Large Vision-Language Models (LVLMs) are promising scalable annotators for video understanding, but they are not directly suited for dense temporal annotation. We study this challenge in egocentric streaming understanding, where the goal is to segment continuous first-person video into atomic actions: short, concrete physical interactions with well-localized temporal boundaries.

We propose CoTT (Chains of Temporal Transitions), an annotation-free framework that structures LVLM reasoning around temporal transitions and combines it with iterative streaming distillation. CoTT uses structured LVLM reasoning to generate dense atomic action pseudo-labels from unlabeled egocentric videos, distills these labels into a lightweight online model, and bootstraps the model’s predictions to improve temporal consistency.

On large-scale egocentric benchmarks, EPIC-Kitchens-100 and Ego-Exo4D, CoTT achieves competitive performance against supervised online localization methods without using ground truth temporal annotations for training. It also transfers across egocentric datasets and, on THUMOS14, outperforms prior best training-free zero-shot Temporal Action Localization methods, even without any dataset-specific training or adaptation.