# TrackTeller: Temporal Multimodal 3D Grounding for Behavior-Dependent Object References

arXiv: https://arxiv.org/abs/2512.21641 · HTML: https://mlsanity.com/paper/2512.21641/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 27 references that are in the map.
- First posted on arXiv 25 Dec 2025.

## Builds on (most cited first, 12 of 12)

- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queries](https://mlsanity.com/paper/2110.06922/) (2021)
- [PETRv2: A Unified Framework for 3D Perception from Multi-Camera Images](https://mlsanity.com/paper/2206.01256/) (2022)
- [Multi-View Transformer for 3D Visual Grounding](https://mlsanity.com/paper/2204.02174/) (2022)
- [LanguageRefer: Spatial-Language Model for 3D Visual Grounding](https://mlsanity.com/paper/2107.03438/) (2021)
- [ViewRefer: Grasp the Multi-view Knowledge for 3D Visual Grounding with GPT and Prototype Guidance](https://mlsanity.com/paper/2303.16894/) (2023)
- [SeeGround: See and Ground for Zero-Shot Open-Vocabulary 3D Visual Grounding](https://mlsanity.com/paper/2412.04383/) (2024)
- [NS3D: Neuro-Symbolic Grounding of 3D Objects and Relations](https://mlsanity.com/paper/2303.13483/) (2023)
- [Standing Between Past and Future: Spatio-Temporal Modeling for Multi-Camera 3D Multi-Object Tracking](https://mlsanity.com/paper/2302.03802/) (2023)
- [NuGrounding: A Multi-View 3D Visual Grounding Framework in Autonomous Driving](https://mlsanity.com/paper/2503.22436/) (2025)
- [GroundFlow: A Plug-in Module for Temporal Reasoning on 3D Point Cloud Sequential Grounding](https://mlsanity.com/paper/2506.21188/) (2025)
- [Fine-Grained Spatial and Verbal Losses for 3D Visual Grounding](https://mlsanity.com/paper/2411.03405/) (2024)

## Abstract (arXiv)

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.