Author name cluster

Jin-Woo Park

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

8 papers

2 author rows

ICLR Conference 2025 Conference Paper

Exploring the Camera Bias of Person Re-identification

Myungseo Song
Jin-Woo Park
Jong-Seok Lee

We empirically investigate the camera bias of person re-identification (ReID) models. Previously, camera-aware methods have been proposed to address this issue, but they are largely confined to training domains of the models. We measure the camera bias of ReID models on unseen domains and reveal that camera bias becomes more pronounced under data distribution shifts. As a debiasing method for unseen domain data, we revisit feature normalization on embedding vectors. While the normalization has been used as a straightforward solution, its underlying causes and broader applicability remain unexplored. We analyze why this simple method is effective at reducing bias and show that it can be applied to detailed bias factors such as low-level image properties and body angle. Furthermore, we validate its generalizability across various models and benchmarks, highlighting its potential as a simple yet effective test-time postprocessing method for ReID. In addition, we explore the inherent risk of camera bias in unsupervised learning of ReID models. The unsupervised models remain highly biased towards camera labels even for seen domain data, indicating substantial room for improvement. Based on observations of the negative impact of camera-biased pseudo labels on training, we suggest simple training strategies to mitigate the bias. By applying these strategies to existing unsupervised learning algorithms, we show that significant performance improvements can be achieved with minor modifications.

Details

ECAI Conference 2020 Conference Paper

Dynamic Thresholding for Learning Sparse Neural Networks

Jin-Woo Park
Jong-Seok Lee

This paper proposes a method called Dynamic Thresholding, which can dynamically adjust the size of deep neural networks by removing redundant weights during training. The key idea is to learn the pruning threshold values applied for weight removal, instead of fixing them manually. We approximate a discontinuous pruning function with a differentiable form involving the thresholds, which can be optimized via the gradient descent learning procedure. While previous sparsity-promoting methods perform pruning with manually determined thresholds, our method can directly obtain a sparse network at each training iteration and thus does not need a trial-and-error process to choose proper threshold values. We examine the performance of the proposed method on the image classification tasks including MNIST, CIFAR10, and ImageNet. It is demonstrated that our method achieves competitive results with existing methods and, at the same time, requires smaller numbers of training iterations in comparison to other approaches based on train-prune-retrain cycles.

Details

JBHI Journal 2019 Journal Article

The Effect of Mirroring Display of Virtual Reality Tour of the Operating Theatre on Preoperative Anxiety: A Randomized Controlled Trial

Jin-woo Park
Francis Sahngun Nahm
Jin-Hee Kim
Young-Tae Jeon
Jung-Hee Ryu
Sung-Hee Han

A virtual reality (VR) tour of the operating theatre could reduce preoperative anxiety by providing a realistic experience for children. This randomized clinical trial was designed to determine whether parental co-experience of preoperative VR tour through a mirroring display could further reduce preoperative anxiety. Eighty children scheduled for elective surgery under general anesthesia were randomly allocated into either the control or mirroring group. Children in the control group watched a 4-min immersive VR video showing the operating theatre and explaining the preoperative process, via a head mounted display. In the mirroring group, parents of children watched the same video through mirroring display concurrently while their child experienced the immersive VR tour. Preoperative anxiety and satisfaction score were measured. Eighty children completed the final analysis (control group = 40 and mirroring group = 40). Preoperative anxiety of children ( p = 0. 025) and parents ( p = 0. 009) were lower in the mirroring group compared with the control group. Parents’ satisfaction in the mirroring group was significantly higher than those in the control group ( p = 0. 008). Parental co-experience of the VR tour with children through mirroring the display was effective in reducing preoperative anxiety in both children and parents.

Details DOI

AAAI Conference 2016 Conference Paper

Fine-Grained Semantic Conceptualization of FrameNet

Jin-woo Park
Seung-won Hwang
Haixun Wang

Understanding verbs is essential for many natural language tasks. To this end, large-scale lexical resources such as FrameNet have been manually constructed to annotate the semantics of verbs (frames) and their arguments (frame elements or FEs) in example sentences. Our goal is to “semantically conceptualize” example sentences by connecting FEs to knowledge base (KB) concepts. For example, connecting Employer FE to company concept in the KB enables the understanding that any (unseen) company can also be FE examples. However, a naive adoption of existing KB conceptualization technique, focusing on scenarios of conceptualizing a few terms, cannot 1) scale to many FE instances (average of 29. 7 instances for all FEs) and 2) leverage interdependence between instances and concepts. We thus propose a scalable k-truss clustering and a Markov Random Field (MRF) model leveraging interdependence between conceptinstance, concept-concept, and instance-instance pairs. Our extensive analysis with real-life data validates that our approach improves not only the quality of the identiﬁed concepts for FrameNet, but also that of applications such as selectional preference.

