Page content
Oral Sessions
Day 1: 8 January
11:00 - 12:00
Best Paper Session
Chair: Toshihiko Yamasaki (The University of Tokyo)
| Paper ID | Paper Title | Authors |
|---|---|---|
| 196 | RoLD: Robot Latent Diffusion for Multi-task Policy Modeling | Tan, Wenhui; Liu, Bei; Zhang, Junbo; Song, Ruihua; Fu, Jianlong |
| 379 | TDM: Temporally-Consistent Diffusion Model for All-in-One Real-World Video Restoration | Li, Yizhou; Liu, Zihua; Monno, Yusuke; Okutomi, Masatoshi |
| 451 | ESC-MISR: Enhancing Spatial Correlations for Multi-Image Super-Resolution in Remote Sensing | Zhang, Zhihui; Pang, Jinhui; Li, Jianan; Hao, Xiaoshuai |
| 462 | Flat Local Minima for Continual learning on Semantic Segmentation | Huang, Zhongzhan; Liang, Mingfu; Liang, Senwei; Zhong, Shanshan |
15:30 – 16:30
Oral Session 1: Content Generation
Chair: Luwei Zhang (The University of Tokyo)
| Paper ID | Paper Title | Authors |
|---|---|---|
| 268 | AD2AT: Audio Description to Alternative Text, a Dataset of Alternative Text from Movies | Lincker, Elise; Guinaudeau, Camille; Satoh, Shin’ichi |
| 310 | KuzushijiDiffuser: Japanese Kuzushiji Font Generation with FontDiffuser | YUAN, HONGHUI; YANAI, KEIJI |
| 167 | Saliency Guided Optimization Of Diffusion Latents | Wang, Xiwen; Zhou, Jizhe; Li, Mao; Zhu, Xuekang; Li, Cheng |
| 308 | Skin-Adapter: Fine-Grained Skin-Color Preservation for Text-to-Image Generation | Chen, Zhuowei; Huang, Mengqi; Chen, Nan; Mao, Zhendong |
16:45 – 17:45
Oral Session 2: Audio Analysis
Chair: Ling Xiao (The University of Tokyo)
| Paper ID | Paper Title | Authors |
|---|---|---|
| 273 | Operatic Singing Voice Synthesis From Inexperienced Voice Considering Tempo and Vowel Change | Sugahara, Aoto; Kishimoto, Soma; Adachi, Yuji; Tai, Kiyoto; Takashima, Ryoichi; Takiguchi, Tetsuya |
| 129 | Small Tunes Transformer: Exploring Macro & Micro-Level Hierarchies for Skeleton-Conditioned Melody Generation | Lv, Yishan; Luo, Jing; Ju, Boyuan; Yang, Xinyu |
| 430 | WavFusion: Towards wav2vec 2.0 Multimodal Speech Emotion Recognition | Li, Feng; Luo, Jiusong; Xia, Wanjun |
| 374 | SPLGAN-TTS:Learning Semantic and Prosody to Enhance the Text-to-Speech Quality of Lightweight GAN Models | Chang, Ding-Chi; Li, Shiou-Chi; Huang, Jen-Wei |
Day 2: 9 January
9:30 – 10:30
Oral Session 3: Object Detection, Recognition, and Tracking
Chair: Wei-Ta Chu (National Cheng Kung University)
| Paper ID | Paper Title | Authors |
|---|---|---|
| 236 | MineTinyNet-YOLO: An Efficient Small Object Detection Method for Complex Underground Coal Mine Scenarios | Yaling, Hao; Wei, Wu |
| 436 | Mix-YOLONet: Deep Image Dehazing for Improving Object Detection | Lim, Xin; Wong, Lai-Kuan; Loh, Yuen Peng; Gu, Ke; Lin, Weisi |
| 411 | Counting Unique Objects in Geo-Tagged Street Images: A Case Study Of Homeless Encampments in Los Angeles | Ghasemi, Narges; Kim, Seon Ho; Alfarrarjeh, Abdullah; Shahabi, Cyrus |
| 181 | HCV: Lightweight Hybrid CNN-Vision Transformer for Visual Object Tracking | Chen, Liang-Chia; Chu, Wei-Ta |
10:45 – 11:30
Oral Session 4: Trusted and Explainable AI
Chair: Kazuaki Nakamura (Tokyo University of Science)
| Paper ID | Paper Title | Authors |
|---|---|---|
