Search Results for author: Jinpeng Li

Found 34 papers, 20 papers with code

VSTAR: A Video-grounded Dialogue Dataset for Situated Semantic Understanding with Scene and Topic Transitions

1 code implementation30 May 2023 Yuxuan Wang, Zilong Zheng, Xueliang Zhao, Jinpeng Li, Yueqian Wang, Dongyan Zhao

Video-grounded dialogue understanding is a challenging problem that requires machine to perceive, parse and reason over situated semantics extracted from weakly aligned video and dialogues.

Dialogue Generation Dialogue Understanding +1

Cross-lingual Alzheimer's Disease detection based on paralinguistic and pre-trained features

no code implementations14 Mar 2023 Xuchu Chen, Yu Pu, Jinpeng Li, Wei-Qiang Zhang

We present our submission to the ICASSP-SPGC-2023 ADReSS-M Challenge Task, which aims to investigate which acoustic features can be generalized and transferred across languages for Alzheimer's Disease (AD) prediction.

alzheimer's disease detection

PointPatchMix: Point Cloud Mixing with Patch Scoring

no code implementations12 Mar 2023 Yi Wang, Jiaze Wang, Jinpeng Li, Zixu Zhao, Guangyong Chen, Anfeng Liu, Pheng-Ann Heng

With Point-MAE as our baseline, our model surpasses previous methods by a significant margin, achieving 86. 3% accuracy on ScanObjectNN and 94. 1% accuracy on ModelNet40.

Data Augmentation

Recognizing Nested Entities from Flat Supervision: A New NER Subtask, Feasibility and Challenges

no code implementations1 Nov 2022 Enwei Zhu, Yiyang Liu, Ming Jin, Jinpeng Li

However, existing nested NER models heavily rely on training data annotated with nested entities, while labeling such data is costly.

named-entity-recognition Named Entity Recognition +1

Decoding Visual Neural Representations by Multimodal Learning of Brain-Visual-Linguistic Features

1 code implementation13 Oct 2022 Changde Du, Kaicheng Fu, Jinpeng Li, Huiguang He

Finally, we construct three trimodal matching datasets, and the extensive experiments lead to some interesting conclusions and cognitive insights: 1) decoding novel visual categories from human brain activity is practically possible with good accuracy; 2) decoding models using the combination of visual and linguistic features perform much better than those using either of them alone; 3) visual perception may be accompanied by linguistic influences to represent the semantics of visual stimuli.

Deep Span Representations for Named Entity Recognition

1 code implementation9 Oct 2022 Enwei Zhu, Yiyang Liu, Jinpeng Li

However, this typically results in significant ineffectiveness for long-span entities, a coupling between the representations of overlapping spans, and ultimately a performance degradation.

named-entity-recognition Named Entity Recognition +1

Spiral Contrastive Learning: An Efficient 3D Representation Learning Method for Unannotated CT Lesions

no code implementations23 Aug 2022 Penghua Zhai, Enwei Zhu, Baolian Qi, Xin Wei, Jinpeng Li

In the past five years, several works have tailored for unsupervised representations of CT lesions via two-dimensional (2D) and three-dimensional (3D) self-supervised learning (SSL) algorithms.

Computed Tomography (CT) Contrastive Learning +3

CM-MLP: Cascade Multi-scale MLP with Axial Context Relation Encoder for Edge Segmentation of Medical Image

1 code implementation23 Aug 2022 Jinkai Lv, Yuyong Hu, Quanshui Fu, Zhiwang Zhang, Yuqiang Hu, Lin Lv, Guoqing Yang, Jinpeng Li, Yi Zhao

However, those methods have the following challenges when dealing with the edges of the medical images: (1) Previous convolutional-based methods do not focus on the boundary relationship between foreground and background around the segmentation edge, which leads to the degradation of segmentation performance when the edge changes complexly.

Image Segmentation Inductive Bias +2

Deep 3D Vessel Segmentation based on Cross Transformer Network

1 code implementation22 Aug 2022 Chengwei Pan, Baolian Qi, Gangming Zhao, Jiaheng Liu, Chaowei Fang, Dingwen Zhang, Jinpeng Li

In CTN, a transformer module is constructed in parallel to a U-Net to learn long-distance dependencies between different anatomical regions; and these dependencies are communicated to the U-Net at multiple stages to endow it with global awareness.

Computed Tomography (CT)

Computer-aided Tuberculosis Diagnosis with Attribute Reasoning Assistance

1 code implementation1 Jul 2022 Chengwei Pan, Gangming Zhao, Junjie Fang, Baolian Qi, Jiaheng Liu, Chaowei Fang, Dingwen Zhang, Jinpeng Li, Yizhou Yu

Although deep learning algorithms have been intensively developed for computer-aided tuberculosis diagnosis (CTD), they mainly depend on carefully annotated datasets, leading to much time and resource consumption.

Relational Reasoning Weakly-supervised Learning

Boundary Smoothing for Named Entity Recognition

1 code implementation ACL 2022 Enwei Zhu, Jinpeng Li

Neural named entity recognition (NER) models may easily encounter the over-confidence issue, which degrades the performance and calibration.

Chinese Named Entity Recognition named-entity-recognition +3

Benchmarking Domain Generalization on EEG-based Emotion Recognition

no code implementations18 Apr 2022 Yan Li, Hao Chen, Jake Zhao, Haolan Zhang, Jinpeng Li

Specifically, numerous domain adaptation (DA) algorithms have been exploited in the past five years to enhance the generalization of emotion recognition models across subjects.

