no code implementations • 17 Apr 2025 • Jongseo Lee, Wooil Lee, Gyeong-Moon Park, Seong Tae Kim, Jinwoo Choi
Unlike methods based on pixel-level features or static textual descriptions, PCBEAR leverages human skeleton poses, which focus solely on body movements, providing robust and interpretable explanations of motion dynamics.
no code implementations • 27 Mar 2025 • Samra Irshad, Seungkyu Lee, Nassir Navab, Hong Joo Lee, Seong Tae Kim
The translation network encodes the characteristics of damaged signs into a latent `damage style code'.
1 code implementation • 19 Dec 2024 • Minkuk Kim, Hyeon Bae Kim, Jinyoung Moon, Jinwoo Choi, Seong Tae Kim
With the growing demand for solutions to real-world video challenges, interest in dense video captioning (DVC) has been on the rise.
Ranked #1 on
Dense Video Captioning
on YouCook2
(using extra training data)
no code implementations • 21 Oct 2024 • Abdullah, Ameer Hamza, Seong Tae Kim
Medical report generation is the task of automatically writing radiology reports for chest X-ray images.
1 code implementation • 7 Oct 2024 • Ameer Hamza, Abdullah, Yong Hyun Ahn, Sungyoung Lee, Seong Tae Kim
To address these issues, we propose a novel Vision-Language framework augmented with a Knowledge Graph (KG)-based datastore, which enhances the model's understanding by incorporating additional domain-specific medical knowledge essential for generating accurate and informative NLEs.
no code implementations • 26 Sep 2024 • Jongseo Lee, Geo Ahn, Seong Tae Kim, Jinwoo Choi
Unlike existing attribution-based XAI approaches, the PCEvE provides a straightforward explanation of a model decision, i. e., a part contribution histogram.
no code implementations • 30 Aug 2024 • Su Hyeon Lim, Minkuk Kim, Hyeon Bae Kim, Seong Tae Kim
In this work, we introduce a new VQA-NLE model, ReRe (Retrieval-augmented natural language Reasoning), using leverage retrieval information from the memory to aid in generating accurate answers and persuasive explanations without relying on complex networks and extra datasets.
1 code implementation • 23 Jul 2024 • Youngmin Oh, Hyung-Il Kim, Seong Tae Kim, Jung Uk Kim
It contains two components: (1) the weather codebook to memorize the knowledge of the clear weather and generate a weather-reference feature for any input, and (2) the weather-adaptive diffusion model to enhance the feature representation of the input feature by incorporating a weather-reference feature.
1 code implementation • 16 Jul 2024 • Hao Ding, Yuqian Zhang, Tuxun Lu, Ruixing Liang, Hongchao Shu, Lalithkumar Seenivasan, Yonghao Long, Qi Dou, Cong Gao, Yicheng Leng, Seok Bong Yoo, Eung-Joo Lee, Negin Ghamsarian, Klaus Schoeffmann, Raphael Sznitman, Zijian Wu, Yuxin Chen, Septimiu E. Salcudean, Samra Irshad, Shadi Albarqouni, Seong Tae Kim, Yueyi Sun, An Wang, Long Bai, Hongliang Ren, Ihsan Ullah, Ho-Gun Ha, Attaullah Khan, Hyunki Lee, Satoshi Kondo, Satoshi Kasai, Kousuke Hirasawa, Sita Tailor, Ricardo Sanchez-Matilla, Imanol Luengo, Tianhao Fu, Jun Ma, Bo wang, Marcos Fernández-Rodríguez, Estevao Lima, João L. Vilaça, Mathias Unberath
Surgical data science has seen rapid advancement due to the excellent performance of end-to-end deep neural networks (DNNs) for surgical video analysis.
1 code implementation • 16 Jul 2024 • Hyeon Bae Kim, Yong Hyun Ahn, Seong Tae Kim
Recent advancements in deep neural networks have shown promise in aiding disease diagnosis and medical decision-making.
1 code implementation • CVPR 2024 • Minkuk Kim, Hyeon Bae Kim, Jinyoung Moon, Jinwoo Choi, Seong Tae Kim
There has been significant attention to the research on dense video captioning, which aims to automatically localize and caption all events within untrimmed video.
Ranked #4 on
Dense Video Captioning
on YouCook2
1 code implementation • 29 Feb 2024 • Yong Hyun Ahn, Hyeon Bae Kim, Seong Tae Kim
Recent advancements in neural networks have showcased their remarkable capabilities across various domains.
no code implementations • 22 Jan 2024 • Chu Myaet Thwal, Minh N. H. Nguyen, Ye Lin Tun, Seong Tae Kim, My T. Thai, Choong Seon Hong
Federated learning (FL) has emerged as a promising approach to collaboratively train machine learning models across multiple edge devices while preserving privacy.
