Search Results for author: Xia Li

Found 64 papers, 31 papers with code

Data Augmentation of Incorporating Real Error Patterns and Linguistic Knowledge for Grammatical Error Correction

no code implementations CoNLL (EMNLP) 2021 Xia Li, Junyi He

Moreover, we also find that linguistic knowledge can be incorporated into data augmentation for generating more representative and more diverse synthetic data.

Data Augmentation Grammatical Error Correction

Multimodal Sentiment Analysis with Multi-perspective Fusion Network Focusing on Sense Attentive Language

no code implementations CCL 2020 Xia Li, Minping Chen

Different from previous studies, we use the language modality as the main part of the final joint representation, and propose a multi-stage and uni-stage fusion strategy to get the fusion representation of the multiple modalities to assist the final language-dominated multimodal representation.

Multimodal Sentiment Analysis

CPT-Interp: Continuous sPatial and Temporal Motion Modeling for 4D Medical Image Interpolation

no code implementations24 May 2024 Xia Li, Runzhao Yang, Xiangtai Li, Antony Lomax, Ye Zhang, Joachim Buhmann

Motion information from 4D medical imaging offers critical insights into dynamic changes in patient anatomy for clinical assessments and radiotherapy planning and, thereby, enhances the capabilities of 3D image analysis.

Continuous sPatial-Temporal Deformable Image Registration (CPT-DIR) for motion modelling in radiotherapy: beyond classic voxel-based methods

no code implementations1 May 2024 Xia Li, Muheng Li, Antony Lomax, Joachim Buhmann, Ye Zhang

Furthermore, CPT-DIR surpasses B-splines for accuracy in the sliding boundary region, lowering MAE and increasing Dice coefficients for the ribcage from 65. 65HU and 90. 41% to 42. 04HU and 90. 56%, versus 75. 40HU and 89. 30% without registration.

Image Registration

Image Copy-Move Forgery Detection via Deep PatchMatch and Pairwise Ranking Learning

no code implementations26 Apr 2024 Yuanman Li, Yingjie He, Changsheng chen, Li Dong, Bin Li, Jiantao Zhou, Xia Li

To address these limitations, this study proposes a novel end-to-end CMFD framework that integrates the strengths of conventional and deep learning methods.

UVMap-ID: A Controllable and Personalized UV Map Generative Model

1 code implementation22 Apr 2024 Weijie Wang, Jichao Zhang, Chang Liu, Xia Li, Xingqian Xu, Humphrey Shi, Nicu Sebe, Bruno Lepri

To solve the above problems, we introduce a novel method, UVMap-ID, which is a controllable and personalized UV Map generative model.


Point-In-Context: Understanding Point Cloud via In-Context Learning

1 code implementation18 Apr 2024 Mengyuan Liu, Zhongbin Fang, Xia Li, Joachim M. Buhmann, Xiangtai Li, Chen Change Loy

With the emergence of large-scale models trained on diverse datasets, in-context learning has emerged as a promising paradigm for multitasking, notably in natural language processing and image processing.

In-Context Learning

VG4D: Vision-Language Model Goes 4D Video Recognition

1 code implementation17 Apr 2024 Zhichao Deng, Xiangtai Li, Xia Li, Yunhai Tong, Shen Zhao, Mengyuan Liu

By transferring the knowledge of the VLM to the 4D encoder and combining the VLM, our VG4D achieves improved recognition performance.

Action Recognition Autonomous Driving +2

Diffusion Schrödinger Bridge Models for High-Quality MR-to-CT Synthesis for Head and Neck Proton Treatment Planning

no code implementations17 Apr 2024 Muheng Li, Xia Li, Sairos Safai, Damien Weber, Antony Lomax, Ye Zhang

The effectiveness of DSBM in MR-based proton treatment planning highlights its potential as a valuable tool in various clinical scenarios.

Image Generation

Neural Clustering based Visual Representation Learning

1 code implementation26 Mar 2024 Guikun Chen, Xia Li, Yi Yang, Wenguan Wang

In this work, we propose feature extraction with clustering (FEC), a conceptually elegant yet surprisingly ad-hoc interpretable neural clustering framework, which views feature extraction as a process of selecting representatives from data and thus automatically captures the underlying data distribution.

