Search Results for author: Xin Xu

Found 59 papers, 19 papers with code

Adaptive Dense Pseudo Label Selection for Semi-supervised Oriented Object Detection

no code implementations21 Nov 2023 Tong Zhao, Qiang Fang, Shuohao Shi, Xin Xu

However, for the multi-oriented and dense objects that are common in aerial scenes, existing dense pseudo-label selection methods are inefficient and impede the performance in semi-supervised oriented object detection.

object-detection Object Detection +3

Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology View

1 code implementation3 Oct 2023 Jintian Zhang, Xin Xu, Shumin Deng

This paper probes the collaboration mechanisms among contemporary NLP systems by melding practical experiments with theoretical insights.


TaskLAMA: Probing the Complex Task Understanding of Language Models

no code implementations29 Aug 2023 Quan Yuan, Mehran Kazemi, Xin Xu, Isaac Noble, Vaiva Imbrasaite, Deepak Ramachandran

Our experiments reveal that LLMs are able to decompose complex tasks into individual steps effectively, with a relative improvement of 15% to 280% over the best baseline.

From Generation to Suppression: Towards Effective Irregular Glow Removal for Nighttime Visibility Enhancement

no code implementations31 Jul 2023 Wanyu Wu, Wei Wang, Zheng Wang, Kui Jiang, Xin Xu

Most existing Low-Light Image Enhancement (LLIE) methods are primarily designed to improve brightness in dark regions, which suffer from severe degradation in nighttime images.

Low-Light Image Enhancement Zero-Shot Learning

Learning to Branch in Combinatorial Optimization with Graph Pointer Networks

no code implementations4 Jul 2023 Rui Wang, Zhiming Zhou, Tao Zhang, Ling Wang, Xin Xu, Xiangke Liao, Kaiwen Li

The proposed model, which combines the graph neural network and the pointer mechanism, can effectively map from the solver state to the branching variable decisions.

Combinatorial Optimization Variable Selection

MuseCoco: Generating Symbolic Music from Text

1 code implementation31 May 2023 Peiling Lu, Xin Xu, Chenfei Kang, Botao Yu, Chengyi Xing, Xu Tan, Jiang Bian

In contrast, symbolic music offers ease of editing, making it more accessible for users to manipulate specific musical elements.

Audio Generation Music Generation

Learning Task-preferred Inference Routes for Gradient De-conflict in Multi-output DNNs

no code implementations31 May 2023 Yi Sun, Xin Xu, Jian Li, Xiaochang Hu, Yifei Shi, Ling-Li Zeng

By designing the learnable task-specific importance variables, DR-MGF evaluates the importance of filters for different tasks.

Dr.ICL: Demonstration-Retrieved In-context Learning

no code implementations23 May 2023 Man Luo, Xin Xu, Zhuyun Dai, Panupong Pasupat, Mehran Kazemi, Chitta Baral, Vaiva Imbrasaite, Vincent Y Zhao

In-context learning (ICL), teaching a large language model (LLM) to perform a task with few-shot demonstrations rather than adjusting the model parameters, has emerged as a strong paradigm for using LLMs.

Language Modelling Large Language Model +1

Schema-adaptable Knowledge Graph Construction

1 code implementation15 May 2023 Hongbin Ye, Honghao Gui, Xin Xu, Xi Chen, Huajun Chen, Ningyu Zhang

This necessitates a system that can handle evolving schema automatically to extract information for KGC.

graph construction UIE

Prokaryotic genome editing based on the subtype I-B-Svi CRISPR-Cas system

no code implementations8 May 2023 Wang-Yu Tong, De-Xiang Yong, Xin Xu, Cai-Hua Qiu, Yan Zhang, Xing-Wang Yang, Ting-Ting Xia, Qing-Yang Liu, Su-Li Cao, Yan Sun, Xue Li

Type I CRISPR-Cas systems are the most common among six types of CRISPR-Cas systems, however, non-self-targeting genome editing based on a single Cas3 of type I CRISPR-Cas systems has not been reported.

Vocal Bursts Type Prediction

How to Unleash the Power of Large Language Models for Few-shot Relation Extraction?

2 code implementations2 May 2023 Xin Xu, Yuqi Zhu, Xiaohan Wang, Ningyu Zhang

Scaling language models have revolutionized widespread NLP tasks, yet little comprehensively explored few-shot relation extraction with large language models.

Language Modelling Large Language Model +1

RSFNet: A White-Box Image Retouching Approach using Region-Specific Color Filters

1 code implementation ICCV 2023 Wenqi Ouyang, Yi Dong, Xiaoyang Kang, Peiran Ren, Xin Xu, Xuansong Xie

Therefore, there is a need for white-box approaches that produce satisfying results and enable users to conveniently edit their images simultaneously.

