Grounding with Confidence: Controllable Generative Video Temporal Grounding

arXiv:2609.39883v1 Announce Type: new Abstract: Video temporal grounding supports applications such as video search, content review, and automated editing by localizing events described in natural language. Yet existing generative models typically output timestamps without explicit interval-level confidence scores to guide candidate selection. We separate candidate generation from acceptance by scoring individual intervals within the original decoding pass. A lightweight confidence head reads pooled decoder states, providing an explicit score trained for interval selection. Offline verifier scores supervise the head on fixed candidate sequences, and temporal-overlap labels adapt it to current rollouts during reinforcement learning. GT-anchored candidate-pool supervision and set-level optimization train the generator. The resulting scores support ranking, threshold-based selection, and rejection without invoking an external verifier at inference. On a fixed OMTG-Bench candidate pool, confidence raises query-macro Recall@0.5 from 9.95% to 14.42% over generation order at a 10% global return budget, and from 26.48% to 31.12% at a 25% budget. The continuous scores let downstream applications adjust return budgets or acceptance thresholds to match their precision-recall preferences, without regenerating candidate intervals.

Related

• Bridging Time and Space: Decoupled Spatio-Temporal Alignment for Video Grounding
• OmniVTG: A Large-Scale Dataset and Training Paradigm for Open-World Video Temporal Grounding
• Locate Anything in Videos: Rethinking Efficient Generative Spatio-Temporal Video Grounding
• MASRA: MLLM-Assisted Semantic-Relational Consistent Alignment for Video Temporal Grounding
• Temporal-Aware Reasoning Optimization for Video Temporal Grounding

Source: arXiv cs.CV | 2026-10-01