EventCoT: Event-centric Video Chain-of-thought for Reasoning Temporal Localization
TL;DR
This work proposes the first event-centric video chain-of-thought framework, dubbed EventCoT, which achieves state-of-the-art results on ActivityNet-RTL while using substantially fewer visual tokens than previous work, and attains strong zero-shot results on the grounded video question answering benchmark ReXTime.
Abstract
Reasoning temporal localization (RTL) requires a model to generate an answer that itself contains the time interval supporting it, coupling high-level reasoning with temporal grounding in a single response. To tackle this challenge, we propose the first event-centric video chain-of-thought framework, dubbed EventCoT. EventCoT first performs event-centric tokenization, converting the video into compact event tokens that enable efficient identification of question-relevant events. It then reasons within these events to generate the answer, grounding the time interval via embedding matching that aligns placeholder tokens with visual embeddings. EventCoT achieves state-of-the-art results on ActivityNet-RTL while using substantially fewer visual tokens than previous work, and attains strong zero-shot results on the grounded video question answering benchmark ReXTime. Our code will be released for research purposes.