Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

HiCM$^2$: Hierarchical Compact Memory Modeling for Dense Video Captioning

About

With the growing demand for solutions to real-world video challenges, interest in dense video captioning (DVC) has been on the rise. DVC involves the automatic captioning and localization of untrimmed videos. Several studies highlight the challenges of DVC and introduce improved methods utilizing prior knowledge, such as pre-training and external memory. In this research, we propose a model that leverages the prior knowledge of human-oriented hierarchical compact memory inspired by human memory hierarchy and cognition. To mimic human-like memory recall, we construct a hierarchical memory and a hierarchical memory reading module. We build an efficient hierarchical compact memory by employing clustering of memory events and summarization using large language models. Comparative experiments demonstrate that this hierarchical memory recall process improves the performance of DVC by achieving state-of-the-art performance on YouCook2 and ViTT datasets.

Minkuk Kim, Hyeon Bae Kim, Jinyoung Moon, Jinwoo Choi, Seong Tae Kim• 2024

Related benchmarks

TaskDatasetResultRank
Event localizationYouCook2 (val)
Recall32.51
13
Event CaptioningYouCook2 1.0 (val)
METEOR12.8
12
Event localizationViTT (test)
Recall45
4
Event CaptioningViTT (test)
CIDEr51.29
3
Showing 4 of 4 rows

Other info

Follow for update