TimePLE: Rethinking Temporal Representation for Video Temporal Grounding
Video temporal grounding (VTG) aims to localize the continuous video interval described by a natural-language query. However, current VLM-based methods typically produce this interval indirectly through two endpoint outputs, represented either as discrete timestamp tokens or continuous boundary coordinates. These formulations differ in how endpoints are encoded, but not in what is predicted: the event interval remains a derived object, while interval validity, duration, and interval-level similarity are handled only implicitly. We propose TimePLE, which reformulates VTG from endpoint prediction to interval-native grounding by predicting a single joint distribution over valid temporal inte...
| Authors | Yuhui Zeng, Xinyu Mao, Xiaokun Liu et al. |
|---|---|
| Primary category | cs.CV |
| Published | 27 July 2026 |
| Last updated at source | 27 July 2026 |
Connected in the knowledge graph
- KlingTeam/TimePLE-DatasetDataset · cited by
Models and datasets referencing this paper
- KlingTeam/TimePLE-DatasetDataset
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.