PDF Details

AAAI Conference 2016 Conference Paper

Understanding Emerging Spatial Entities

Jinyoung Yeo
Jin-woo Park
Seung-won Hwang

In Foursquare or Google+ Local, emerging spatial entities, such as new business or venue, are reported to grow by 1% every day. As information on such spatial entities is initially limited (e. g. , only name), we need to quickly harvest related information from social media such as Flickr photos. Especially, achieving high-recall in photo population is essential for emerging spatial entities, which suffer from data sparseness (e. g. , 71% restaurants of TripAdvisor in Seattle do not have any photo, as of Sep 03, 2015). Our goal is thus to address this limitation by identifying effective linking techniques for emerging spatial entities and photos. Compared with state-of-the-art baselines, our proposed approach improves recall and F1 score by up to 24% and 18%, respectively. To show the effectiveness and robustness of our approach, we have conducted extensive experiments in three different cities, Seattle, Washington D. C. , and Taipei, of varying characteristics such as geographical density and language.

PDF Details

AAAI Conference 2012 Conference Paper

Predictive Mining of Comparable Entities from the Web

Myungha Jang
Jin-woo Park
Seung-won Hwang

Comparing entities is an important part of decision making. Several approaches have been reported for mining comparable entities from Web sources to improve user experience in comparing entities online. However, these efforts extract only entities explicitly compared in the corpora, and may exclude entities that occur less-frequently but potentially comparable. To build a more complete comparison machine that can infer such missing relations, here we develop a solution to predict transitivity of known comparable relations. Named CLIQUE- GROW, our approach predicts missing links given a comparable entity graph obtained from versus query logs. Our approach achieved the highest F1-score among five link prediction approaches and a commercial comparison engine provided by Yahoo! .

PDF Details

AAAI Conference 2011 Conference Paper

CosTriage: A Cost-Aware Triage Algorithm for Bug Reporting Systems

Jin-woo Park
Mu-Woong Lee
Jinhan Kim
Seung-won Hwang
Sunghun Kim

‘Who can ﬁx this bug? ’ is an important question in bug triage to “accurately” assign developers to bug reports. To address this question, recent research treats it as a optimizing recommendation accuracy problem and proposes a solution that is essentially an instance of content-based recommendation (CBR). However, CBR is well-known to cause over-specialization, recommending only the types of bugs that each developer has solved before. This problem is critical in practice, as some experienced developers could be overloaded, and this would slow the bug ﬁxing process. In this paper, we take two directions to address this problem: First, we reformulate the problem as an optimization problem of both accuracy and cost. Second, we adopt a content-boosted collaborative ﬁltering (CBCF), combining an existing CBR with a collaborative ﬁltering recommender (CF), which enhances the recommendation quality of either approach alone. However, unlike general recommendation scenarios, bug ﬁx history is extremely sparse. Due to the nature of bug ﬁxes, one bug is ﬁxed by only one developer, which makes it challenging to pursue the above two directions. To address this challenge, we develop a topic-model to reduce the sparseness and enhance the quality of CBCF. Our experimental evaluation shows that our solution reduces the cost efﬁciently by 30% without seriously compromising accuracy.

PDF Details

ICRA Conference 2001 Conference Paper

An On-line Production Scheduler using Neural Network and Simulator based on Manufacturing System States

Ki-Tae Kim
Seong-Yong Jang
Byung-Hoon Yoo
Jin-Woo Park

Customers are demanding shorter lead times and higher product variety without making concessions on product price and quality. To remain competitive, a manufacturing system needs to react adequately to perturbations on its environment and uncertainties in manufacturing processes. The paper touches upon three research topics for the development of a scheduler based on manufacturing system states: development of a simulator for the simulation of a manufacturing system, the clustering method for manufacturing system states, and the search method for the most compatible dispatching rule to a manufacturing system state. Finally, the results of simulation experiments are given to compare the proposed method with other scheduling methods. The result shows that the superiority of the proposed scheduler. In the process of developing the scheduler, a general methodology for the development of a simulator and the clustering method for system states were developed. The proposed methodology for the development of simulators seems to be useful for developing simulators for various domains. The clustering method of system states and the knowledge acquisition method for scheduling rules are shown to be efficient for the development of an autonomous real-time scheduling system.

Details