# ReferTrack: Referring Then Tracking for Embodied Visual Tracking

Page: https://stenobird.com/podcast/daily-paper-cast-7079649/refertrack-referring-then-tracking-for-embodied-visual-tracking
Text version: https://stenobird.com/podcast/daily-paper-cast-7079649/refertrack-referring-then-tracking-for-embodied-visual-tracking.md
Podcast: [Daily Paper Cast](https://stenobird.com/podcast/daily-paper-cast-7079649)
Published: 2026-07-25T03:41:54+00:00
Episode link: https://share.transistor.fm/s/78209b35
Audio file: https://media.transistor.fm/78209b35/9d2c8a41.mp3
Processing state: not_requested
JSON: https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/refertrack-referring-then-tracking-for-embodied-visual-tracking
Duration seconds: 1248

## Resource

🤗 Upvotes: 45 | cs.RO Authors: Hanjing Ye, Tianle Zeng, Jiazhao Zhang, Shaoan Wang, Zibo Zhang, Weisi Situ, Yuchen Zhou, Yonggen Ling, Hong Zhang Title: ReferTrack: Referring Then Tracking for Embodied Visual Tracking Arxiv: http://arxiv.org/abs/2607.20061v1 Abstract: Embodied visual tracking (EVT) requires a mobile agent to continuously follow a specific target described in natural language using only onboard vision. While recent vision-language-action (VLA) policies unify target identification and trajectory planning, their chain-of-thought (CoT) reasoning often operates in abstract spatial latents that are difficult to supervise and weakly aligned with explicit image-space detections. To address this, we introduce ReferTrack, a referring-then-tracking paradigm that grounds EVT using a single forward-facing camera. Our model first selects the target from an indexed set of bounding boxes, then decodes tracking waypoints conditioned on this image-grounded decision. To preserve target motion cues over time, ReferTrack maintains a sliding-window queue of previously selected bounding boxes, injecting their geometric features into the visual history via temporal-viewpoint-bbox indicator (TVBI) tokens. We further enhance target identification by co-training on a custom Refer-QA dataset. On EVT-Bench, ReferTrack achieves state-of-the-art single-view performance with success rates of 89.4%, 73.3%, and 74.1% on the single-target, distracted, and ambiguity tracking splits, respectively -- matching or even surpassing several multi-camera baselines on identification-heavy tasks. Finally, real-world deployments on legged and humanoid robots validate its robust sim-to-real transfer capabilities. Code is available at https://github.com/MedlarTea/referTrack.

## Actions

- request_transcript: `POST https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/refertrack-referring-then-tracking-for-embodied-visual-tracking/transcription-requests` — Idempotently request low-priority transcript generation for this episode.
- read_markdown: `GET https://stenobird.com/podcast/daily-paper-cast-7079649/refertrack-referring-then-tracking-for-embodied-visual-tracking.md` — Read the agent-friendly Markdown representation of this episode resource.

A page view does not enqueue transcription. Agents should invoke `request_transcript` explicitly when they need this episode processed.

## Transcript

Full transcripts are not published on public pages unless there is a clear rights basis.