Search Results for author: Jinyoung Park

Found 24 papers, 18 papers with code

VidChain: Chain-of-Tasks with Metric-based Direct Preference Optimization for Dense Video Captioning

1 code implementation12 Jan 2025 Ji Soo Lee, Jongha Kim, Jeehye Na, Jinyoung Park, Hyunwoo J. Kim

Despite the advancements of Video Large Language Models (VideoLLMs) in various tasks, they struggle with fine-grained temporal understanding, such as Dense Video Captioning (DVC).

Dense Video Captioning Video Grounding +3

Difficulty-aware Balancing Margin Loss for Long-tailed Recognition

1 code implementation20 Dec 2024 Minseok Son, Inyong Koo, Jinyoung Park, Changick Kim

When trained with severely imbalanced data, deep neural networks often struggle to accurately recognize classes with only a few samples.

Inversion-based Latent Bayesian Optimization

1 code implementation8 Nov 2024 Jaewon Chu, Jinyoung Park, Seunghun Lee, Hyunwoo J. Kim

LBO learns a surrogate model to approximate the black-box objective function in the latent space.

Bayesian Optimization Decoder

LLaMo: Large Language Model-based Molecular Graph Assistant

1 code implementation31 Oct 2024 Jinyoung Park, Minseong Bae, Dohwan Ko, Hyunwoo J. Kim

Thus, we propose LLaMo: Large Language Model-based Molecular graph assistant, which is an end-to-end trained large molecular graph-language model.

Instruction Following IUPAC Name Prediction +6

Generative Subgraph Retrieval for Knowledge Graph-Grounded Dialog Generation

1 code implementation12 Oct 2024 Jinyoung Park, Minseok Joo, Joo-Kyung Kim, Hyunwoo J. Kim

Knowledge graph-grounded dialog generation requires retrieving a dialog-relevant subgraph from the given knowledge base graph and integrating it with the dialog history.

Informativeness Retrieval +1

VideoMamba: Spatio-Temporal Selective State Space Model

1 code implementation11 Jul 2024 Jinyoung Park, Hee-Seon Kim, Kangwook Ko, Minbeom Kim, Changick Kim

We introduce VideoMamba, a novel adaptation of the pure Mamba architecture, specifically designed for video recognition.

Mamba model +2

Flow-Assisted Motion Learning Network for Weakly-Supervised Group Activity Recognition

no code implementations28 May 2024 Muhammad Adi Nugroho, Sangmin Woo, Sumin Lee, Jinyoung Park, Yooseung Wang, Donguk Kim, Changick Kim

The first pathway of the relation module, the actor-centric path, initially captures the temporal dynamics of individual actors and then constructs inter-actor relationships.

Group Activity Recognition Optical Flow Estimation +1

Prompt Learning via Meta-Regularization

1 code implementation CVPR 2024 Jinyoung Park, Juyeon Ko, Hyunwoo J. Kim

Recently, prompt learning approaches have been explored to efficiently and effectively adapt the vision-language models to a variety of downstream tasks.

Domain Generalization General Knowledge +1

Groupwise Query Specialization and Quality-Aware Multi-Assignment for Transformer-based Visual Relationship Detection

1 code implementation CVPR 2024 Jongha Kim, Jihwan Park, Jinyoung Park, Jinyoung Kim, Sehyung Kim, Hyunwoo J. Kim

Groupwise Query Specialization trains a specialized query by dividing queries and relations into disjoint groups and directing a query in a specific query group solely toward relations in the corresponding relation group.

Relation Relationship Detection +2

Graph Elicitation for Guiding Multi-Step Reasoning in Large Language Models

no code implementations16 Nov 2023 Jinyoung Park, Ameen Patel, Omar Zia Khan, Hyunwoo J. Kim, Joo-Kyung Kim

To deal with them, we propose a GE-Reasoning method, which directs LLMs to generate proper sub-questions and corresponding answers.

Multi-hop Question Answering Question Answering +3

Sketch-based Video Object Localization

1 code implementation2 Apr 2023 Sangmin Woo, So-Yeong Jeon, Jinyoung Park, Minji Son, Sumin Lee, Changick Kim

We introduce Sketch-based Video Object Localization (SVOL), a new task aimed at localizing spatio-temporal object boxes in video queried by the input sketch.