Image Retouching Photo Retouching

MasQCLIP for Open-Vocabulary Universal Image Segmentation

1 code implementation ICCV 2023 Xin Xu, Tianyi Xiong, Zheng Ding, Zhuowen Tu

We present a new method for open-vocabulary universal image segmentation, which is capable of performing instance, semantic, and panoptic segmentation under a unified framework.

Image Segmentation Panoptic Segmentation +1

Neural Koopman Pooling: Control-Inspired Temporal Dynamics Encoding for Skeleton-Based Action Recognition

1 code implementation CVPR 2023 Xinghan Wang, Xin Xu, Yadong Mu

Besides, we also show that our Koopman pooling framework can be easily extended to one-shot action recognition when combined with Dynamic Mode Decomposition.

Action Recognition Skeleton Based Action Recognition +1

LAMBADA: Backward Chaining for Automated Reasoning in Natural Language

no code implementations20 Dec 2022 Mehran Kazemi, Najoung Kim, Deepti Bhatia, Xin Xu, Deepak Ramachandran

Remarkable progress has been made on automated reasoning with natural text, by using Language Models (LMs) and methods such as Chain-of-Thought and Selection-Inference.

LAMBADA Logical Reasoning

Towards Generalizable Person Re-identification with a Bi-stream Generative Model

no code implementations19 Jun 2022 Xin Xu, Wei Liu, Zheng Wang, Ruiming Hu, Qi Tian

Guided by original pedestrian images, one stream is employed to learn a camera-invariant global feature for the CC problem via filtering cross-camera interference factors.

Domain Generalization Generalizable Person Re-identification

Deep Learning for Visual Speech Analysis: A Survey

no code implementations22 May 2022 Changchong Sheng, Gangyao Kuang, Liang Bai, Chenping Hou, Yulan Guo, Xin Xu, Matti Pietikäinen, Li Liu

Visual speech, referring to the visual domain of speech, has attracted increasing attention due to its wide applications, such as public security, medical treatment, military defense, and film entertainment.

speech-recognition Visual Speech Recognition

Scientific and Technological Information Oriented Semantics-adversarial and Media-adversarial Cross-media Retrieval

no code implementations16 Mar 2022 Ang Li, Junping Du, Feifei Kou, Zhe Xue, Xin Xu, Mingying Xu, Yang Jiang

In light of this, we propose a scientific and technological information oriented Semantics-adversarial and Media-adversarial Cross-media Retrieval method (SMCR) to find an effective common subspace.

Information Retrieval Retrieval +2

WenetSpeech: A 10000+ Hours Multi-domain Mandarin Corpus for Speech Recognition

1 code implementation7 Oct 2021 BinBin Zhang, Hang Lv, Pengcheng Guo, Qijie Shao, Chao Yang, Lei Xie, Xin Xu, Hui Bu, Xiaoyu Chen, Chenchen Zeng, Di wu, Zhendong Peng

In this paper, we present WenetSpeech, a multi-domain Mandarin corpus consisting of 10000+ hours high-quality labeled speech, 2400+ hours weakly labeled speech, and about 10000 hours unlabeled speech, with 22400+ hours in total.

Label Error Detection Optical Character Recognition +5

Learning Practically Feasible Policies for Online 3D Bin Packing

2 code implementations31 Aug 2021 Hang Zhao, Chenyang Zhu, Xin Xu, Hui Huang, Kai Xu

In this problem, the items are delivered to the agent without informing the full sequence information.

3D Bin Packing Collision Avoidance

Robust Tube-based Model Predictive Control with Koopman Operators--Extended Version

no code implementations30 Aug 2021 Xinglong Zhang, Wei Pan, Riccardo Scattolini, Shuyou Yu, Xin Xu

The finite data-driven approximation of Koopman operators results in a class of linear predictors, useful for formulating linear model predictive control (MPC) of nonlinear dynamical systems with reduced computational complexity.

A LiDAR Assisted Control Module with High Precision in Parking Scenarios for Autonomous Driving Vehicle

no code implementations2 May 2021 Xin Xu, Yu Dong, Fan Zhu

For example, humans are good at interactive tasks (while autonomous driving systems usually do not), but we are often incompetent for tasks with strict precision demands.

Autonomous Driving

The Multi-speaker Multi-style Voice Cloning Challenge 2021

no code implementations5 Apr 2021 Qicong Xie, Xiaohai Tian, Guanghou Liu, Kun Song, Lei Xie, Zhiyong Wu, Hai Li, Song Shi, Haizhou Li, Fen Hong, Hui Bu, Xin Xu

The challenge consists of two tracks, namely few-shot track and one-shot track, where the participants are required to clone multiple target voices with 100 and 5 samples respectively.

