Search Results for author: Long Bai

Found 41 papers, 21 papers with code

Meta-CQG: A Meta-Learning Framework for Complex Question Generation over Knowledge Bases

no code implementations COLING 2022 Kun Zhang, Yunqi Qiu, Yuanzhuo Wang, Long Bai, Wei Li, Xuhui Jiang, HuaWei Shen, Xueqi Cheng

Complex question generation over knowledge bases (KB) aims to generate natural language questions involving multiple KB relations or functional constraints.

Contrastive Learning Decoder +3

Temporal Knowledge Graph Question Answering: A Survey

no code implementations20 Jun 2024 Miao Su, Zixuan Li, Zhuo Chen, Long Bai, Xiaolong Jin, Jiafeng Guo

In response, this paper provides a thorough survey from two perspectives: the taxonomy of temporal questions and the methodological categorization for TKGQA.

Graph Question Answering Knowledge Base Question Answering +1

EndoUIC: Promptable Diffusion Transformer for Unified Illumination Correction in Capsule Endoscopy

1 code implementation19 Jun 2024 Long Bai, Tong Chen, Qiaozhi Tan, Wan Jun Nah, Yanheng Li, ZhiCheng He, Sishen Yuan, Zhen Chen, Jinlin Wu, Mobarakol Islam, Zhen Li, Hongbin Liu, Hongliang Ren

While researchers have discussed the challenges of low-light enhancement in WCE, the issue of correcting for different exposure levels remains underexplored.

Image Enhancement Navigate +1

Learning to Adapt Foundation Model DINOv2 for Capsule Endoscopy Diagnosis

no code implementations15 Jun 2024 BoWen Zhang, Ying Chen, Long Bai, Yan Zhao, Yuxiang Sun, Yixuan Yuan, Jianhua Zhang, Hongliang Ren

Our method, inspired by the DINOv2 foundation model, applies low-rank adaptation learning to tailor foundation models for capsule endoscopy diagnosis effectively.

EndoDAC: Efficient Adapting Foundation Model for Self-Supervised Depth Estimation from Any Endoscopic Camera

1 code implementation14 May 2024 Beilei Cui, Mobarakol Islam, Long Bai, An Wang, Hongliang Ren

We propose Endoscopic Depth Any Camera (EndoDAC) which is an efficient self-supervised depth estimation framework that adapts foundation models to endoscopic scenes.

Depth Estimation Surface Reconstruction

Adapting SAM for Surgical Instrument Tracking and Segmentation in Endoscopic Submucosal Dissection Videos

no code implementations16 Apr 2024 Jieming Yu, Long Bai, Guankun Wang, An Wang, Xiaoxiao Yang, Huxin Gao, Hongliang Ren

Specifically, with a tiny subset of frames for segmentation, we ensure accurate segmentation across the entire surgical video.

Segmentation

Selective Temporal Knowledge Graph Reasoning

no code implementations2 Apr 2024 Zhongni Hou, Xiaolong Jin, Zixuan Li, Long Bai, Jiafeng Guo, Xueqi Cheng

Temporal Knowledge Graph (TKG), which characterizes temporally evolving facts in the form of (subject, relation, object, timestamp), has attracted much attention recently.

Class-Incremental Few-Shot Event Detection

no code implementations2 Apr 2024 Kailin Zhao, Xiaolong Jin, Long Bai, Jiafeng Guo, Xueqi Cheng

Therefore, this paper proposes a new task, called class-incremental few-shot event detection.

Event Detection Few-Shot Learning +1

KnowCoder: Coding Structured Knowledge into LLMs for Universal Information Extraction

no code implementations12 Mar 2024 Zixuan Li, Yutao Zeng, Yuxin Zuo, Weicheng Ren, Wenxuan Liu, Miao Su, Yucan Guo, Yantao Liu, Xiang Li, Zhilei Hu, Long Bai, Wei Li, Yidan Liu, Pan Yang, Xiaolong Jin, Jiafeng Guo, Xueqi Cheng

After instruction tuning, KnowCoder further exhibits strong generalization ability on unseen schemas and achieves up to $\textbf{12. 5%}$ and $\textbf{21. 9%}$, compared to sota baselines, under the zero-shot setting and the low resource setting, respectively.

Code Generation Language Modelling +2

EndoOOD: Uncertainty-aware Out-of-distribution Detection in Capsule Endoscopy Diagnosis

no code implementations18 Feb 2024 Qiaozhi Tan, Long Bai, Guankun Wang, Mobarakol Islam, Hongliang Ren

Wireless capsule endoscopy (WCE) is a non-invasive diagnostic procedure that enables visualization of the gastrointestinal (GI) tract.

Decision Making Out-of-Distribution Detection

OSSAR: Towards Open-Set Surgical Activity Recognition in Robot-assisted Surgery

1 code implementation10 Feb 2024 Long Bai, Guankun Wang, Jie Wang, Xiaoxiao Yang, Huxin Gao, Xin Liang, An Wang, Mobarakol Islam, Hongliang Ren

Existing algorithms dedicated to surgical activity recognition predominantly cater to pre-defined closed-set paradigms, ignoring the challenges of real-world open-set scenarios.

