OmniGround: Strengthening Omni-Modal Temporal Grounding via Attention-Consistency Training
Overview & Synopsis
Omni-modal large language models can jointly understand video, audio, and text, yet they remain weak at temporal grounding, a capability essential for real-world audio-visual applications. To understand this limitation, we look beyond final predictions and examine the model's internal temporal evidence. We identify a temporal generation gap: the internal attention of the model localizes the target moment more accurately than the timestamps it generates. To close this gap, we propose TACG (Temporal Attention-Consistency Grounding), a post-training method that treats internal attention as a reliable temporal pivot and aligns it with both the model prediction and the ground-truth annotation through attention-consistency training. We further build a 580K-sample training dataset by reconstructing temporal QA from dense audio-visual annotations and organizing general omni-modal instruction data. Using TACG and this training dataset, we train OmniGround, a general-purpose omni-modal model with stronger temporal grounding capability, without injecting any additional temporal cues. OmniGround reaches state-of-the-art omni-modal temporal grounding, including 37.5 mIoU on LongVALE and 35.7 mIoU on UnAV-100, while staying competitive on both general audio-visual understanding and vision-only grounding.
arxiv.org)
← / → for pages • + / - for zoom • 0 to fit width
Powered by Mozilla PDF.js v3.11
Document Information
| Document Title | OmniGround: Strengthening Omni-Modal Temporal Grounding via Attention-Consistency Training |
|---|---|
| Author / Organization | Zixuan Chen, Depeng Wang, Hao Lin, Ke Xu, Ya Guo, Huijia Zhu, Tanfeng Sun, Xinghao Jiang |
| Subject & Discipline | cs.CV |
| Categories | Science & Mathematics |
| Publication Year | 2026 |
| License / Rights | arXiv Open Access / Creative Commons |
| Resource Verification | Listed PDF (Verification Pending) |
| Original Host Website |
arXiv
(arxiv.org)
|
| File Format | application/pdf (Portable Document Format) |
| Language | EN |
| Catalog ID | DOC-274053 |
| Original Source Link | Visit Source Page on arxiv.org » |