4 accepted papers
Multimodal models integrating natural language and visual information have substantially improved emotion recognition performance. However, their effectiveness significantly declines in real-world situations where certain modalities are missing or unavailable. This degradation primarily stems from i
Two-sided matching under uncertainty has recently drawn much attention due to its wide applications. Existing works in matching bandits mainly focus on the one-sided learning setting and design algorithms with the objective of converging to stable matching with low regret. In this paper, we consid…
Low-overlap registration is an important subtask in point cloud registration. In this letter, we focus on two extreme states of low-overlap registration tasks: zero overlap rate and even negative overlap rate point cloud registration. Instead of filtering out non-overlapping regions, overlapping reg
In this paper, we consider the matching of multi-agent multi-armed bandit problem, i.e., while agents prefer arms with higher expected reward, arms also have preferences on agents. In such case, agents pulling the same arm may encounter collisions, which leads to a reward of zero. For this problem,…