Activity Recognition

Privacy-Preserving Synthetic Continual Semantic Segmentation for Robotic Surgery

1 code implementation8 Feb 2024 Mengya Xu, Mobarakol Islam, Long Bai, Hongliang Ren

The problem becomes worse when it limits releasing the dataset of the old instruments for the old model due to privacy concerns and the unavailability of the data for the new or updated version of the instruments for the continual learning model.

Continual Learning Continual Semantic Segmentation +3

Endo-4DGS: Endoscopic Monocular Scene Reconstruction with 4D Gaussian Splatting

2 code implementations29 Jan 2024 Yiming Huang, Beilei Cui, Long Bai, Ziqi Guo, Mengya Xu, Mobarakol Islam, Hongliang Ren

In the realm of robot-assisted minimally invasive surgery, dynamic scene reconstruction can significantly enhance downstream tasks and improve surgical outcomes.

Dynamic Reconstruction Monocular Depth Estimation +2

Surgical-DINO: Adapter Learning of Foundation Models for Depth Estimation in Endoscopic Surgery

1 code implementation11 Jan 2024 Beilei Cui, Mobarakol Islam, Long Bai, Hongliang Ren

There is clear evidence in the results that zero-shot prediction on pre-trained weights in computer vision datasets or naive fine-tuning is not sufficient to use the foundation model in the surgical domain directly.

3D Reconstruction Depth Estimation

Retrieval-Augmented Code Generation for Universal Information Extraction

no code implementations6 Nov 2023 Yucan Guo, Zixuan Li, Xiaolong Jin, Yantao Liu, Yutao Zeng, Wenxuan Liu, Xiang Li, Pan Yang, Long Bai, Jiafeng Guo, Xueqi Cheng

Therefore, in this paper, we propose a universal retrieval-augmented code generation framework based on LLMs, called Code4UIE, for IE tasks.

Code Generation In-Context Learning +1

Joint Sparse Representations and Coupled Dictionary Learning in Multi-Source Heterogeneous Image Pseudo-color Fusion

no code implementations15 Oct 2023 Long Bai, Shilong Yao, Kun Gao, Yanjun Huang, Ruijie Tang, Hong Yan, Max Q. -H. Meng, Hongliang Ren

Considering that Coupled Dictionary Learning (CDL) method can obtain a reasonable linear mathematical relationship between resource images, we propose a novel CDL-based Synthetic Aperture Radar (SAR) and multispectral pseudo-color fusion method.

Dictionary Learning

ProtoEM: A Prototype-Enhanced Matching Framework for Event Relation Extraction

no code implementations22 Sep 2023 Zhilei Hu, Zixuan Li, Daozhu Xu, Long Bai, Cheng Jin, Xiaolong Jin, Jiafeng Guo, Xueqi Cheng

To comprehensively understand their intrinsic semantics, in this paper, we obtain prototype representations for each type of event relation and propose a Prototype-Enhanced Matching (ProtoEM) framework for the joint extraction of multiple kinds of event relations.

Event Relation Extraction Graph Neural Network +2

Nested Event Extraction upon Pivot Element Recogniton

1 code implementation22 Sep 2023 Weicheng Ren, Zixuan Li, Xiaolong Jin, Long Bai, Miao Su, Yantao Liu, Saiping Guan, Jiafeng Guo, Xueqi Cheng

Since existing NEE datasets (e. g., Genia11) are limited to specific domains and contain a narrow range of event types with nested structures, we systematically categorize nested events in the generic domain and construct a new NEE dataset, called ACE2005-Nest.

Event Extraction

Landmark Detection using Transformer Toward Robot-assisted Nasal Airway Intubation

1 code implementation5 Aug 2023 Tianhang Liu, Hechen Li, Long Bai, Yanan Wu, An Wang, Mobarakol Islam, Hongliang Ren

This paper proposes a transformer-based landmark detection solution with deformable DeTR and the semantic-aligned-matching module for detecting landmarks in robot-assisted intubation.

Revisiting Distillation for Continual Learning on Visual Question Localized-Answering in Robotic Surgery

1 code implementation22 Jul 2023 Long Bai, Mobarakol Islam, Hongliang Ren

We further establish a CL framework on three public surgical datasets in the context of surgical settings that consist of overlapping classes between old and new surgical VQLA tasks.

Continual Learning Scene Understanding

CAT-ViL: Co-Attention Gated Vision-Language Embedding for Visual Question Localized-Answering in Robotic Surgery

1 code implementation11 Jul 2023 Long Bai, Mobarakol Islam, Hongliang Ren

Therefore, a surgical Visual Question Localized-Answering (VQLA) system would be helpful for medical students and junior surgeons to learn and understand from recorded surgical videos.

