default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCID4th ICPRAI 2024: Jeju Island, South Korea - Part I
- Christian Wallraven
, Cheng-Lin Liu, Arun Ross:
Pattern Recognition and Artificial Intelligence - 4th International Conference, ICPRAI 2024, Jeju Island, South Korea, July 03-06, 2024, Proceedings, Part I. Lecture Notes in Computer Science 14892, Springer 2025, ISBN 978-981-97-8701-2
Oral Session: Deep Learning
- David Hagerman, Roman Naeem, Jakob Lindqvist, Carl Lindström, Fredrik Kahl, Lennart Svensson:
SwInception - Local Attention Meets Convolutions. 3-17 - Giacomo Verardo, Magnus Boman, Samuel Bruchfeld, Marco Chiesa, Sabine Koch, Gerald Q. Maguire Jr., Dejan Kostic:
FMM-Head: Enhancing Autoencoder-Based ECG Anomaly Detection with Prior Knowledge. 18-32 - Jiajia Li, Letian Peng, Ping Wang, Hai Zhao:
Hierarchical Attention Decoder for Solving Math Word Problems. 33-46 - Keiichiro Yamamura, Issa Oe, Hiroki Ishikura, Katsuki Fujisawa:
Enhancing Output Diversity Improves Conjugate Gradient-Based Adversarial Attacks. 47-61 - Gertjan J. Burghouts, Fieke Hillerström, Erwin Walraven, Michael van Bekkum, Frank Ruis, Joris Sijs, Jelle van Mil, Judith Dijk, Wouter Meijer:
Open-World Visual Reasoning by a Neuro-Symbolic Program of Zero-Shot Symbols. 62-75 - Damien A. Dablain, Nitesh V. Chawla:
The Hidden Influence of Latent Feature Magnitude When Learning with Imbalanced Data. 76-91 - Vitaliy Kim, Gunho Jung, Seong-Whan Lee:
AM-SORT: Adaptable Motion Predictor with Historical Trajectory Embedding for Multi-Object Tracking. 92-107 - Donghoon Lee, Jun Yeop Shim, Sunjae Yoon, Chang D. Yoo:
Character Identifying Video Language Alignment Network for Weakly-Supervised Video-Subtitle Moment Retrieval. 108-123
Oral Session : Computer Vision
- Olivier Lézoray, Sébastien Bougleux:
Spiral Patch Exemplar-Based Inpainting of 3D Colored Meshes. 127-141 - Zeen Pan, Zongyang Tong, Yuhan Dong:
BEVFormer's Plugin: Integrating Historical Detection Data, BEV-Level Information, Time Information, and Depth Information. 142-156 - Josef Bengtson, David Nilsson, Che-Tsung Lin, Marcel Büsching, Fredrik Kahl:
Adjustable Visual Appearance for Generalizable Novel View Synthesis. 157-171 - Chenhui Xue, Shugong Xu, Shiyi Mu, Yilin Gao:
Flexible Video Matting With Temporally Coherent Trimaps Generation. 172-185 - Kiyoon Kim, Shreyank N. Gowda, Panagiotis Eustratiadis, Antreas Antoniou, Robert B. Fisher:
Adversarial Augmentation Training Makes Action Recognition Models More Robust to Realistic Video Distribution Shifts. 186-200 - DongYoon Seo, Hyung-Gun Chi, Sunghee Hong, Byoung Soo Koh, Karthik Ramani, Sangpil Kim:
Egocentric View Hand Action Recognition by Leveraging Hand Surface and Hand Grasp Type. 201-215
Oral Session: Knowledge Representation
- Debargha Ganguly, Debayan Gupta, Vipin Chaudhary:
Visual Concept Networks: A Graph-Based Approach to Detecting Anomalous Data in Deep Neural Networks. 219-232 - Andrea Papaluca, Daniel Krefl, Artem Lensky, Hanna Suominen:
Contrastive Language-Entity Pre-training for Richer Knowledge Graph Embedding. 233-246 - Jia-Yi Liu, Zhi-Dong Deng:
Fine-Tuning Pre-trained Model with Prototype Learning for OOD Detection. 247-261 - Wooyeol Park, Ahmad Wisnu Mulyadi, Eunsong Kang, Heung-Il Suk:
Prototype-Guided Contrastive Knowledge Graph Representation Learning for Diagnosis Prediction. 262-275
Oral Session: Explainability and Uncertainty
- Matteo Rizzo, Matteo Marcuzzo, Alessandro Zangari, Michele Schiavinato, Andrea Albarelli, Andrea Gasparetto:
Stop Overkilling Simple Tasks with Black-Box Models, Use More Transparent Models Instead. 279-293 - Omid Davoodi, Majid Komeili:
Feature-Based Explainable Reinforcement Learning in Environments with Multiple Sources of Risk. 294-307 - Youngju Joung, Sehyun Lee, Jaesik Choi:
Probing Network Decisions: Capturing Uncertainties and Unveiling Vulnerabilities Without Label Information. 308-321 - Woo-Seok Jo, Yeong-Joon Ju, Seong-Whan Lee:
Enhancing Robustness of Over-Parameterized Models via Feature Reweighting Using Logit-Wise Mixup. 322-336
Oral Session: Applications
- Rina Buoy, Masakazu Iwamura, Sovila Srun, Koichi Kise:
Language-Aware Non-autoregressive Khmer Textline Recognition. 339-353 - Jihye Han, Sang Keun Lee:
ATA: Attentive Text Augmentation for Typo-Robust Language Models. 354-365 - Morgan Sandler, Hyesun Choung, Arun Ross, Prabu David:
A Linguistic Comparison Between Human and ChatGPT-Generated Conversations. 366-380 - Ji-Hye Oh, Eunjung Jo, Tae-Eui Kam:
A Comparative Study: Enhancing Conditional Generative Adversarial Networks for Functional Connectivity Synthesis in Major Depressive Disorder. 381-393 - Parisa Farmanifard, Arun Ross:
Iris-SAM: Iris Segmentation Using a Foundation Model. 394-409 - Geun-Deok Jang, Dong-Kyun Han, Seong-Whan Lee:
Test-Time Adaptation for EEG-Based Driver Drowsiness Classification. 410-424
Poster Session
- Shreyan Mitra, Leilani Gilpin:
A Novel Post-Hoc Explanation Comparison Metric and Applications. 427-446 - Yuye Feng, Yongfeng Niu:
Time Series Anomaly Detection via Reconstruction-Limited Probability Estimation. 447-461 - Wajahat Khalid, Bin Liu, Xulin Li, Muhammad Ali Qureshi:
Cloth-Independent Feature Learning from Multi-perspective for Cloth-Changing Person Re-Identification. 462-477 - Felip Guimerà Cuevas, Helmut Schmid:
Calibration Misalignment as a Post-Hoc Approach for Out-of-Distribution Detection in Deep Neural Networks. 478-492 - Anton Dereventsov, Andrew Starnes, Clayton G. Webster:
Examining Policy Entropy of Reinforcement Learning Agents for Personalization Tasks. 493-504 - Chunhu Zhang, Mayire Ibrayim, Askar Hamdulla, Qilin Deng:
Arbitrary-Shape Text Spotting Based on Global, Pixel and Sequence Semantics. 505-519
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
last updated on 2025-12-01 23:21 CET by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by:
