UniUD FBK UB UniBZ Submission
The "UniUD FBK UB UniBZ Submission" topic encompasses a range of research efforts focused on improving various aspects of machine learning, particularly in natural language processing and computer vision. Current research emphasizes advancements in model architectures like transformers and neural networks, often incorporating techniques such as data augmentation, ensemble methods, and multi-level training strategies to enhance performance in tasks such as machine translation, quality estimation, and video object tracking. These advancements contribute to the broader field by improving the accuracy and efficiency of AI systems across diverse applications, from automated language processing to real-time video analysis.
Papers
MetricX-24: The Google Submission to the WMT 2024 Metrics Shared Task
Juraj Juraska, Daniel Deutsch, Mara Finkelstein, Markus Freitag
Cogs in a Machine, Doing What They're Meant to Do -- The AMI Submission to the WMT24 General Translation Task
Atli Jasonarson, Hinrik Hafsteinsson, Bjarki Ármannsson, Steinþór Steingrímsson
ZJU ReLER Submission for EPIC-KITCHEN Challenge 2023: TREK-150 Single Object Tracking
Yuanyou Xu, Jiahao Li, Zongxin Yang, Yi Yang, Yueting Zhuang
ZJU ReLER Submission for EPIC-KITCHEN Challenge 2023: Semi-Supervised Video Object Segmentation
Jiahao Li, Yuanyou Xu, Zongxin Yang, Yi Yang, Yueting Zhuang