Clustering Representation Learning

MD-Dose: A Diffusion Model based on the Mamba for Radiotherapy Dose Prediction

1 code implementation13 Mar 2024 Linjie Fu, Xia Li, Xiuding Cai, Yingkai Wang, Xueyao Wang, Yali Shen, Yu Yao

To tackle these challenges, we introduce a novel diffusion model, MD-Dose, based on the Mamba architecture for predicting radiation therapy dose distribution in thoracic cancer patients.


Uncertainty-Aware Testing-Time Optimization for 3D Human Pose Estimation

no code implementations4 Feb 2024 Ti Wang, Mengyuan Liu, Hong Liu, Bin Ren, Yingxuan You, Wenhao Li, Nicu Sebe, Xia Li

We observe that previous optimization-based methods commonly rely on projection constraint, which only ensures alignment in 2D space, potentially leading to the overfitting problem.

3D Human Pose Estimation

ModelNet-O: A Large-Scale Synthetic Dataset for Occlusion-Aware Point Cloud Classification

1 code implementation16 Jan 2024 Zhongbin Fang, Xia Li, Xiangtai Li, Shen Zhao, Mengyuan Liu

Through extensive experiments, we demonstrate that our PointMLS achieves state-of-the-art results on ModelNet-O and competitive results on regular datasets, and it is robust and effective.

3D Point Cloud Classification Point Cloud Classification

Text-Driven Traffic Anomaly Detection with Temporal High-Frequency Modeling in Driving Videos

no code implementations7 Jan 2024 Rongqin Liang, Yuanman Li, Jiantao Zhou, Xia Li

Traffic anomaly detection (TAD) in driving videos is critical for ensuring the safety of autonomous driving and advanced driver assistance systems.

Anomaly Detection Autonomous Driving +1

Skeleton-in-Context: Unified Skeleton Sequence Modeling with In-Context Learning

1 code implementation6 Dec 2023 Xinshun Wang, Zhongbin Fang, Xia Li, Xiangtai Li, Chen Chen, Mengyuan Liu

Under this setting, the model can perceive tasks from prompts and accomplish them without any extra task-specific head predictions or model fine-tuning.

In-Context Learning motion prediction +1

FedLPA: One-shot Federated Learning with Layer-Wise Posterior Aggregation

no code implementations30 Sep 2023 Xiang Liu, Liangxi Liu, Feiyang Ye, Yunheng Shen, Xia Li, Linshan Jiang, Jialin Li

Efficiently aggregating trained neural networks from local clients into a global model on a server is a widely researched topic in federated learning.

Federated Learning

Calibration-based Dual Prototypical Contrastive Learning Approach for Domain Generalization Semantic Segmentation

1 code implementation25 Sep 2023 Muxin Liao, Shishun Tian, Yuhang Zhang, Guoguang Hua, Wenbin Zou, Xia Li

Based on these observations, a calibration-based dual prototypical contrastive learning (CDPCL) approach is proposed to reduce the domain discrepancy between the learned class-wise features and the prototypes of different domains for domain generalization semantic segmentation.

Contrastive Learning Domain Generalization +1

Co-Evolution of Pose and Mesh for 3D Human Body Estimation from Video

1 code implementation ICCV 2023 Yingxuan You, Hong Liu, Ti Wang, Wenhao Li, Runwei Ding, Xia Li

Despite significant progress in single image-based 3D human mesh recovery, accurately and smoothly recovering 3D human motion from a video remains challenging.

3D Human Pose Estimation Decoder +1

Multi-scale Target-Aware Framework for Constrained Image Splicing Detection and Localization

no code implementations18 Aug 2023 Yuxuan Tan, Yuanman Li, Limin Zeng, Jiaxiong Ye, Wei Wang, Xia Li

Additionally, in order to handle scale transformations, we introduce a multi-scale projection method, which can be readily integrated into our target-aware framework that enables the attention process to be conducted between tokens containing information of varying scales.

Image Copy-Move Forgery Detection via Deep Cross-Scale PatchMatch

no code implementations8 Aug 2023 Yingjie He, Yuanman Li, Changsheng chen, Xia Li

The recently developed deep algorithms achieve promising progress in the field of image copy-move forgery detection (CMFD).

