7 papers
Adaptive Debiasing Tsallis Entropy for Test-Time Adaptation
Xiangyu Wu, Dongming Jiang, Feng Yu +5
Mainstream Test-Time Adaptation (TTA) methods for adapting vision-language models, e.g., CLIP, typically rely on Shannon Entropy (SE) at test time to measure prediction uncertainty…
LPO: Towards Accurate GUI Agent Interaction via Location Preference Optimization
Jiaqi Tang, Yu Xia, Yi-Feng Wu +9
The advent of autonomous agents is transforming interactions with Graphical User Interfaces (GUIs) by employing natural language as a powerful intermediary. Despite the predominanc…
Multi-Label Test-Time Adaptation with Bound Entropy Minimization
Xiangyu Wu, Feng Yu, Qing-Guo Chen +2
Mainstream test-time adaptation (TTA) techniques endeavor to mitigate distribution shifts via entropy minimization for multi-class classification, inherently increasing the probabi…
Solution for Point Tracking Task of ECCV 2nd Perception Test Challenge 2024
Yuxuan Zhang, Pengsong Niu, Kun Yu +2
This report introduces an improved method for the Tracking Any Point~(TAP), focusing on monitoring physical surfaces in video footage. Despite their success with short-sequence sce…
The Solution for Temporal Sound Localisation Task of ICCV 1st Perception Test Challenge 2023
Yurui Huang, Yang Yang, Shou Chen +3
In this paper, we propose a solution for improving the quality of temporal sound localization. We employ a multimodal fusion approach to combine visual and audio features. High-qua…
TAI++: Text as Image for Multi-Label Image Classification by Co-Learning Transferable Prompt
Xiangyu Wu, Qing-Yuan Jiang, Yang Yang +3
The recent introduction of prompt tuning based on pre-trained vision-language models has dramatically improved the performance of multi-label image classification. However, some ex…
Solution for SMART-101 Challenge of ICCV Multi-modal Algorithmic Reasoning Task 2023
Xiangyu Wu, Yang Yang, Shengdong Xu +3
In this paper, we present our solution to a Multi-modal Algorithmic Reasoning Task: SMART-101 Challenge. Different from the traditional visual question-answering datasets, this cha…