Benchmarking Voice Cloning

CKNet: A Convolutional Neural Network Based on Koopman Operator for Modeling Latent Dynamics from Pixels

no code implementations19 Feb 2021 Yongqian Xiao, Xin Xu, QianLi Lin

In this paper, a novel Koopman-based deep convolutional network, called CKNet, is proposed to identify latent dynamics from raw pixels.

StablePose: Learning 6D Object Poses from Geometrically Stable Patches

no code implementations CVPR 2021 Yifei Shi, Junwen Huang, Xin Xu, Yifan Zhang, Kai Xu

According to the theory of geometric stability analysis, a minimal set of three planar/cylindrical patches are geometrically stable and determine the full 6DoFs of the object pose.

6D Pose Estimation using RGB Pose Prediction

Galaxy Clusters from the DESI Legacy Imaging Surveys. I. Cluster Detection

no code implementations29 Jan 2021 Hu Zou, Jinghua Gao, Xin Xu, Xu Zhou, Jun Ma, Zhimin Zhou, Tianmeng Zhang, Jundan Nie, Jiali Wang, Suijian Xue

Based on the photometric redshift catalog of Zou H. et al. (2019), we apply a fast clustering algorithm to identify 540, 432 galaxy clusters at $z\lesssim1$ in the DESI legacy imaging surveys, which cover a sky area of about 20, 000 deg$^2$.

Astrophysics of Galaxies Cosmology and Nongalactic Astrophysics

Identifiability of Bifactor Models

no code implementations22 Dec 2020 Guanhua Fang, Xin Xu, Jinxin Guo, Zhiliang Ying, Susu Zhang

The bifactor model and its extensions are multidimensional latent variable models, under which each item measures up to one subdimension on top of the primary dimension(s).

Statistics Theory Applications Statistics Theory

RTFN: A Robust Temporal Feature Network for Time Series Classification

no code implementations24 Nov 2020 Zhiwen Xiao, Xin Xu, Huanlai Xing, Shouxi Luo, Penglin Dai, Dawei Zhan

Most of the existing feature networks pay more attention to local features rather than the relationships among them.

Classification General Classification +4

Re-identification = Retrieval + Verification: Back to Essence and Forward with a New Metric

1 code implementation23 Nov 2020 Zheng Wang, Xin Yuan, Toshihiko Yamasaki, Yutian Lin, Xin Xu, Wenjun Zeng

In essence, current re-ID overemphasizes the importance of retrieval but underemphasizes that of verification, \textit{i. e.}, all returned images are considered as the target.

Image Retrieval Retrieval

Multi-View Spectral Clustering with High-Order Optimal Neighborhood Laplacian Matrix

no code implementations31 Aug 2020 Weixuan Liang, Sihang Zhou, Jian Xiong, Xinwang Liu, Siwei Wang, En Zhu, Zhiping Cai, Xin Xu

Multi-view spectral clustering can effectively reveal the intrinsic cluster structure among data by performing clustering on the learned optimal embedding across views.

Clustering Vocal Bursts Intensity Prediction

RTFN: Robust Temporal Feature Network

no code implementations18 Aug 2020 Zhiwen Xiao, Xin Xu, Huanlai Xing, Juan Chen

The temporal feature networks are built to extract basic features from input data while the attentional LSTM networks are devised to capture complicated shapelets and relationships to enrich features.

Clustering Time Series +1

SymmetryNet: Learning to Predict Reflectional and Rotational Symmetries of 3D Shapes from Single-View RGB-D Images

no code implementations2 Aug 2020 Yifei Shi, Junwen Huang, Hongjia Zhang, Xin Xu, Szymon Rusinkiewicz, Kai Xu

We propose an end-to-end deep neural network which is able to predict both reflectional and rotational symmetries of 3D objects present in the input RGB-D image.

Multi-Task Learning Symmetry Detection

Exploring Image Enhancement for Salient Object Detection in Low Light Images

no code implementations31 Jul 2020 Xin Xu, Shiqin Wang, Zheng Wang, Xiaolong Zhang, Ruimin Hu

Low light images captured in a non-uniform illumination environment usually are degraded with the scene depth and the corresponding environment lights.

Image Enhancement object-detection +2

Deep Neural Networks with Koopman Operators for Modeling and Control of Autonomous Vehicles

no code implementations5 Jul 2020 Yongqian Xiao, Xinglong Zhang, Xin Xu, Xueqing Liu, Jiahang Liu

Furthermore, a data-driven model predictive controller with the learned Koopman model is designed for path tracking control of autonomous vehicles.

