Furthermore, the proposed UCRDNet shows more excellent collaborative representation capabilities than the CDL deep collaborative networks for unsupervised clustering.

A General Deep Learning Framework for Network Reconstruction and Dynamics Learning

1 code implementation30 Dec 2018 Zhang Zhang, Yi Zhao, Jing Liu, Shuo Wang, Ruyi Tao, Ruyue Xin, Jiang Zhang

We exhibit the universality of our framework on different kinds of time-series data: with the same structure, our model can be trained to accurately recover the network structure and predict future states on continuous, discrete, and binary dynamics, and outperforms competing network reconstruction methods.

Time Series

Unsupervised Feature Learning Architecture with Multi-clustering Integration RBM

no code implementations5 Dec 2018 Jielei Chu, Hongjun Wang, Jing Liu, Zhiguo Gong, Tianrui Li

In this paper, we present a novel unsupervised feature learning architecture, which consists of a multi-clustering integration module and a variant of RBM termed multi-clustering integration RBM (MIRBM).

Supervised Classification Methods for Flash X-ray single particle diffraction Imaging

no code implementations25 Oct 2018 Jing Liu, Gijs van der Schot, Stefan Engblom

It is also straightforward to parallelize them so as to fully match the XFEL repetition rate, thereby enabling processing at site.

General Classification

Aggregated Semantic Matching for Short Text Entity Linking

no code implementations CONLL 2018 Feng Nie, Shuyan Zhou, Jing Liu, Jinpeng Wang, Chin-Yew Lin, Rong pan

The task of entity linking aims to identify concepts mentioned in a text fragments and link them to a reference knowledge base.

Card Games Entity Linking +2

Answer-focused and Position-aware Neural Question Generation

no code implementations EMNLP 2018 Xingwu Sun, Jing Liu, Yajuan Lyu, wei he, Yanjun Ma, Shi Wang

(2) The model copies the context words that are far from and irrelevant to the answer, instead of the words that are close and relevant to the answer.

Machine Reading Comprehension Question Answering +1

Dual Attention Network for Scene Segmentation

10 code implementations CVPR 2019 Jun Fu, Jing Liu, Haijie Tian, Yong Li, Yongjun Bao, Zhiwei Fang, Hanqing Lu

Specifically, we append two types of attention modules on top of traditional dilated FCN, which model the semantic interdependencies in spatial and channel dimensions respectively.

Scene Segmentation

Neural Math Word Problem Solver with Reinforcement Learning

no code implementations COLING 2018 Danqing Huang, Jing Liu, Chin-Yew Lin, Jian Yin

Experimental results show that (1) The copy and alignment mechanism is effective to address the two issues; (2) Reinforcement learning leads to better performance than maximum likelihood on this task; (3) Our neural model is complementary to the feature-based model and their combination significantly outperforms the state-of-the-art results.

Feature Engineering Math Word Problem Solving

Adaptations of ROUGE and BLEU to Better Evaluate Machine Reading Comprehension Task

no code implementations WS 2018 An Yang, Kai Liu, Jing Liu, Yajuan Lyu, Sujian Li

Current evaluation metrics to question answering based machine reading comprehension (MRC) systems generally focus on the lexical overlap between the candidate and reference answers, such as ROUGE and BLEU.

Machine Reading Comprehension Question Answering

Multi-Passage Machine Reading Comprehension with Cross-Passage Answer Verification

no code implementations ACL 2018 Yizhong Wang, Kai Liu, Jing Liu, wei he, Yajuan Lyu, Hua Wu, Sujian Li, Haifeng Wang

Machine reading comprehension (MRC) on real web data usually requires the machine to answer a question by analyzing multiple passages retrieved by search engine.

Machine Reading Comprehension Question Answering

DuReader: a Chinese Machine Reading Comprehension Dataset from Real-world Applications

3 code implementations WS 2018 Wei He, Kai Liu, Jing Liu, Yajuan Lyu, Shiqi Zhao, Xinyan Xiao, Yu-An Liu, Yizhong Wang, Hua Wu, Qiaoqiao She, Xuan Liu, Tian Wu, Haifeng Wang

Experiments show that human performance is well above current state-of-the-art baseline systems, leaving plenty of room for the community to make improvements.

Machine Reading Comprehension

A Statistical Framework for Product Description Generation

no code implementations IJCNLP 2017 Jinpeng Wang, Yutai Hou, Jing Liu, Yunbo Cao, Chin-Yew Lin

We present in this paper a statistical framework that generates accurate and fluent product description from product attributes.

Data-to-Text Generation

Stacked Deconvolutional Network for Semantic Segmentation

no code implementations16 Aug 2017 Jun Fu, Jing Liu, Yuhang Wang, Hanqing Lu

In SDN, multiple shallow deconvolutional networks, which are called as SDN units, are stacked one by one to integrate contextual information and guarantee the fine recovery of localization information.

Semantic Segmentation

Long-term Blood Pressure Prediction with Deep Recurrent Neural Networks

1 code implementation12 May 2017 Peng Su, Xiao-Rong Ding, Yuan-Ting Zhang, Jing Liu, Fen Miao, Ni Zhao

Existing methods for arterial blood pressure (BP) estimation directly map the input physiological signals to output BP values without explicitly modeling the underlying temporal dependencies in BP dynamics.

Blood pressure estimation Electrocardiography (ECG)

Assessing Uncertainties in X-ray Single-particle Three-dimensional reconstructions

no code implementations2 Jan 2017 Stefan Engblom, Carl Nettelblad, Jing Liu

These two-dimensional diffraction patterns can be practically reconstructed and retrieved down to a resolution of a few \angstrom.

Machine learning for ultrafast X-ray diffraction patterns on large-scale GPU clusters

no code implementations11 Sep 2014 Tomas Ekeberg, Stefan Engblom, Jing Liu

With the expected enormous amount of diffraction data to be produced in the foreseeable future, this is the required scale to approach real time processing of data at the beam site.

Weakly-Supervised Dual Clustering for Image Semantic Segmentation

no code implementations CVPR 2013 Yang Liu, Jing Liu, Zechao Li, Jinhui Tang, Hanqing Lu

In this paper, we propose a novel Weakly-Supervised Dual Clustering (WSDC) approach for image semantic segmentation with image-level labels, i. e., collaboratively performing image segmentation and tag alignment with those regions.

Semantic Segmentation

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