Energy-Guided Diffusion Model for CBCT-to-CT Synthesis

no code implementations7 Aug 2023 Linjie Fu, Xia Li, Xiuding Cai, Dong Miao, Yu Yao, Yali Shen

Cone Beam CT (CBCT) plays a crucial role in Adaptive Radiation Therapy (ART) by accurately providing radiation treatment when organ anatomy changes occur.


A Memory-Augmented Multi-Task Collaborative Framework for Unsupervised Traffic Accident Detection in Driving Videos

no code implementations27 Jul 2023 Rongqin Liang, Yuanman Li, Yingxin Yi, Jiantao Zhou, Xia Li

Different from previous approaches, our method can more accurately detect both ego-involved and non-ego accidents by simultaneously modeling appearance changes and object motions in video frames through the collaboration of optical flow reconstruction and future object localization tasks.

Autonomous Driving Object +3

Explore In-Context Learning for 3D Point Cloud Understanding

2 code implementations NeurIPS 2023 Zhongbin Fang, Xiangtai Li, Xia Li, Joachim M. Buhmann, Chen Change Loy, Mengyuan Liu

With the rise of large-scale models trained on broad data, in-context learning has become a new learning paradigm that has demonstrated significant potential in natural language processing and computer vision tasks.

In-Context Learning

Interweaved Graph and Attention Network for 3D Human Pose Estimation

1 code implementation27 Apr 2023 Ti Wang, Hong Liu, Runwei Ding, Wenhao Li, Yingxuan You, Xia Li

Despite substantial progress in 3D human pose estimation from a single-view image, prior works rarely explore global and local correlations, leading to insufficient learning of human skeleton representations.

3D Human Pose Estimation

SGFormer: Semantic Graph Transformer for Point Cloud-based 3D Scene Graph Generation

1 code implementation20 Mar 2023 Changsheng Lv, Mengshi Qi, Xia Li, Zhengyuan Yang, Huadong Ma

In this paper, we propose a novel model called SGFormer, Semantic Graph TransFormer for point cloud-based 3D scene graph generation.

3d scene graph generation Graph Embedding +3

Randomized Kaczmarz in Adversarial Distributed Setting

no code implementations24 Feb 2023 Longxiu Huang, Xia Li, Deanna Needell

Additionally, the efficiency of the proposed methods for solving convex problems is shown in simulations with the presence of adversaries.

Betrayed by Captions: Joint Caption Grounding and Generation for Open Vocabulary Instance Segmentation

2 code implementations ICCV 2023 Jianzong Wu, Xiangtai Li, Henghui Ding, Xia Li, Guangliang Cheng, Yunhai Tong, Chen Change Loy

Experiments on the COCO dataset with two settings: Open Vocabulary Instance Segmentation (OVIS) and Open Set Panoptic Segmentation (OSPS) demonstrate the superiority of the CGG.

Caption Generation Instance Segmentation +2

STGlow: A Flow-based Generative Framework with Dual Graphormer for Pedestrian Trajectory Prediction

no code implementations21 Nov 2022 Rongqin Liang, Yuanman Li, Jiantao Zhou, Xia Li

Different from previous approaches, our method can more precisely model the underlying data distribution by optimizing the exact log-likelihood of motion behaviors.

Anomaly Detection Autonomous Driving +3

PI-Trans: Parallel-ConvMLP and Implicit-Transformation Based GAN for Cross-View Image Translation

1 code implementation9 Jul 2022 Bin Ren, Hao Tang, Yiming Wang, Xia Li, Wei Wang, Nicu Sebe

For semantic-guided cross-view image translation, it is crucial to learn where to sample pixels from the source view image and where to reallocate them guided by the target view semantic map, especially when there is little overlap or drastic view difference between the source and target images.

Generative Adversarial Network

Distributed randomized Kaczmarz for the adversarial workers

no code implementations28 Feb 2022 Xia Li, Longxiu Huang, Deanna Needell

Developing large-scale distributed methods that are robust to the presence of adversarial or corrupted workers is an important part of making such methods practical for real-world problems.

POI-Transformers: POI Entity Matching through POI Embeddings by Incorporating Semantic and Geographic Information

no code implementations29 Sep 2021 Jinbao Zhang, Changwang Zhang, Xiaojuan Liu, Xia Li, Weilin Liao, Penghua Liu, Yao Yao, Jihong Zhang

A general and robust POI embedding framework, the POI-Transformers, is initially proposed in this study to address these problems of POI entity matching.

