keyword

hierarchical video captioning

Hierarchical video captioning is a computer vision and natural language processing task that involves generating descriptive text for video content across multiple levels of temporal granularity and semantic abstraction. Unlike conventional video captioning approaches that produce a single description for a brief clip, hierarchical captioning models the multi-tiered structure of extended video footage. The process typically produces fine-grained descriptions for short clips containing specific atomic actions, intermediate summaries for longer segments composed of multiple related events, and comprehensive overviews for entire long-form videos. This structured approach enables systems to preserve detailed visual actions while capturing broader narrative context and long-range semantic relationships.

1 item

Video ReCap: Recursive Captioning of Hour-Long Videos

Md Mohaiminul Islam, Ngan Ho, Xitong Yang, Tushar Nagarajan, Lorenzo Torresani, Gedas Bertasius

OrganizationsMetaUniversity of North Carolina at Chapel Hill

Why you should read this

Presents a recursive video-language model and benchmark dataset that efficiently generate hierarchical captions across multiple temporal granularities for hour-long untrimmed videos.

Most video captioning models are designed to process short video clips of few seconds and output text describing low-level visual concepts (e.g., objects, scenes, atomic actions). However, most real-world videos last for minutes or hours and have a complex hierarchical structure spanning different temporal granularities. We propose Video ReCap, a recursive video captioning model that can process video inputs of dramatically different lengths (from 1 second to 2 hours) and output video captions at multiple hierarchy levels. The recursive video-language architecture exploits the synergy between different video hierarchies and can process hour-long videos efficiently. We utilize a curriculum learning training scheme to learn the hierarchical structure of videos, starting from clip-level captions describing atomic actions, then focusing on segment-level descriptions, and concluding with generating summaries for hour-long videos. Furthermore, we introduce Ego4D-HCap dataset by augmenting Ego4D with 8,267 manually collected long-range video summaries. Our recursive model can flexibly generate captions at different hierarchy levels while also being useful for other complex video understanding tasks, such as VideoQA on EgoSchema. Data, code, and models are publicly available at https://sites.google.com/view/vidrecap.

Source

https://arxiv.org/pdf/2402.13250

Added

2026-09-26