Question Answering Scene Understanding +1

LLCaps: Learning to Illuminate Low-Light Capsule Endoscopy with Curved Wavelet Attention and Reverse Diffusion

1 code implementation5 Jul 2023 Long Bai, Tong Chen, Yanan Wu, An Wang, Mobarakol Islam, Hongliang Ren

Given the exuberant development of the denoising diffusion probabilistic model (DDPM) in computer vision, we introduce a WCE LLIE framework based on the multi-scale convolutional neural network (CNN) and reverse diffusion process.

Denoising Low-Light Image Enhancement

Semantic Structure Enhanced Event Causality Identification

no code implementations22 May 2023 Zhilei Hu, Zixuan Li, Xiaolong Jin, Long Bai, Saiping Guan, Jiafeng Guo, Xueqi Cheng

This is a very challenging task, because causal relations are usually expressed by implicit associations between events.

Event Causality Identification

Domain Adaptive Sim-to-Real Segmentation of Oropharyngeal Organs Towards Robot-assisted Intubation

no code implementations19 May 2023 Guankun Wang, Tian-Ao Ren, JIEWEN LAI, Long Bai, Hongliang Ren

Robotic-assisted tracheal intubation requires the robot to distinguish anatomical features like an experienced physician using deep-learning techniques.

Image Segmentation Segmentation +2

Surgical-VQLA: Transformer with Gated Vision-Language Embedding for Visual Question Localized-Answering in Robotic Surgery

1 code implementation19 May 2023 Long Bai, Mobarakol Islam, Lalithkumar Seenivasan, Hongliang Ren

In this paper, we propose Visual Question Localized-Answering in Robotic Surgery (Surgical-VQLA) to localize the specific surgical area during the answer prediction.

Answer Generation object-detection +3

Domain Adaptive Sim-to-Real Segmentation of Oropharyngeal Organs

1 code implementation18 May 2023 Guankun Wang, Tian-Ao Ren, JIEWEN LAI, Long Bai, Hongliang Ren

In this work, we propose a domain adaptive Sim-to-Real framework called IoU-Ranking Blend-ArtFlow (IRB-AF) for image segmentation of oropharyngeal organs.

Image Segmentation Segmentation +2

Rich Event Modeling for Script Event Prediction

1 code implementation16 Dec 2022 Long Bai, Saiping Guan, Zixuan Li, Jiafeng Guo, Xiaolong Jin, Xueqi Cheng

Fundamentally, it is based on the proposed rich event description, which enriches the existing ones with three kinds of important information, namely, the senses of verbs, extra semantic roles, and types of participants.

Two-stage Contextual Transformer-based Convolutional Neural Network for Airway Extraction from CT Images

1 code implementation15 Dec 2022 Yanan Wu, Shuiqing Zhao, Shouliang Qi, Jie Feng, Haowen Pang, Runsheng Chang, Long Bai, Mengqi Li, Shuyue Xia, Wei Qian, Hongliang Ren

In the first stage, the total airway mask and CT images are provided to the subnetwork, and the intrapulmonary airway mask and corresponding CT scans to the subnetwork in the second stage.

Computed Tomography (CT) Decoder +1

HiSMatch: Historical Structure Matching based Temporal Knowledge Graph Reasoning

no code implementations18 Oct 2022 Zixuan Li, Zhongni Hou, Saiping Guan, Xiaolong Jin, Weihua Peng, Long Bai, Yajuan Lyu, Wei Li, Jiafeng Guo, Xueqi Cheng

This is actually a matching task between a query and candidate entities based on their historical structures, which reflect behavioral trends of the entities at different timestamps.

Relation

Complex Evolutional Pattern Learning for Temporal Knowledge Graph Reasoning

1 code implementation ACL 2022 Zixuan Li, Saiping Guan, Xiaolong Jin, Weihua Peng, Yajuan Lyu, Yong Zhu, Long Bai, Wei Li, Jiafeng Guo, Xueqi Cheng

Furthermore, these models are all trained offline, which cannot well adapt to the changes of evolutional patterns from then on.

Diversity

What is Event Knowledge Graph: A Survey

1 code implementation31 Dec 2021 Saiping Guan, Xueqi Cheng, Long Bai, Fujun Zhang, Zixuan Li, Yutao Zeng, Xiaolong Jin, Jiafeng Guo

Besides entity-centric knowledge, usually organized as Knowledge Graph (KG), events are also an essential kind of knowledge in the world, which trigger the spring up of event-centric knowledge representation form like Event KG (EKG).

Question Answering Text Generation

Integrating Deep Event-Level and Script-Level Information for Script Event Prediction

1 code implementation EMNLP 2021 Long Bai, Saiping Guan, Jiafeng Guo, Zixuan Li, Xiaolong Jin, Xueqi Cheng

In this paper, we propose a Transformer-based model, called MCPredictor, which integrates deep event-level and script-level information for script event prediction.

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