ReferTrack: Referring Then Tracking for Embodied Visual Tracking
Overview
ReferTrack结合指代与跟踪，用单目相机和TVBI时序记忆，在仿真中取得SOTA，可部署于四足和人形机器人。在DT、AT任务中表现优于部分多相机基线。","latest":"ReferTrack通过单目相机和TVBI时序记忆，在仿真中取得SOTA，可部署于四足和人形机器人。"}
Generated from attributed reports · Updated 35 minutes ago
Event evidence and corrections
0 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
Environment: simulation
“EVT‑Bench基准上单目设置拿下SOTA，在目标极易混淆的任务上，效果甚至优于部分多相机基线；同时完成四足、人形机器人部署，证明强大的仿真到现实迁移能力。”
Exact source · revision 4Source owner not reported
Artifact availability · code: available
“作者 ：Hanjing Ye , Tianle Zeng , Jiazhao Zhang , Shaoan Wang , Zibo Zhang , Weisi Situ , Yuchen Zhou , Yonggen Ling , Hong Zhang 单位 ： 南方科技大学RCV实验室， 腾讯Robotics X， 北京大学， 福田实验室 论文标题 ：ReferTrack: Referring Then Tracking for Embodied Visual Tracking 论文链接 ：https://arxiv.org/abs/2607.20061 代码链接 ：https://github.com/MedlarTea/referTrack 研究背景 具身视觉跟踪EVT ，简单说就是：机器人只靠自身机载摄像头，听懂人类自然语言指令，持续跟随指令描述的特定行人。”
Exact source · revision 4Source owner not reported
Artifact availability · paper: available
“作者 ：Hanjing Ye , Tianle Zeng , Jiazhao Zhang , Shaoan Wang , Zibo Zhang , Weisi Situ , Yuchen Zhou , Yonggen Ling , Hong Zhang 单位 ： 南方科技大学RCV实验室， 腾讯Robotics X， 北京大学， 福田实验室 论文标题 ：ReferTrack: Referring Then Tracking for Embodied Visual Tracking 论文链接 ：https://arxiv.org/abs/2607.20061 代码链接 ：https://github.com/MedlarTea/referTrack 研究背景 具身视觉跟踪EVT ，简单说就是：机器人只靠自身机载摄像头，听懂人类自然语言指令，持续跟随指令描述的特定行人。”
Exact source · revision 4Source owner not reported
Evidence dependency changes (2)
- 2026-10-13T08:21:28.710Z · evidence updated · source revision 4. Evidence extraction was updated; current source attributions are shown above.
- 2026-10-10T11:49:16.124Z · evidence updated · source revision 3. Evidence extraction was updated; current source attributions are shown above.
Report timeline
Follow attributed reports and material updates.
- Chinese robotics — Robot learning researchSignalReferTrack: Referring Then Tracking for Embodied Visual Tracking
This paper proposes ReferTrack, a new paradigm for embodied visual tracking that combines referring and tracking. The model uses a single forward-facing camera, selects targets via index detection boxes, and employs TVBI temporal visual boundary information to achieve state-of-the-art results on EVT-Bench. It is deployable on quadruped and humanoid robots, showing strong simulation-to-reality transfer capabilities.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).