{"ID":2825217,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.21641","arxiv_id":"2512.21641","title":"TrackTeller: Temporal Multimodal 3D Grounding for Behavior-Dependent Object References","abstract":"Understanding natural-language references to objects in dynamic 3D driving scenes is essential for interactive autonomous systems. In practice, many referring expressions describe targets through recent motion or short-term interactions, which cannot be resolved from static appearance or geometry alone. We study temporal language-based 3D grounding, where the objective is to identify the referred object in the current frame by leveraging multi-frame observations. We propose TrackTeller, a temporal multimodal grounding framework that integrates LiDAR-image fusion, language-conditioned decoding, and temporal reasoning in a unified architecture. TrackTeller constructs a shared UniScene representation aligned with textual semantics, generates language-aware 3D proposals, and refines grounding decisions using motion history and short-term dynamics. Experiments on the NuPrompt benchmark demonstrate that TrackTeller consistently improves language-grounded tracking performance, outperforming strong baselines with a 70% relative improvement in Average Multi-Object Tracking Accuracy and a 3.15-3.4 times reduction in False Alarm Frequency.","short_abstract":"Understanding natural-language references to objects in dynamic 3D driving scenes is essential for interactive autonomous systems. In practice, many referring expressions describe targets through recent motion or short-term interactions, which cannot be resolved from static appearance or geometry alone. We study tempor...","url_abs":"https://arxiv.org/abs/2512.21641","url_pdf":"https://arxiv.org/pdf/2512.21641v1","authors":"[\"Jiahong Yu\",\"Ziqi Wang\",\"Hailiang Zhao\",\"Wei Zhai\",\"Xueqiang Yan\",\"Shuiguang Deng\"]","published":"2025-12-25T12:02:56Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.AI\"]","methods":"[]","has_code":false}