作者位次 #5/9IROS 2026Poster· Adapting Detection and Segmentation to New Settings
3D Open-Vocabulary Detection Via Visual Alignment and Generative Captions
Thomas Edward Huang · Alex Zihao Zhu · Hao Xiang · Tianyi Cai · Jingwei Ji · Yuliang Zou · Jiafan Yu · Xin Huang · Mingxing Tan
多模态对齐与偏好Object Detection, Segmentation and CategorizationDeep Learning for Visual PerceptionSemantic Scene UnderstandingOpenReview