Search Results for author: Bo Peng

Found 56 papers, 10 papers with code

Discovering Financial Hypernyms by Prompting Masked Language Models

no code implementations FNP (LREC) 2022 Bo Peng, Emmanuele Chersoni, Yu-Yin Hsu, Chu-Ren Huang

With the rising popularity of Transformer-based language models, several studies have tried to exploit their masked language modeling capabilities to automatically extract relational linguistic knowledge, although this kind of research has rarely investigated semantic relations in specialized domains.

Domain Adaptation Language Modelling +1

Is Domain Adaptation Worth Your Investment? Comparing BERT and FinBERT on Financial Tasks

no code implementations EMNLP (ECONLP) 2021 Bo Peng, Emmanuele Chersoni, Yu-Yin Hsu, Chu-Ren Huang

With the recent rise in popularity of Transformer models in Natural Language Processing, research efforts have been dedicated to the development of domain-adapted versions of BERT-like architectures.

Continual Pretraining Domain Adaptation

ROCLING-2021 Shared Task: Dimensional Sentiment Analysis for Educational Texts

no code implementations ROCLING 2021 Liang-Chih Yu, Jin Wang, Bo Peng, Chu-Ren Huang

This paper presents the ROCLING 2021 shared task on dimensional sentiment analysis for educational texts which seeks to identify a real-value sentiment score of self-evaluation comments written by Chinese students in the both valence and arousal dimensions.

Sentiment Analysis

Collaborative Feature Learning for Fine-grained Facial Forgery Detection and Segmentation

no code implementations17 Apr 2023 Weinan Guan, Wei Wang, Jing Dong, Bo Peng, Tieniu Tan

An important topic in manipulation detection is the localization of the fake regions.

Learning Invariant Representation via Contrastive Feature Alignment for Clutter Robust SAR Target Recognition

no code implementations4 Apr 2023 Bowen Peng, Jianyue Xie, Bo Peng, Li Liu

The proposed method contributes a mixed clutter variants generation strategy and a new inference branch equipped with channel-weighted mean square error (CWMSE) loss for invariant representation learning.

Contrastive Learning Representation Learning

IntrinsicNGP: Intrinsic Coordinate based Hash Encoding for Human NeRF

no code implementations28 Feb 2023 Bo Peng, Jun Hu, Jingtao Zhou, Xuan Gao, Juyong Zhang

To achieve this target, we introduce a continuous and optimizable intrinsic coordinate rather than the original explicit Euclidean coordinate in the hash encoding module of instant-NGP.

Novel View Synthesis

Designing a 3D-Aware StyleNeRF Encoder for Face Editing

no code implementations19 Feb 2023 Songlin Yang, Wei Wang, Bo Peng, Jing Dong

For more flexible face manipulation, we then design a dual-branch StyleFlow module to transfer the StyleNeRF codes with disentangled geometry and texture flows.

Face Model Video Editing

Visual Realism Assessment for Face-swap Videos

no code implementations2 Feb 2023 Xianyun Sun, Beibei Dong, Caiyong Wang, Bo Peng, Jing Dong

The research community has been focusing on the automatic detection of these fake videos, but the as sessment of their visual realism, as perceived by human eyes, is still an unexplored dimension.

DeepFake Detection Face Swapping

SelfNeRF: Fast Training NeRF for Human from Monocular Self-rotating Video

no code implementations4 Oct 2022 Bo Peng, Jun Hu, Jingtao Zhou, Juyong Zhang

Extensive experimental results on several different datasets demonstrate the effectiveness and efficiency of SelfNeRF to challenging monocular videos.

Novel View Synthesis

Recursive Attentive Methods with Reused Item Representations for Sequential Recommendation

no code implementations16 Sep 2022 Bo Peng, Srinivasan Parthasarathy, Xia Ning

Our run-time performance comparison signifies that RAM could also be more efficient on benchmark datasets.

Sequential Recommendation

Scattering Model Guided Adversarial Examples for SAR Target Recognition: Attack and Defense

no code implementations11 Sep 2022 Bowen Peng, Bo Peng, Jie zhou, Jianyue Xie, Li Liu

Toward building more robust DNN-based SAR ATR models, this article explores the domain knowledge of SAR imaging process and proposes a novel Scattering Model Guided Adversarial Attack (SMGAA) algorithm which can generate adversarial perturbations in the form of electromagnetic scattering response (called adversarial scatterers).