Ranked #7 on
Image Classification
on EMNIST-Balanced
1 code implementation • CVPR 2024 • Yong Hyun Ahn, Hyeon Bae Kim, Seong Tae Kim
Recent advancements in neural networks have showcased their remarkable capabilities across various domains.
no code implementations • 4 Apr 2023 • Chaoning Zhang, Chenshuang Zhang, Chenghao Li, Yu Qiao, Sheng Zheng, Sumit Kumar Dam, Mengchun Zhang, Jung Uk Kim, Seong Tae Kim, Jinwoo Choi, Gyeong-Moon Park, Sung-Ho Bae, Lik-Hang Lee, Pan Hui, In So Kweon, Choong Seon Hong
Overall, this work is the first to survey ChatGPT with a comprehensive review of its underlying technology, applications, and challenges.
no code implementations • 26 Mar 2023 • Soyoun Won, Sung-Ho Bae, Seong Tae Kim
Data augmentation strategies are actively used when training deep neural networks (DNNs).
1 code implementation • CVPR 2023 • Yong Hyun Ahn, Gyeong-Moon Park, Seong Tae Kim
In this study, from the perspective of neurons in the deep layer of the model representing high-level features, we introduce a new aspect for analyzing the difference in model outputs between in-distribution data and OOD data.
Ranked #2 on
Out-of-Distribution Detection
on ImageNet-1k vs SUN
1 code implementation • 9 Oct 2022 • Samra Irshad, Douglas P. S. Gomes, Seong Tae Kim
To address the problem of abdominal multi-organ segmentation, we train the 3D encoder-decoder network to simultaneously segment the abdominal organs and their corresponding boundaries in CT scans via multi-task learning.
no code implementations • 25 Jul 2022 • Felix Buchert, Nassir Navab, Seong Tae Kim
By considering the consistency information with the diversity in the consistency-based embedding scheme, the proposed method could select more informative samples for labeling in the semi-supervised learning setting.
no code implementations • 4 Apr 2022 • Ashkan Khakzar, Yawei Li, Yang Zhang, Mirac Sanisoglu, Seong Tae Kim, Mina Rezaei, Bernd Bischl, Nassir Navab
One challenging property lurking in medical datasets is the imbalanced data distribution, where the frequency of the samples between the different classes is not balanced.
no code implementations • 21 Mar 2022 • Tobias Czempiel, Coco Rogers, Matthias Keicher, Magdalini Paschali, Rickmer Braren, Egon Burian, Marcus Makowski, Nassir Navab, Thomas Wendler, Seong Tae Kim
For this purpose, longitudinal self-supervision schemes are explored on clinical longitudinal COVID-19 CT scans.
1 code implementation • NeurIPS 2021 • Yang Zhang, Ashkan Khakzar, Yawei Li, Azade Farshad, Seong Tae Kim, Nassir Navab
We propose a method to identify features with predictive information in the input domain.
no code implementations • 3 Oct 2021 • Michelle Xiao-Lin Foo, Seong Tae Kim, Magdalini Paschali, Leili Goli, Egon Burian, Marcus Makowski, Rickmer Braren, Nassir Navab, Thomas Wendler
Existing automatic and interactive segmentation models for medical images only use data from a single time point (static).
1 code implementation • 4 Apr 2021 • Ashkan Khakzar, Sabrina Musatian, Jonas Buchberger, Icxel Valeriano Quiroz, Nikolaus Pinger, Soroosh Baselizadeh, Seong Tae Kim, Nassir Navab
We present our findings using publicly available chest pathologies (CheXpert, NIH ChestX-ray8) and COVID-19 datasets (BrixIA, and COVID-19 chest X-ray segmentation dataset).
1 code implementation • 1 Apr 2021 • Ashkan Khakzar, Yang Zhang, Wejdene Mansour, Yuezhi Cai, Yawei Li, Yucheng Zhang, Seong Tae Kim, Nassir Navab
Neural networks have demonstrated remarkable performance in classification and regression tasks on chest X-rays.
2 code implementations • CVPR 2021 • Ashkan Khakzar, Soroosh Baselizadeh, Saurabh Khanduja, Christian Rupprecht, Seong Tae Kim, Nassir Navab
Is critical input information encoded in specific sparse pathways within the neural network?
no code implementations • 19 Mar 2021 • Aadhithya Sankar, Matthias Keicher, Rami Eisawy, Abhijeet Parida, Franz Pfister, Seong Tae Kim, Nassir Navab
Disentangled representations can be useful in many downstream tasks, help to make deep learning models more interpretable, and allow for control over features of synthetically generated images that can be useful in training other models that require a large number of labelled or unlabelled data.
