# Activitynet 2019 Task 3: Exploring Contexts for Dense Captioning Events in Videos

arXiv: https://arxiv.org/abs/1907.05092 · HTML: https://mlsanity.com/paper/1907.05092/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Jul 2019.

## Built on by (most cited first, 5 of 5)

- [HumanVBench: Probing Human-Centric Video Understanding in MLLMs with Automatically Synthesized Benchmarks](https://mlsanity.com/paper/2412.17574/) (2024)
- [Implicit Location-Caption Alignment via Complementary Masking for Weakly-Supervised Dense Video Captioning](https://mlsanity.com/paper/2412.12791/) (2024)
- [A Comprehensive Review of the Video-to-Text Problem](https://mlsanity.com/paper/2103.14785/) (2021)
- [Go Beyond Earth: Understanding Human Actions and Scenes in Microgravity Environments](https://mlsanity.com/paper/2506.02845/) (2025)
- [Team RUC_AIM3 Technical Report at ActivityNet 2021: Entities Object Localization](https://mlsanity.com/paper/2106.06138/) (2021)

## Abstract (arXiv)

Contextual reasoning is essential to understand events in long untrimmed videos. In this work, we systematically explore different captioning models with various contexts for the dense-captioning events in video task, which aims to generate captions for different events in the untrimmed video. We propose five types of contexts as well as two categories of event captioning models, and evaluate their contributions for event captioning from both accuracy and diversity aspects. The proposed captioning models are plugged into our pipeline system for the dense video captioning challenge. The overall system achieves the state-of-the-art performance on the dense-captioning events in video task with 9.91 METEOR score on the challenge testing set.