Adversarial Attack Adversarial Robustness

MultiEarth 2022 -- The Champion Solution for the Matrix Completion Challenge via Multimodal Regression and Generation

no code implementations17 Jun 2022 Bo Peng, Hongchen Liu, Hang Zhou, Yuchuan Gou, Jui-Hsin Lai

Earth observation satellites have been continuously monitoring the earth environment for years at different locations and spectral bands with different modalities.

Matrix Completion regression +1

MultiEarth 2022 -- The Champion Solution for Image-to-Image Translation Challenge via Generation Models

no code implementations17 Jun 2022 Yuchuan Gou, Bo Peng, Hongchen Liu, Hang Zhou, Jui-Hsin Lai

The MultiEarth 2022 Image-to-Image Translation challenge provides a well-constrained test bed for generating the corresponding RGB Sentinel-2 imagery with the given Sentinel-1 VV & VH imagery.

Image-to-Image Translation Translation

Prospective Preference Enhanced Mixed Attentive Model for Session-based Recommendation

no code implementations4 Jun 2022 Bo Peng, Chang-Yu Tai, Srinivasan Parthasarathy, Xia Ning

In this manuscript, we develop prospective preference enhanced mixed attentive model (P2MAM) to generate session-based recommendations using two important factors: temporal patterns and estimates of users' prospective preferences.

Session-Based Recommendations

Exposing Fine-Grained Adversarial Vulnerability of Face Anti-Spoofing Models

no code implementations30 May 2022 Songlin Yang, Wei Wang, Chenye Xu, Ziwen He, Bo Peng, Jing Dong

These fine-grained adversarial examples can be used for selecting robust backbone networks and auxiliary features.

Adversarial Attack Adversarial Robustness +1

UWC: Unit-wise Calibration Towards Rapid Network Compression

no code implementations17 Jan 2022 Chen Lin, Zheyang Li, Bo Peng, Haoji Hu, Wenming Tan, Ye Ren, ShiLiang Pu

This paper introduces a post-training quantization~(PTQ) method achieving highly efficient Convolutional Neural Network~ (CNN) quantization with high performance.


Deep Stereo Image Compression via Bi-Directional Coding

no code implementations CVPR 2022 Jianjun Lei, Xiangrui Liu, Bo Peng, Dengchao Jin, Wanqing Li, Jingxiao Gu

Existing learning-based stereo compression methods usually adopt a unidirectional approach to encoding one image independently and the other image conditioned upon the first.

Image Compression

HeadNeRF: A Real-time NeRF-based Parametric Head Model

1 code implementation CVPR 2022 Yang Hong, Bo Peng, Haiyao Xiao, Ligang Liu, Juyong Zhang

Different from existing related parametric models, we use the neural radiance fields as a novel 3D proxy instead of the traditional 3D textured mesh, which makes that HeadNeRF is able to generate high fidelity images.

Neural Rendering

Multi-View Stereo with Transformer

no code implementations1 Dec 2021 Jie Zhu, Bo Peng, Wanqing Li, Haifeng Shen, Zhe Zhang, Jianjun Lei

It is built upon Transformer and is capable of extracting dense features with global context and 3D consistency, which are crucial to achieving reliable matching for MVS.

Novel View Synthesis from a Single Image via Unsupervised learning

no code implementations29 Oct 2021 Bingzheng Liu, Jianjun Lei, Bo Peng, Chuanbo Yu, Wanqing Li, Nam Ling

In particular, the network consists of a token transformation module (TTM) that facilities the transformation of the features extracted from a source viewpoint image into an intrinsic representation with respect to a pre-defined reference pose and a view generation module (VGM) that synthesizes an arbitrary view from the representation.

Novel View Synthesis

TGEA: An Error-Annotated Dataset and Benchmark Tasks for TextGeneration from Pretrained Language Models

no code implementations ACL 2021 Jie He, Bo Peng, Yi Liao, Qun Liu, Deyi Xiong

Each error is hence manually labeled with comprehensive annotations, including the span of the error, the associated span, minimal correction to the error, the type of the error, and rationale behind the error.

Common Sense Reasoning Text Generation

Robust Face-Swap Detection Based on 3D Facial Shape Information

no code implementations28 Apr 2021 Weinan Guan, Wei Wang, Jing Dong, Bo Peng, Tieniu Tan

Maliciously-manipulated images or videos - so-called deep fakes - especially face-swap images and videos have attracted more and more malicious attackers to discredit some key figures.

SOGAN: 3D-Aware Shadow and Occlusion Robust GAN for Makeup Transfer

no code implementations21 Apr 2021 Yueming Lyu, Jing Dong, Bo Peng, Wei Wang, Tieniu Tan

Since human faces are symmetrical in the UV space, we can conveniently remove the undesired shadow and occlusion from the reference image by carefully designing a Flip Attention Module (FAM).

