Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileAcademic lineage
Possible advisorsa guess from early papers, not confirmed
- Seong-Bae ParkSuggested from co-authorship
- Lili JiangSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works52 from public data
- Modular Graph Transformer Networks for Multi-Label Image Classification83
The paper presents a modular learning scheme to enhance the classification performance by segregating the computational graph into multiple sub-graphs based on modularity and validates the framework on MS-COCO and Fashion550K datasets to demonstrate improvements for multi-label image classification.
- 35
- ETNLP: A Visual-Aided Systematic Approach to Select Pre-Trained Embeddings for a Downstream Task29
This paper proposes a systematic approach for extracting, evaluating, and visualizing multiple sets of pre-trained word embeddings to determine whichembeddings should be used in a downstream task and creates an open-source system using the proposed systematic approach to facilitate similar studies on other NLP tasks.
- Privacy-Preserving Visual Content Tagging using Graph Transformer Networks26
An end-to-end framework (SGTN) using Graph Transformer and Convolutional Networks to significantly improve classification and privacy preservation of visual data and unveils new state-of-the-art on MS-COCO dataset in various semi-supervised settings.
- NIHRIO at SemEval-2018 Task 3: A Simple and Accurate Neural Network Model for Irony Detection in Twitter24
This paper describes the NIHRIO system for SemEval-2018 Task 3 “Irony detection in English tweets”, which achieves very high performance in both subtasks of binary and multi-class irony detection in tweets.
- 23
- ViGPTQA - State-of-the-Art LLMs for Vietnamese Question Answering: System Overview, Core Models Training, and Evaluations22
This paper introduces a practical real-world implementation of a question answering system for Vietnamese, called ViGPTQA, leveraging the power of LLM, and proposes, evaluates, and open-source an instruction-tuned LLM for Vietnamese, named ViGPT.
- 18
- 18
- Reinforced Transformer Learning for VSI-DDoS Detection in Edge Clouds17
This work proposes a novel and efficient approach for detecting VSI-DDoS attacks using reinforced transformer learning that mitigates the tail latency and service availability problems in edge clouds and demonstrates that the proposed approach is suitable, effective, and efficient.
- 15
- ICDAR 2021 Competition on Multimodal Emotion Recognition on Comics Scenes15
The motivation, dataset preparation, task definition of the competition, the analysis of participant’s performance and submitted methods believe that the competition have drawn attention from the document analysis community in both computer vision and natural language processing on the task of emotion recognition in documents.
- dpUGC: Learn Differentially Private Representation for User Generated Contents (Best Paper Award, Third Place, Shared)13
A user-level approach to learn personalized differentially private word embedding model on user generated contents (UGC) to protect the privacy of the individual from re-identification and provide better trade-off of privacy and data utility on UGC data for sharing.
- 13
- Graph-based Interactive Data Federation System for Heterogeneous Data Retrieval and Analytics13
An interactive data federation system is presented by applying large-scale techniques including heterogeneous data federation, natural language processing, association rules and semantic web to perform data retrieval and analytics on social network data.
- 13
- Lexical-semantic resources: yet powerful resources for automatic personality classification12
This paper proposes and extracts three types of lexical-semantic features, which capture high-level concepts and emotions, overcoming the lexical gap of word n-grams.
- VLSP 2021 - VieCap4H Challenge: Automatic Image Caption Generation for Healthcare Domain in Vietnamese11
VieCap4H is presented, a novel human-annotated image captioning dataset in Vietnamese that contains over 10,000 image-caption pairs collected from real-world scenarios in the healthcare domain that was run on AIHUB.VN platform.
- Self-adaptive Privacy Concern Detection for User-Generated Content10
This work proposes a self-adaptive approach for privacy concern detection based on user personality and demonstrates the effectiveness to address a suitable personalized privacy protection for cold-start users.