1 code implementation • 12 Mar 2021 • Seong Tae Kim, Leili Goli, Magdalini Paschali, Ashkan Khakzar, Matthias Keicher, Tobias Czempiel, Egon Burian, Rickmer Braren, Nassir Navab, Thomas Wendler
Chest computed tomography (CT) has played an essential diagnostic role in assessing patients with COVID-19 by showing disease-specific image features such as ground-glass opacity and consolidation.
no code implementations • 5 Mar 2021 • Tobias Czempiel, Magdalini Paschali, Daniel Ostler, Seong Tae Kim, Benjamin Busam, Nassir Navab
In this paper we introduce OperA, a transformer-based model that accurately predicts surgical phases from long video sequences.
no code implementations • 1 Jan 2021 • Ashkan Khakzar, Soroosh Baselizadeh, Saurabh Khanduja, Christian Rupprecht, Seong Tae Kim, Nassir Navab
Is critical input information encoded in specific sparse paths within the network?
no code implementations • 10 Nov 2020 • Abinav Ravi Venkatakrishnan, Seong Tae Kim, Rami Eisawy, Franz Pfister, Nassir Navab
To address these issues, recently, unsupervised deep anomaly detection methods that train the model on large-sized normal scans and detect abnormal scans by calculating reconstruction error have been reported.
no code implementations • 21 May 2020 • Hakmin Lee, Hong Joo Lee, Seong Tae Kim, Yong Man Ro
After the ensemble models are trained, it can hide the gradient efficiently and avoid the gradient-based attack by the random layer sampling method.
no code implementations • 21 May 2020 • Hong Joo Lee, Seong Tae Kim, Hakmin Lee, Nassir Navab, Yong Man Ro
Experimental results show that the proposed method could provide useful uncertainty information by Bayesian approximation with the efficient ensemble model generation and improve the predictive performance.
1 code implementation • 7 Apr 2020 • Stefan Denner, Ashkan Khakzar, Moiz Sajid, Mahdi Saleh, Ziga Spiclin, Seong Tae Kim, Nassir Navab
Our results show that spatio-temporal information in longitudinal data is a beneficial cue for improving segmentation.
no code implementations • 5 Apr 2020 • Seong Tae Kim, Farrukh Mushtaq, Nassir Navab
Active learning is one of the solutions to this problem where an active learner is designed to indicate which samples need to be annotated to effectively train a target model.
2 code implementations • 24 Mar 2020 • Tobias Czempiel, Magdalini Paschali, Matthias Keicher, Walter Simson, Hubertus Feussner, Seong Tae Kim, Nassir Navab
Automatic surgical phase recognition is a challenging and crucial task with the potential to improve patient safety and become an integral part of intra-operative decision-support systems.
Ranked #5 on
Surgical phase recognition
on Cholec80
1 code implementation • 26 Feb 2020 • Maria Tirindelli, Maria Victorova, Javier Esteban, Seong Tae Kim, David Navarro-Alarcon, Yong Ping Zheng, Nassir Navab
Processed force and ultrasound data are fused using a 1D Convolutional Network to compute the location of the vertebral levels.
no code implementations • 25 Nov 2019 • Ashkan Khakzar, Soroosh Baselizadeh, Saurabh Khanduja, Christian Rupprecht, Seong Tae Kim, Nassir Navab
Attributing the output of a neural network to the contribution of given input elements is a way of shedding light on the black-box nature of neural networks.
no code implementations • 10 Jun 2019 • Hyebin Lee, Seong Tae Kim, Yong Man Ro
The ambiguity of the decision-making process has been pointed out as the main obstacle to applying the deep learning-based method in a practical way in spite of its outstanding performance.
no code implementations • 17 Sep 2018 • Jae-Hyeok Lee, Seong Tae Kim, Hakmin Lee, Yong Man Ro
In order to learn deep network model to be well-behaved in bio-image computing fields, a lot of labeled data is required.
no code implementations • 23 May 2018 • Seong Tae Kim, Hakmin Lee, Hak Gu Kim, Yong Man Ro
In this paper, we investigate interpretability in CADx with the proposed interpretable CADx (ICADx) framework.
no code implementations • ECCV 2018 • Seong Tae Kim, Yong Man Ro
In this paper, a novel deep learning approach, named facial dynamics interpreter network, has been proposed to interpret the important relations between local dynamics for estimating facial traits from expression sequence.
no code implementations • 28 Nov 2017 • Geonmo Gu, Seong Tae Kim, Kihyun Kim, Wissam J. Baddar, Yong Man Ro
through a generative model is helpful in addressing the lack of training data.
no code implementations • 31 Jul 2017 • Tae Kwan Lee, Wissam J. Baddar, Seong Tae Kim, Yong Man Ro
Our classification results on Multi-PIE dataset for facial expression recognition and CIFAR-10 dataset for object classification reveal that the compact CNN with the proposed logarithmic filter grouping scheme outperforms the same network with the uniform filter grouping in terms of accuracy and parameter efficiency.
no code implementations • 31 May 2017 • Seong Tae Kim, Yong Man Ro
In order to improve the effectiveness of the learning with instructional video, observation and evaluation of the activity are required.