Metraipolis › archive › dc_1da9bcd154af

TempoGround: State-Aware Streaming Visual Grounding with Vision-Language Models — arXiv:2609.02359

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.02359
License (as archived)
CC0-1.0
Archived
2026-10-17T05:50:03.048Z
SHA-256 of the archived text
176b04eb71dac7cf1f93b522b20718430c03dddd6c4016e092e47b8a78f85241
Stable URL of this page
https://metraipolis.com/documento/dc_1da9bcd154af

How to cite

TempoGround: State-Aware Streaming Visual Grounding with Vision-Language Models — arXiv:2609.02359 — arXiv (en), https://arxiv.org/abs/2609.02359 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_1da9bcd154af (Metraipolis archive dc_1da9bcd154af, sha256 176b04eb71dac7cf1f93b522b20718430c03dddd6c4016e092e47b8a78f85241)
BibTeX
@misc{dc1da9bcd154af,
  title = {TempoGround: State-Aware Streaming Visual Grounding with Vision-Language Models — arXiv:2609.02359},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.02359},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_1da9bcd154af; sha256 176b04eb71dac7cf1f93b522b20718430c03dddd6c4016e092e47b8a78f85241},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.02359. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Visual grounding maps language referents to spatial targets and is central to open-vocabulary perception with vision-language models. Existing methods have made substantial progress on single-frame and video-based visual grounding, yet under streaming inputs they still suffer from identity drift, cross-frame inconsistency, and fragile localization under partial occlusion. To address these issues, we present TempoGround, a VLM-native framework that detects cross-frame object correspondence and explicitly models object presence states, thereby enabling accurate and consistent visual grounding under streaming inputs. The key is a curriculum prediction mechanism guided by state-aware cross-frame correspondence: TempoGround resolves 2D instance association, predicts whether each object newly enters, continues in, or leaves the view, decodes the 2D box, and then lifts it to a camera-frame 3D box. As token-level supervision alone cannot capture the geometric objectives of streaming grounding, we further introduce Streaming Grounding Reinforcement (SGR), which optimizes TempoGround with verifiable Grounding, Identity, and Consistency rewards, jointly reinforcing persistent localization and temporally consistent predictions. We carefully design a three-stage training strategy and train TempoGround on large-scale data. We evaluate visual grounding under causally streaming inputs on multiple challenging benchmarks: TempoGround improves [email protected] and [email protected] by 4.4 and 0.5 on average, and [email protected] and AP_3D by 6.2 and 7.5, respectively. These results demonstrate that TempoGround provides a practical foundation for visual grounding under streaming inputs.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-03 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.02359 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T05:25:58.107Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-03?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).