- 10
- MGLEP: Multimodal Graph Learning for Modeling Emerging Pandemics with Big Data9
A novel framework that integrates temporal graph neural networks and multi-modal data for learning and forecasting, and incorporates big data sources, including social media content, by utilizing specific pre-trained language models and discovering the underlying graph structure among users is proposed.
- 9
- Cformer9
This work proposes a semi-supervised learning method called Cformer for automatic clustering of text documents in cases where clusters are described by a small number of labeled examples, while the majority of training examples are unlabeled.
- Multimodal Review Generation with Privacy and Fairness Awareness9
MG-PriFair is the first to bring user privacy and sentiment fairness into the review generation task and is capable of generating plausibly long reviews while controlling the amount of exploited user data and using the least sentiment biased word embeddings.
- 9
- 9
- Building a Vietnamese SentiWordNet Using Vietnamese Electronic Dictionary and String Kernel9
A novel approach to construct a Vietnamese SentiWordNet (VSWN), a lexical resource supporting sentiment analysis in Vietnamese, by adopting a string kernel function which measures the string similarity based on both common contiguous and non-contiguous subsequences.
- Pseudonymization Categories across Domain Boundaries8
An analysis of tagsets that have previously been utilized in anonymization and pseudonymization reveals that none of the analyzed tagsets account for all of the PII types present cross-domain at the level of detailedness seemingly required for pseudonymization.
- Personality-based Knowledge Extraction for Privacy-preserving Data Analysis8
A differential privacy preserving approach, which extracts personality-based knowledge to serve privacy guarantee data analysis on personal sensitive data, is presented and an end-to-end privacy guarantee system, KaPPA, is implemented to provide researchers iterativeData analysis on sensitive data.
- NeuProNet: neural profiling networks for sound classification7
This work proposes novel neural profiling networks (NeuProNet) capable of learning and extracting high-level unique profile representations from sounds, and introduces an in-batch profile grouping mechanism based on profile awareness and attention pooling to produce reliable and robust features with contrastive learning.
- ETNLP: A Toolkit for Extraction, Evaluation and Visualization of Pre-trained Word Embeddings.6
A comprehensive toolkit, ETNLP, which can evaluate, extract, and visualize multiple sets of pre-trained word embeddings, and has a visualization module which is for exploring the embedded words interactively is introduced.
- Grandma Karl is 27 years old – research agenda for pseudonymization of research data5
There is need of studies into the effects of pseudonymization on unstructured data in relation to e.g. readability and language assessment, as well as the effectiveness of pseudonymized as a way of protecting writer identity, while also exploring different ways of developing context-sensitive algorithms for detection, labelling and replacement of personal information in unstructuring data.
- 5
- 5
- 4
- 3
- 3
- Improving Recurrent Neural Networks with Predictive Propagation for Sequence Labelling3
By propagating the prediction of previous labels the authors can improve the performance of RNNs while keeping the number of parameters in RNN's unchanged and adding only one more step for inference, which is still more compact and efficient than other models with complex memory gates.
- Improving Text-Based Image Search with Textual and Visual Features Combination3
A unified framework to cluster and re-rank returned images with respect to an input query is proposed and the experimental results show that the proposed model can significantly improve the performance of a text-based image search system (i.e. Flickr).
- 1
- 1
- Reason-to-Learn (R2L): Multi-Agent Knowledge Distillation for Lightweight LLMs in Sentiment Analysis–
Reason-to-Learn (R2L), a novel multi-agent collaborative knowledge distillation framework enabling small LLMs to learn from a distributed system of specialized agent models, offers an efficient path to compact, high-performing specialist models through coordinated multi-agent learning.
- –
- –
- –
- –
- –
- –
- –
- Personalization for Robust Voice Pathology Detection in Sound Waves–
A non-invasive framework that contrastively learns personalization from sound waves as a pre-train and predicts latent-spaced profile features through semi-supervised learning is proposed, which allows all subjects from various distributions to benefit from personalized predictions for robust voice pathology in a privacy-fulfilled manner.
- –
- –
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-14. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.