Benchmarking Domain Generalization +2

A Unified Framework of Medical Information Annotation and Extraction for Chinese Clinical Text

1 code implementation8 Mar 2022 Enwei Zhu, Qilin Sheng, Huanwan Yang, Jinpeng Li

The resulted annotated corpus includes 1, 200 full medical records (or 18, 039 broken-down documents), and achieves inter-annotator agreements (IAAs) of 94. 53%, 73. 73% and 91. 98% F 1 scores for the three tasks.

Attribute Extraction Relation Extraction

Pedestrian Detection: Domain Generalization, CNNs, Transformers and Beyond

2 code implementations10 Jan 2022 Irtiza Hasan, Shengcai Liao, Jinpeng Li, Saad Ullah Akram, Ling Shao

As for the data, we show that the autonomous driving benchmarks are monotonous in nature, that is, they are not diverse in scenarios and dense in pedestrians.

Autonomous Driving Domain Generalization +4

Stylized Dialogue Generation with Multi-Pass Dual Learning

1 code implementation NeurIPS 2021 Jinpeng Li, Yingce Xia, Rui Yan, Hongda Sun, Dongyan Zhao, Tie-Yan Liu

Considering there is no parallel data between the contexts and the responses of target style S1, existing works mainly use back translation to generate stylized synthetic data for training, where the data about context, target style S1 and an intermediate style S0 is used.

Dialogue Generation

Efficient Person Search: An Anchor-Free Approach

3 code implementations1 Sep 2021 Yichao Yan, Jinpeng Li, Jie Qin, Shengcai Liao, Xiaokang Yang

Third, by investigating the advantages of both anchor-based and anchor-free models, we further augment AlignPS with an ROI-Align head, which significantly improves the robustness of re-id features while still keeping our model highly efficient.

Person Search

MVCNet: Multiview Contrastive Network for Unsupervised Representation Learning for 3D CT Lesions

no code implementations17 Aug 2021 Penghua Zhai, Huaiwei Cong, Gangming Zhao, Chaowei Fang, Jinpeng Li, Ting Cai, Huiguang He

To avoid the subjectivity associated with these methods, we propose the MVCNet, a novel unsupervised three dimensional (3D) representation learning method working in a transformation-free manner.

Computed Tomography (CT) Representation Learning +1

Polyp-PVT: Polyp Segmentation with Pyramid Vision Transformers

2 code implementations16 Aug 2021 Bo Dong, Wenhai Wang, Deng-Ping Fan, Jinpeng Li, Huazhu Fu, Ling Shao

Unlike existing CNN-based methods, we adopt a transformer encoder, which learns more powerful and robust representations.

Medical Image Segmentation

MS-MDA: Multisource Marginal Distribution Adaptation for Cross-subject and Cross-session EEG Emotion Recognition

1 code implementation16 Jul 2021 Hao Chen, Ming Jin, Zhunan Li, Cunhang Fan, Jinpeng Li, Huiguang He

Although several studies have adopted domain adaptation (DA) approaches to tackle this problem, most of them treat multiple EEG data from different subjects and sessions together as a single source domain for transfer, which either fails to satisfy the assumption of domain adaptation that the source has a certain marginal distribution, or increases the difficulty of adaptation.

Domain Adaptation EEG Emotion Recognition +2

GREN: Graph-Regularized Embedding Network for Weakly-Supervised Disease Localization in X-ray Images

1 code implementation14 Jul 2021 Baolian Qi, Gangming Zhao, Xin Wei, Changde Du, Chengwei Pan, Yizhou Yu, Jinpeng Li

To model the relationship, we propose the Graph Regularized Embedding Network (GREN), which leverages the intra-image and inter-image information to locate diseases on chest X-ray images.

Decision Making

When Liebig's Barrel Meets Facial Landmark Detection: A Practical Model

no code implementations27 May 2021 Haibo Jin, Jinpeng Li, Shengcai Liao, Ling Shao

To this end, we first propose a baseline model equipped with one transformer decoder as detection head.

Facial Landmark Detection

Anchor-Free Person Search

1 code implementation CVPR 2021 Yichao Yan, Jinpeng Li, Jie Qin, Song Bai, Shengcai Liao, Li Liu, Fan Zhu, Ling Shao

Person search aims to simultaneously localize and identify a query person from realistic, uncropped images, which can be regarded as the unified task of pedestrian detection and person re-identification (re-id).

Pedestrian Detection Person Re-Identification +1

Investigating Critical Risk Factors in Liver Cancer Prediction

no code implementations3 Feb 2021 Jinpeng Li, Yaling Tao, Ting Cai

We exploit liver cancer prediction model using machine learning algorithms based on epidemiological data of over 55 thousand peoples from 2014 to the present.

BIG-bench Machine Learning

Generalizable Pedestrian Detection: The Elephant In The Room

1 code implementation CVPR 2021 Irtiza Hasan, Shengcai Liao, Jinpeng Li, Saad Ullah Akram, Ling Shao

Furthermore, we illustrate that diverse and dense datasets, collected by crawling the web, serve to be an efficient source of pre-training for pedestrian detection.

Ranked #2 on Pedestrian Detection on CityPersons (using extra training data)

Autonomous Driving Pedestrian Detection

DuBox: No-Prior Box Objection Detection via Residual Dual Scale Detectors

no code implementations15 Apr 2019 Shuai Chen, Jinpeng Li, Chuanqi Yao, Wenbo Hou, Shuo Qin, Wenyao Jin, Xu Tang

Working with multi-scale features, the designed dual scale residual unit makes dual scale detectors no longer run independently.

object-detection Object Detection

Semi-supervised Bayesian Deep Multi-modal Emotion Recognition

no code implementations25 Apr 2017 Changde Du, Changying Du, Jinpeng Li, Wei-Long Zheng, Bao-liang Lu, Huiguang He

In this paper, we first build a multi-view deep generative model to simulate the generative process of multi-modality emotional data.

Emotion Recognition Imputation

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