Object Object Localization +1

Self-positioning Point-based Transformer for Point Cloud Understanding

1 code implementation CVPR 2023 Jinyoung Park, Sanghyeok Lee, Sihyeon Kim, Yunyang Xiong, Hyunwoo J. Kim

In this paper, we present a Self-Positioning point-based Transformer (SPoTr), which is designed to capture both local and global shape contexts with reduced complexity.

3D Part Segmentation Scene Segmentation +1

Relation-Aware Language-Graph Transformer for Question Answering

1 code implementation2 Dec 2022 Jinyoung Park, Hyeong Kyu Choi, Juyeon Ko, Hyeonjin Park, Ji-Hoon Kim, Jisu Jeong, KyungMin Kim, Hyunwoo J. Kim

To address these issues, we propose Question Answering Transformer (QAT), which is designed to jointly reason over language and graphs with respect to entity relations in a unified manner.

MedQA Question Answering +1

Deformable Graph Transformer

no code implementations29 Jun 2022 Jinyoung Park, Seongjun Yun, Hyeonjin Park, Jaewoo Kang, Jisu Jeong, Kyung-Min Kim, Jung-Woo Ha, Hyunwoo J. Kim

Transformer-based models have recently shown success in representation learning on graph-structured data beyond natural language processing and computer vision.

Representation Learning

Metropolis-Hastings Data Augmentation for Graph Neural Networks

no code implementations NeurIPS 2021 Hyeonjin Park, Seunghun Lee, Sihyeon Kim, Jinyoung Park, Jisu Jeong, Kyung-Min Kim, Jung-Woo Ha, Hyunwoo J. Kim

We also propose a simple and effective semi-supervised learning strategy with generated samples from MH-Aug. Our extensive experiments demonstrate that MH-Aug can generate a sequence of samples according to the target distribution to significantly improve the performance of GNNs.

Data Augmentation Diversity

Explore-And-Match: Bridging Proposal-Based and Proposal-Free With Transformer for Sentence Grounding in Videos

1 code implementation25 Jan 2022 Sangmin Woo, Jinyoung Park, Inyong Koo, Sumin Lee, Minki Jeong, Changick Kim

To our surprise, we found that training schedule shows divide-and-conquer-like pattern: time segments are first diversified regardless of the target, then coupled with each target, and fine-tuned to the target again.

Natural Language Queries Sentence +2

Deformable Graph Convolutional Networks

1 code implementation29 Dec 2021 Jinyoung Park, Sungdong Yoo, Jihwan Park, Hyunwoo J. Kim

To address the two common problems of graph convolution, in this paper, we propose Deformable Graph Convolutional Networks (Deformable GCNs) that adaptively perform convolution in multiple latent spaces and capture short/long-range dependencies between nodes.

Node Classification on Non-Homophilic (Heterophilic) Graphs Representation Learning

OCR-free Document Understanding Transformer

5 code implementations30 Nov 2021 Geewook Kim, Teakgyu Hong, Moonbin Yim, Jeongyeon Nam, Jinyoung Park, Jinyeong Yim, Wonseok Hwang, Sangdoo Yun, Dongyoon Han, Seunghyun Park

Current Visual Document Understanding (VDU) methods outsource the task of reading text to off-the-shelf Optical Character Recognition (OCR) engines and focus on the understanding task with the OCR outputs.

Document Image Classification document understanding +4

Deep neural network for solving differential equations motivated by Legendre-Galerkin approximation

no code implementations24 Oct 2020 Bryce Chudomelka, Youngjoon Hong, Hyunwoo Kim, Jinyoung Park

Nonlinear differential equations are challenging to solve numerically and are important to understanding the dynamics of many physical systems.

Robust Neural Networks inspired by Strong Stability Preserving Runge-Kutta methods

1 code implementation ECCV 2020 Byungjoo Kim, Bryce Chudomelka, Jinyoung Park, Jaewoo Kang, Youngjoon Hong, Hyunwoo J. Kim

Motivated by the SSP property and a generalized Runge-Kutta method, we propose Strong Stability Preserving networks (SSP networks) which improve robustness against adversarial attacks.

The number of maximal independent sets in the Hamming cube

no code implementations10 Sep 2019 Jeff Kahn, Jinyoung Park

Let $Q_n$ be the $n$-dimensional Hamming cube and $N=2^n$.

Combinatorics 05C69

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