| 174 | Detoxification of Unlabeled Dataset: Reducing Implicit Class Imbalance Using Pseudo-Jacobian of GAN’s Generator | Suyama, Kosei; Nakamura, Kazuaki |
| 244 | Making strides Security in Multimodal Fake News Detection Models: A Comprehensive Analysis of Adversarial Attacks | Si, Jiahua; Wang, Youze; Hu, Wenbo; Liu, Qiang; Hong, Richang |
| 415 | AMPLE: Emotion-Aware Multimodal Fusion Prompt Learning for Fake News Detection | Xu, Xiaoman; Li, Xiangrun; Wang, Taihang; Jiang, Ye |
15:00 – 15:45
Oral Session 5: Signal Processing
Chair: Masahiro Toyoura (University of Yamanashi)
| Paper ID | Paper Title | Authors |
|---|---|---|
| 297 | Uncertainty-guided Joint Semi-supervised Segmentation and Registration of Cardiac Images | Chen, Junjian; Yang, Xuan |
| 337 | Wavelet Integrated Convolutional Neural Network for ECG Signal Denoising | Terada, Takamasa; Toyoura, Masahiro |
| 392 | MPPQNet: A Moment-Preserving Product Quantization Neural Network for Progressive 3D Point Cloud Transmission | Cheng, Shyi-Chyi; CHEN, YEN-LIN; Li, Shih-Yu |
Day 3: 10 January
10:30 – 11:30
Oral Session 6: Recognition and Reasoning
Chair: Satoshi Yamasaki (NEC)
| Paper ID | Paper Title | Authors |
|---|---|---|
| 218 | A Multi-Expert Collaborative Framework for Multimodal Named Entity Recognition | Xu, Bo; Jiang, Haiqi; Wei, Shouang; Du, Ming; Song, Hui; Wang, Hongya |
| 266 | SSDL:Sensor-to-Skeleton Diffusion Model with Lipschitz Regularization for Human Activity Recognition | Sharma, Nikhil; Sun, Changchang; Zhao, Zhenghao; Ngu, Anne Hee Hiong; Latapie, Hugo; Yan, Yan |
| 395 | Open-vocabulary Scene Graph Generation via Synonym-based Predicate Descriptor | Goto, Yuta; Yamazaki, Satoshi; Shibata, Takashi; Liu, Jianquan |
| 274 | Grounding Deliberate Reasoning in Multimodal Large Language Models | Chen, Jiaxing; Liu, Yuxuan; Li, Dehu; An, Xiang; Deng, Weimo; Feng, Ziyong; Zhao, Yongle; Xie, Yin |
15:00 – 16:00
Special Session: MLLMA
Chair: Rajiv Ratn Shah (IIIT-Delhi)
| Paper ID | Paper Title | Authors |
|---|---|---|
| 193 | Image2Text2Image: A Novel Framework for Label-Free Evaluation of Image-to-Text Generation with Text-to-Image Diffusion Models | Huang, Jia-Hong; Zhu, Hongyi; Shen, Yixian; Rudinac, Stevan; Kanoulas, Evangelos |
| 288 | Enhanced Anomaly Detection in 3D Motion through Language-Inspired Occlusion-Aware Modeling | Li, Su; Wang, Liang; Wang, Jianye; Zhang, Ziheng; Zhang, Junjun; Zhang, Lei |
| 364 | Evaluating VQA Models' Consistency in the Scientific Domain | C. Quan, Khanh-An; Guinaudeau, Camille; Satoh, Shin’ichi |
| Panel Discussion |
16:15 – 17:00
Oral Session 7: Search and Retrieval
Chair: Nicolas Michel (The University of Tokyo)
| Paper ID | Paper Title | Authors |
|---|---|---|
| 346 | RobSparse: Automatic Search for GPU-Friendly Robust and Sparse Vision Transformers | Su, Yulan; Zhang, Sisi; Wang, Yan; Wang, Xingbin; Zhao, Lutan; Dan, Meng; Hou, Rui |
| 232 | Image-Generation AI Model Retrieval by Contrastive Learning-based Style Distance Calculation | Vu, Thi Ngoc Anh; Shoji, Yoshiyuki; Oe, Yuma; PHAM, Huu Long; Ohshima, Hiroaki |
| 414 | Dynamic Exploration Graph: A Novel Approach for Efficient Nearest Neighbor Search in Evolving Multimedia Datasets | Hezel, Nico; Barthel, Kai Uwe; Schilling, Bruno; Schall, Konstantin; Jung, Klaus |
