Don't Guess, Just Ask: Resolving Ambiguity in Referring Segmentation via Multi-turn Clarification 事件

Don't Guess, Just Ask: Resolving Ambiguity in Referring Segmentation via Multi-turn Clarification arXiv:2605.17531v2 Announce Type: replace Abstract: Referring segmentation aims to segment the target objects in images or videos based on the textual query. Despite remarkable progress over the past years, existing works always assume that the user-provided queries are already precise and clear. However, this assumption is impractical. In real-world scenarios, it is unrealistic to expect all users