COAL: Counterfactual and Observation-Enhanced Alignment Learning for Discriminative Referring Multi-Object Tracking
COAL: 基于反事实和观察增强的对齐学习用于判别性参照多目标跟踪
机构 * School of Automation, Southeast University, Nanjing, China(东南大学自动化学院,南京,中国) ; Key Laboratory of Measurement and Control of Complex Systems of Engineering, Ministry of Education, Nanjing, China(工程复杂系统测量与控制国家重点实验室,教育部,南京,中国) ; School of Physical & Mathematical Sciences, Nanyang Technological University, Singapore(南洋理工大学物理与数学科学学院,新加坡) ; Big Data Institute, Central South University, Changsha, China(中南大学大数据研究院,长沙,中国)
专题命中 VLM训练与架构 :VLM(abstract,abstract_cn);分类 cs.CV
AI总结 COAL通过知识正则化解决RMOT中高判别性需求与稀疏语义监督的矛盾,引入显式语义注入和反事实学习提升多目标跟踪的判别能力。