Search Results for author: Dong-Kyu Chae

Found 6 papers, 4 papers with code

BanglaAutoKG: Automatic Bangla Knowledge Graph Construction with Semantic Neural Graph Filtering

1 code implementation4 Apr 2024 Azmine Toushik Wasi, Taki Hasan Rafi, Raima Islam, Dong-Kyu Chae

Knowledge Graphs (KGs) have proven essential in information processing and reasoning applications because they link related entities and give context-rich information, supporting efficient information retrieval and knowledge discovery; presenting information flow in a very effective manner.

graph construction Information Retrieval +6

SentiCSE: A Sentiment-aware Contrastive Sentence Embedding Framework with Sentiment-guided Textual Similarity

1 code implementation1 Apr 2024 JaeMin Kim, Yohan Na, KangMin Kim, Sang Rak Lee, Dong-Kyu Chae

However, they neglect to evaluate the quality of their constructed sentiment representations; they just focus on improving the fine-tuning performance, which overshadows the representation quality.

Sentence Sentence Embedding +2

CADGL: Context-Aware Deep Graph Learning for Predicting Drug-Drug Interactions

no code implementations25 Mar 2024 Azmine Toushik Wasi, Taki Hasan Rafi, Raima Islam, Serbetar Karlo, Dong-Kyu Chae

CADGL surpasses other state-of-the-art DDI prediction models, excelling in predicting clinically valuable novel DDIs, supported by rigorous case studies.

Decoder Drug–drug Interaction Extraction +1

Towards Category Unification of 3D Single Object Tracking on Point Clouds

no code implementations20 Jan 2024 Jiahao Nie, Zhiwei He, Xudong Lv, Xueyi Zhou, Dong-Kyu Chae, Fei Xie

Based on this observation, we design a novel point set representation learning network inheriting transformer architecture, termed AdaFormer, which adaptively encodes the dynamically varying shape and size information from cross-category data in a unified manner.

3D Single Object Tracking Attribute +2

ARBEx: Attentive Feature Extraction with Reliability Balancing for Robust Facial Expression Learning

1 code implementation2 May 2023 Azmine Toushik Wasi, Karlo Šerbetar, Raima Islam, Taki Hasan Rafi, Dong-Kyu Chae

We also employ learnable anchor points in the embedding space with label distributions and multi-head self-attention mechanism to optimize performance against weak predictions with reliability balancing, which is a strategy that leverages anchor points, attention scores, and confidence values to enhance the resilience of label predictions.

Facial Expression Recognition (FER)

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