Is Attention Better Than Matrix Decomposition?

3 code implementations ICLR 2021 Zhengyang Geng, Meng-Hao Guo, Hongxu Chen, Xia Li, Ke Wei, Zhouchen Lin

As an essential ingredient of modern deep learning, attention mechanism, especially self-attention, plays a vital role in the global correlation discovery.

Conditional Image Generation Semantic Segmentation

Optimization Induced Equilibrium Networks

no code implementations27 May 2021 Xingyu Xie, Qiuhao Wang, Zenan Ling, Xia Li, Yisen Wang, Guangcan Liu, Zhouchen Lin

In this paper, we investigate an emerging question: can an implicit equilibrium model's equilibrium point be regarded as the solution of an optimization problem?

PointFlow: Flowing Semantics Through Points for Aerial Image Segmentation

1 code implementation CVPR 2021 Xiangtai Li, Hao He, Xia Li, Duo Li, Guangliang Cheng, Jianping Shi, Lubin Weng, Yunhai Tong, Zhouchen Lin

Experimental results on three different aerial segmentation datasets suggest that the proposed method is more effective and efficient than state-of-the-art general semantic segmentation methods.

Image Segmentation Segmentation +1

Temporal Pyramid Network for Pedestrian Trajectory Prediction with Multi-Supervision

1 code implementation3 Dec 2020 Rongqin Liang, Yuanman Li, Xia Li, Yi Tang, Jiantao Zhou, Wenbin Zou

Predicting human motion behavior in a crowd is important for many applications, ranging from the natural navigation of autonomous vehicles to intelligent security systems of video surveillance.

Autonomous Vehicles Pedestrian Trajectory Prediction +1

SWAFN: Sentimental Words Aware Fusion Network for Multimodal Sentiment Analysis

1 code implementation COLING 2020 Minping Chen, Xia Li

For the aggregation part, we design a multitask of sentimental words classification to help and guide the deep fusion of the three modalities and obtain the final sentimental words aware fusion representation.

Multimodal Sentiment Analysis

Who killed Lilly Kane? A case study in applying knowledge graphs to crime fiction

no code implementations24 Nov 2020 Mariam Alaverdian, William Gilroy, Veronica Kirgios, Xia Li, Carolina Matuk, Daniel Mckenzie, Tachin Ruangkriengsin, Andrea Bertozzi, Jeffrey Brantingham

We present a preliminary study of a knowledge graph created from season one of the television show Veronica Mars, which follows the eponymous young private investigator as she attempts to solve the murder of her best friend Lilly Kane.

Knowledge Graphs

Towards Efficient Scene Understanding via Squeeze Reasoning

1 code implementation6 Nov 2020 Xiangtai Li, Xia Li, Ansheng You, Li Zhang, Guangliang Cheng, Kuiyuan Yang, Yunhai Tong, Zhouchen Lin

Instead of propagating information on the spatial map, we first learn to squeeze the input feature into a channel-wise global vector and perform reasoning within the single vector where the computation cost can be significantly reduced.

Instance Segmentation object-detection +4

COVID-19 Literature Topic-Based Search via Hierarchical NMF

no code implementations EMNLP (NLP-COVID19) 2020 Rachel Grotheer, Yihuan Huang, Pengyu Li, Elizaveta Rebrova, Deanna Needell, Longxiu Huang, Alona Kryshchenko, Xia Li, Kyung Ha, Oleksandr Kryshchenko

A dataset of COVID-19-related scientific literature is compiled, combining the articles from several online libraries and selecting those with open access and full text available.


Improving Semantic Segmentation via Decoupled Body and Edge Supervision

2 code implementations ECCV 2020 Xiangtai Li, Xia Li, Li Zhang, Guangliang Cheng, Jianping Shi, Zhouchen Lin, Shaohua Tan, Yunhai Tong

Our insight is that appealing performance of semantic segmentation requires \textit{explicitly} modeling the object \textit{body} and \textit{edge}, which correspond to the high and low frequency of the image.

Object Segmentation +1

Quasi-Dense Similarity Learning for Multiple Object Tracking

3 code implementations CVPR 2021 Jiangmiao Pang, Linlu Qiu, Xia Li, Haofeng Chen, Qi Li, Trevor Darrell, Fisher Yu

Compared to methods with similar detectors, it boosts almost 10 points of MOTA and significantly decreases the number of ID switches on BDD100K and Waymo datasets.