Face Model Facial Makeup Transfer

Variational quantum solver employing the PDS energy functional

no code implementations21 Jan 2021 Bo Peng, Karol Kowalski

Recently a new class of quantum algorithms that are based on the quantum computation of the connected moment expansion has been reported to find the ground and excited state energies.

Quantum Physics

Topological holographic quench dynamics in a synthetic dimension

no code implementations21 Jan 2021 Danying Yu, Bo Peng, Xianfeng Chen, Xiong-Jun Liu, Luqi Yuan

The notion of topological phases extended to dynamical systems stimulates extensive studies, of which the characterization of non-equilibrium topological invariants is a central issue and usually necessitates the information of quantum dynamics in both the time and spatial dimensions.

Quantum Physics Optics

The Arecibo Ultra-Deep Survey

no code implementations17 Dec 2020 Hongwei Xi, Lister Staveley-Smith, Bi-Qing For, Wolfram Freudling, Martin Zwaan, Laura Hoppmann, Fu-Heng Liang, Bo Peng

The mass range of detected galaxies is $\log(M_{\rm HI}~[h_{70}^{-2}{\rm M}_\odot]) = 6. 32 - 10. 76$.

Astrophysics of Galaxies

MUST-GAN: Multi-level Statistics Transfer for Self-driven Person Image Generation

1 code implementation CVPR 2021 Tianxiang Ma, Bo Peng, Wei Wang, Jing Dong

To deal with this problem, we propose a novel multi-level statistics transfer model, which disentangles and transfers multi-level appearance features from person images and merges them with pose features to reconstruct the source person images themselves.

Pose Transfer Style Transfer

Hybrid Collaborative Filtering Models for Clinical Search Recommendation

no code implementations19 Jul 2020 Zhiyun Ren, Bo Peng, Titus K. Schleyer, Xia Ning

With increasing and extensive use of electronic health records, clinicians are often under time pressure when they need to retrieve important information efficiently among large amounts of patients' health records in clinics.

Collaborative Filtering Recommendation Systems

M2: Mixed Models with Preferences, Popularities and Transitions for Next-Basket Recommendation

3 code implementations3 Apr 2020 Bo Peng, Zhiyun Ren, Srinivasan Parthasarathy, Xia Ning

We compared M2 with different combinations of the factors with 5 state-of-the-art next-basket recommendation methods on 4 public benchmark datasets in recommending the first, second and third next basket.

Next-basket recommendation

Learning Pose-invariant 3D Object Reconstruction from Single-view Images

1 code implementation3 Apr 2020 Bo Peng, Wei Wang, Jing Dong, Tieniu Tan

Learning to reconstruct 3D shapes using 2D images is an active research topic, with benefits of not requiring expensive 3D data.

3D Object Reconstruction Domain Adaptation

Co-occurrence Background Model with Superpixels for Robust Background Initialization

no code implementations29 Mar 2020 Wenjun Zhou, Yuheng Deng, Bo Peng, Dong Liang, Shun'ichi Kaneko

Background initialization is an important step in many high-level applications of video processing, ranging from video surveillance to video inpainting. However, this process is often affected by practical challenges such as illumination changes, background motion, camera jitter and intermittent movement, etc. In this paper, we develop a co-occurrence background model with superpixel segmentation for robust background initialization.


HAM: Hybrid Associations Models for Sequential Recommendation

2 code implementations27 Feb 2020 Bo Peng, Zhiyun Ren, Srinivasan Parthasarathy, Xia Ning

We compared HAM models with the most recent, state-of-the-art methods on six public benchmark datasets in three different experimental settings.

Sequential Recommendation

Cognitive Biomarker Prioritization in Alzheimer's Disease using Brain Morphometric Data

no code implementations18 Feb 2020 Bo Peng, Xiaohui Yao, Shannon L. Risacher, Andrew J. Saykin, Li Shen, Xia Ning

This method learns the latent scoring function that pushes the most effective cognitive assessments onto the top of the prioritization list.


A Deep Reinforcement Learning Algorithm Using Dynamic Attention Model for Vehicle Routing Problems

3 code implementations9 Feb 2020 Bo Peng, Jiahai Wang, Zizhen Zhang

However, the fact is, the state of an instance is changed according to the decision that the model made at different construction steps, and the node features should be updated correspondingly.

Combinatorial Optimization reinforcement-learning +1

Scalable Fine-grained Generated Image Classification Based on Deep Metric Learning

no code implementations10 Dec 2019 Xinsheng Xuan, Bo Peng, Wei Wang, Jing Dong

The new types of generated images are emerging one after another, and the existing detection methods cannot cope well.

