Foresee-to-Ground: From Predictive Temporal Perception to Evidence-Driven Reasoning for Video Temporal Grounding
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913151957598208 |
|---|---|
| author | Zheng, Zelin Liu, Xinyan Li, Ruixin Chan, Antoni B. Li, Guorong Huang, Qingming Qing, Laiyun |
| author_facet | Zheng, Zelin Liu, Xinyan Li, Ruixin Chan, Antoni B. Li, Guorong Huang, Qingming Qing, Laiyun |
| contents | Current Video-LLM approaches for Video Temporal Grounding (VTG) typically rely on direct timestamp generation from an unstructured visual-token stream, often leading to brittle numerics and inconsistent boundaries. To address this, we propose Foresee-to-Ground (F2G), a framework that reformulates VTG as a verifiable Identify-then-Measure problem. F2G integrates Predictive Temporal Perception with Evidence-Driven Reasoning: it learns boundary-sensitive temporal representations to build a video-wide evidence pool of candidate event segments, and exposes these segments to the LLM as citable evidence units that bind boundary prediction to explicit event hypotheses. By decoupling event identification from precise boundary measurement, F2G stabilizes grounding and makes predictions verifiable. Extensive experiments demonstrate that F2G consistently improves grounding accuracy across diverse benchmarks, transfers robustly across different Video-LLM backbones, and preserves general video understanding capabilities. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_21973 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Foresee-to-Ground: From Predictive Temporal Perception to Evidence-Driven Reasoning for Video Temporal Grounding Zheng, Zelin Liu, Xinyan Li, Ruixin Chan, Antoni B. Li, Guorong Huang, Qingming Qing, Laiyun Computer Vision and Pattern Recognition Current Video-LLM approaches for Video Temporal Grounding (VTG) typically rely on direct timestamp generation from an unstructured visual-token stream, often leading to brittle numerics and inconsistent boundaries. To address this, we propose Foresee-to-Ground (F2G), a framework that reformulates VTG as a verifiable Identify-then-Measure problem. F2G integrates Predictive Temporal Perception with Evidence-Driven Reasoning: it learns boundary-sensitive temporal representations to build a video-wide evidence pool of candidate event segments, and exposes these segments to the LLM as citable evidence units that bind boundary prediction to explicit event hypotheses. By decoupling event identification from precise boundary measurement, F2G stabilizes grounding and makes predictions verifiable. Extensive experiments demonstrate that F2G consistently improves grounding accuracy across diverse benchmarks, transfers robustly across different Video-LLM backbones, and preserves general video understanding capabilities. |
| title | Foresee-to-Ground: From Predictive Temporal Perception to Evidence-Driven Reasoning for Video Temporal Grounding |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.21973 |