Contrastive Learning Metric Learning +4

Bi-directional Exponential Angular Triplet Loss for RGB-Infrared Person Re-Identification

1 code implementation1 Jun 2020 Hanrong Ye, Hong Liu, Fanyang Meng, Xia Li

As an angularly discriminative feature space is important for classifying the human images based on their embedding vectors, in this paper, we propose a novel ranking loss function, named Bi-directional Exponential Angular Triplet Loss, to help learn an angularly separable common feature space by explicitly constraining the included angles between embedding vectors.

Person Re-Identification

Spatial Pyramid Based Graph Reasoning for Semantic Segmentation

no code implementations CVPR 2020 Xia Li, Yibo Yang, Qijie Zhao, Tiancheng Shen, Zhouchen Lin, Hong Liu

The convolution operation suffers from a limited receptive filed, while global modeling is fundamental to dense prediction tasks, such as semantic segmentation.

Segmentation Semantic Segmentation

Dynamical System Inspired Adaptive Time Stepping Controller for Residual Network Families

no code implementations23 Nov 2019 Yibo Yang, Jianlong Wu, Hongyang Li, Xia Li, Tiancheng Shen, Zhouchen Lin

We establish a stability condition for ResNets with step sizes and weight parameters, and point out the effects of step sizes on the stability and performance.

SOGNet: Scene Overlap Graph Network for Panoptic Segmentation

1 code implementation18 Nov 2019 Yibo Yang, Hongyang Li, Xia Li, Qijie Zhao, Jianlong Wu, Zhouchen Lin

In order to overcome the lack of supervision, we introduce a differentiable module to resolve the overlap between any pair of instances.

Instance Segmentation Panoptic Segmentation +1

Quality Assessment of DIBR-synthesized views: An Overview

no code implementations16 Nov 2019 Shishun Tian, Lu Zhang, Wenbin Zou, Xia Li, Ting Su, Luce Morin, Olivier Deforges

In this paper, we provide a comprehensive survey on various current approaches for DIBR-synthesized views.

Masked Non-Autoregressive Image Captioning

no code implementations3 Jun 2019 Junlong Gao, Xi Meng, Shiqi Wang, Xia Li, Shanshe Wang, Siwei Ma, Wen Gao

Existing captioning models often adopt the encoder-decoder architecture, where the decoder uses autoregressive decoding to generate captions, such that each token is generated sequentially given the preceding generated tokens.

Decoder Image Captioning +2

Primitive-based 3D Building Modeling, Sensor Simulation, and Estimation

no code implementations16 Jan 2019 Xia Li, Yen-Liang Lin, James Miller, Alex Cheon, Walt Dixon

As we begin to consider modeling large, realistic 3D building scenes, it becomes necessary to consider a more compact representation over the polygonal mesh model.

Instance Segmentation Semantic Segmentation

Recurrent Squeeze-and-Excitation Context Aggregation Net for Single Image Deraining

no code implementations ECCV 2018 Xia Li, Jianlong Wu, Zhouchen Lin, Hong Liu, Hongbin Zha

In heavy rain, rain streaks have various directions and shapes, which can be regarded as the accumulation of multiple rain streak layers.

Single Image Deraining

Compression of phase-only holograms with JPEG standard and deep learning

no code implementations11 Jun 2018 Shuming Jiao, Zhi Jin, Chenliang Chang, Changyuan Zhou, Wenbin Zou, Xia Li

It is a critical issue to reduce the enormous amount of data in the processing, storage and transmission of a hologram in digital format.

Review on Optical Image Hiding and Watermarking Techniques

no code implementations16 Apr 2018 Shuming Jiao, Changyuan Zhou, Yishi Shi, Wenbin Zou, Xia Li

Information security is a critical issue in modern society and image watermarking can effectively prevent unauthorized information access.

Sensing Urban Land-Use Patterns By Integrating Google Tensorflow And Scene-Classification Models

no code implementations4 Aug 2017 Yao Yao, Haolin Liang, Xia Li, Jinbao Zhang, Jialv He

To take advantage of the deep-learning method in detecting urban land-use patterns, we applied a transfer-learning-based remote-sensing image approach to extract and classify features.

General Classification Scene Classification +1

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