General Classification Image Classification +2

CNN-based Dual-Chain Models for Knowledge Graph Learning

no code implementations15 Nov 2019 Bo Peng, Renqiang Min, Xia Ning

We also present an extension of this model, which incorporates descriptions of entities and learns a second set of entity embeddings from the descriptions.

Entity Embeddings Graph Learning

Semi-Heterogeneous Three-Way Joint Embedding Network for Sketch-Based Image Retrieval

no code implementations10 Nov 2019 Jianjun Lei, Yuxin Song, Bo Peng, Zhanyu Ma, Ling Shao, Yi-Zhe Song

How to align abstract sketches and natural images into a common high-level semantic space remains a key problem in SBIR.

Retrieval Sketch-Based Image Retrieval

Comprehensive Video Understanding: Video summarization with content-based video recommender design

no code implementations30 Oct 2019 Yudong Jiang, Kaixu Cui, Bo Peng, Changliang Xu

In this paper, we formulate video summarization as a content-based recommender problem, which should distill the most useful content from a long video for users who suffer from information overload.

Action Recognition Data Augmentation +3

Point Clouds Learning with Attention-based Graph Convolution Networks

no code implementations31 May 2019 Zhuyang Xie, Junzhou Chen, Bo Peng

In addition, we introduce an additional global graph structure network to compensate for the relative information of the individual points in the graph structure network.

General Classification

Q# and NWChem: Tools for Scalable Quantum Chemistry on Quantum Computers

no code implementations1 Apr 2019 Guang Hao Low, Nicholas P. Bauman, Christopher E. Granade, Bo Peng, Nathan Wiebe, Eric J. Bylaska, Dave Wecker, Sriram Krishnamoorthy, Martin Roetteler, Karol Kowalski, Matthias Troyer, Nathan A. Baker

Fault-tolerant quantum computation promises to solve outstanding problems in quantum chemistry within the next decade.

Quantum Physics Emerging Technologies Chemical Physics Computational Physics

On the generalization of GAN image forensics

no code implementations27 Feb 2019 Xinsheng Xuan, Bo Peng, Wei Wang, Jing Dong

Recently the GAN generated face images are more and more realistic with high-quality, even hard for human eyes to detect.

GAN image forensics Image Forensics

A deep Convolutional Neural Network for topology optimization with strong generalization ability

no code implementations23 Jan 2019 Yiquan Zhang, Bo Peng, Xiaoyi Zhou, Cheng Xiang, Dalei Wang

The performance of the proposed method was evaluated by comparing its efficiency and accuracy with SIMP on a series of typical optimization problems.

A Blended Deep Learning Approach for Predicting User Intended Actions

no code implementations11 Oct 2018 Fei Tan, Zhi Wei, Jun He, Xiang Wu, Bo Peng, Haoran Liu, Zhenyu Yan

In this work, we focus on pre- dicting attrition, which is one of typical user intended actions.

Person Re-Identification by Semantic Region Representation and Topology Constraint

no code implementations20 Aug 2018 Jianjun Lei, Lijie Niu, Huazhu Fu, Bo Peng, Qingming Huang, Chunping Hou

In this paper, we propose a novel person re-identification method, which consists of a reliable representation called Semantic Region Representation (SRR), and an effective metric learning with Mapping Space Topology Constraint (MSTC).

Metric Learning Person Re-Identification

Extreme Network Compression via Filter Group Approximation

no code implementations ECCV 2018 Bo Peng, Wenming Tan, Zheyang Li, Shun Zhang, Di Xie, ShiLiang Pu

In this paper we propose a novel decomposition method based on filter group approximation, which can significantly reduce the redundancy of deep convolutional neural networks (CNNs) while maintaining the majority of feature representation.

General Classification Image Classification

Chinese Grammatical Error Diagnosis Using Single Word Embedding

no code implementations WS 2016 Jinnan Yang, Bo Peng, Jin Wang, Jixian Zhang, Xue-jie Zhang

A computer-assisted learning tool which can automatically detect and correct Chinese grammatical errors is necessary for those foreign students.

Grammatical Error Detection Language Modelling +1

A Tabu Search/Path Relinking Algorithm to Solve the Job Shop Scheduling Problem

1 code implementation23 Feb 2014 Bo Peng, Zhipeng Lu, T. C. E. Cheng

We present an algorithm that incorporates a tabu search procedure into the framework of path relinking to tackle the job shop scheduling problem (JSP).

Data Structures and Algorithms

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