# Multi-scale 2D Representation Learning for weakly-supervised moment retrieval

arXiv: https://arxiv.org/abs/2111.02741 · HTML: https://mlsanity.com/paper/2111.02741/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 30 references that are in the map.
- First posted on arXiv 4 Nov 2021.

## Builds on (most cited first, 19 of 19)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Localizing Moments in Video with Natural Language](https://mlsanity.com/paper/1708.01641/) (2017)
- [TALL: Temporal Activity Localization via Language Query](https://mlsanity.com/paper/1705.02101/) (2017)
- [Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding](https://mlsanity.com/paper/1604.01753/) (2016)
- [Caffe: Convolutional Architecture for Fast Feature Embedding](https://mlsanity.com/paper/1408.5093/) (2014)
- [Learning 2D Temporal Adjacent Networks for Moment Localization with Natural Language](https://mlsanity.com/paper/1912.03590/) (2019)
- [BSN: Boundary Sensitive Network for Temporal Action Proposal Generation](https://mlsanity.com/paper/1806.02964/) (2018)
- [Graph Convolutional Networks for Temporal Action Localization](https://mlsanity.com/paper/1909.03252/) (2019)
- [Multilevel Language and Vision Integration for Text-to-Clip Retrieval](https://mlsanity.com/paper/1804.05113/) (2018)
- [Fast Learning of Temporal Action Proposal via Dense Boundary Generator](https://mlsanity.com/paper/1911.04127/) (2019)
- [Weakly Supervised Video Moment Retrieval From Text Queries](https://mlsanity.com/paper/1904.03282/) (2019)
- [Temporally Grounding Language Queries in Videos by Contextual Boundary-aware Prediction](https://mlsanity.com/paper/1909.05010/) (2019)
- [Proposal-free Temporal Moment Localization of a Natural-Language Query in Video using Guided Attention](https://mlsanity.com/paper/1908.07236/) (2019)
- [AutoLoc: Weakly-supervised Temporal Action Localization](https://mlsanity.com/paper/1807.08333/) (2018)
- [Background Suppression Network for Weakly-supervised Temporal Action Localization](https://mlsanity.com/paper/1911.09963/) (2019)
- [Weakly-Supervised Video Moment Retrieval via Semantic Completion Network](https://mlsanity.com/paper/1911.08199/) (2019)
- [Weakly Supervised Dense Event Captioning in Videos](https://mlsanity.com/paper/1812.03849/) (2018)
- [LoGAN: Latent Graph Co-Attention Network for Weakly-Supervised Video Moment Retrieval](https://mlsanity.com/paper/1909.13784/) (2019)
- [WSLLN: Weakly Supervised Natural Language Localization Networks](https://mlsanity.com/paper/1909.00239/) (2019)

## Built on by (most cited first, 2 of 2)

- [Temporal Sentence Grounding in Videos: A Survey and Future Directions](https://mlsanity.com/paper/2201.08071/) (2022)
- [A Survey on Video Moment Localization](https://mlsanity.com/paper/2306.07515/) (2023)

## Abstract (arXiv)

Video moment retrieval aims to search the moment most relevant to a given language query. However, most existing methods in this community often require temporal boundary annotations which are expensive and time-consuming to label. Hence weakly supervised methods have been put forward recently by only using coarse video-level label. Despite effectiveness, these methods usually process moment candidates independently, while ignoring a critical issue that the natural temporal dependencies between candidates in different temporal scales. To cope with this issue, we propose a Multi-scale 2D Representation Learning method for weakly supervised video moment retrieval. Specifically, we first construct a two-dimensional map for each temporal scale to capture the temporal dependencies between candidates. Two dimensions in this map indicate the start and end time points of these candidates. Then, we select top-K candidates from each scale-varied map with a learnable convolutional neural network. With a newly designed Moments Evaluation Module, we obtain the alignment scores of the selected candidates. At last, the similarity between captions and language query is served as supervision for further training the candidates' selector. Experiments on two benchmark datasets Charades-STA and ActivityNet Captions demonstrate that our approach achieves superior performance to state-of-the-art results.