Autonomous Driving

LSTM Networks for Music Generation

no code implementations16 Jun 2020 Xin Xu

The paper presents a method of the music generation based on LSTM (Long Short-Term Memory), contrasts the effects of different network structures on the music generation and introduces other methods used by some researchers.

Music Generation

PointNet on FPGA for Real-Time LiDAR Point Cloud Processing

no code implementations29 May 2020 Lin Bai, Yecheng Lyu, Xin Xu, Xinming Huang

LiDAR sensors have been widely used in many autonomous vehicle modalities, such as perception, mapping, and localization.

Autonomous Vehicles Segmentation

Person Re-Identification via Active Hard Sample Mining

no code implementations10 Apr 2020 Xin Xu, Lei Liu, Weifeng Liu, Meng Wang, Ruimin Hu

To alleviate such a problem, we present an active hard sample mining framework via training an effective re-ID model with the least labeling efforts.

Person Re-Identification

Asymptotic proximal point methods: finding the global minima with linear convergence for a class of multiple minima problems

1 code implementation5 Apr 2020 Xiaopeng Luo, Xin Xu

We propose and analyze asymptotic proximal point (APP) methods to find the global minimizer for a class of nonconvex, nonsmooth, or even discontinuous multiple minima functions.

Optimization and Control Numerical Analysis Numerical Analysis 65K05, 68Q25, 90C26, 90C56

Can speed up the convergence rate of stochastic gradient methods to $\mathcal{O}(1/k^2)$ by a gradient averaging strategy?

no code implementations25 Feb 2020 Xin Xu, Xiaopeng Luo

In this paper we consider the question of whether it is possible to apply a gradient averaging strategy to improve on the sublinear convergence rates without any increase in storage.

Stochastic gradient-free descents

no code implementations31 Dec 2019 Xiaopeng Luo, Xin Xu

In this paper we propose stochastic gradient-free methods and accelerated methods with momentum for solving stochastic optimization problems.

Stochastic Optimization

Robust Learning-based Predictive Control for Discrete-time Nonlinear Systems with Unknown Dynamics and State Constraints

no code implementations22 Nov 2019 Xinglong Zhang, Jiahang Liu, Xin Xu, Shuyou Yu, Hong Chen

Robust model predictive control (MPC) is a well-known control technique for model-based control with constraints and uncertainties.

Contraction methods for continuous optimization

1 code implementation3 Sep 2019 Xiaopeng Luo, Xin Xu

Motivated by the grid search method and Bayesian optimization, we introduce the concept of contractibility and its applications in model-based optimization.

Optimization and Control Computational Complexity Numerical Analysis Numerical Analysis 65K05, 68Q15, 90C26, 90C56

Coordinated Path Following Control of Fixed-wing Unmanned Aerial Vehicles

no code implementations13 Jun 2019 Hao Chen, Yirui Cong, Xiangke Wang, Xin Xu, Lincheng Shen

At the coordination level, we prove that even with speed constraints, the proposed control law can make sure the path following errors reduce to zero, while the desired arc distances converge to the desired value.

Sparse residual tree and forest

no code implementations18 Feb 2019 Xin Xu, Xiaopeng Luo

The hierarchical parallel SRT algorithm is based on both tree decomposition and adaptive radial basis function (RBF) explorations, whereby for each child a sparse and proper RBF refinement is added to the approximation by minimizing the norm of the residual inherited from its parent.

Tree Decomposition

Baidu Apollo Auto-Calibration System - An Industry-Level Data-Driven and Learning based Vehicle Longitude Dynamic Calibrating Algorithm

1 code implementation30 Aug 2018 Fan Zhu, Lin Ma, Xin Xu, Dingfeng Guo, Xiao Cui, Qi Kong

Since manual calibration is not sustainable once entering into mass production stage for industrial purposes, we here introduce a machine-learning based auto-calibration system for autonomous driving vehicles.

Autonomous Driving BIG-bench Machine Learning

Beyond Random Walk and Metropolis-Hastings Samplers: Why You Should Not Backtrack for Unbiased Graph Sampling

1 code implementation18 Apr 2012 Chul-Ho Lee, Xin Xu, Do Young Eun

In this paper, we propose non-backtracking random walk with re-weighting (NBRW-rw) and MH algorithm with delayed acceptance (MHDA) which are theoretically guaranteed to achieve, at almost no additional cost, not only unbiased graph sampling but also higher efficiency (smaller asymptotic variance of the resulting unbiased estimators) than the SRW-rw and the MH algorithm, respectively.

Methodology Data Structures and Algorithms Networking and Internet Architecture Social and Information Networks Data Analysis, Statistics and Probability Physics and Society

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