# Coarse to Fine: Video Retrieval before Moment Localization

arXiv: https://arxiv.org/abs/2110.07201 · HTML: https://mlsanity.com/paper/2110.07201/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 10 references that are in the map.
- First posted on arXiv 14 Oct 2021.

## Builds on (most cited first, 9 of 9)

- [HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-training](https://mlsanity.com/paper/2005.00200/) (2020)
- [Span-based Localizing Network for Natural Language Video Localization](https://mlsanity.com/paper/2004.13931/) (2020)
- [ConSERT: A Contrastive Framework for Self-Supervised Sentence Representation Transfer](https://mlsanity.com/paper/2105.11741/) (2021)
- [TVR: A Large-Scale Dataset for Video-Subtitle Moment Retrieval](https://mlsanity.com/paper/2001.09099/) (2020)
- [QANet: Combining Local Convolution with Global Self-Attention for Reading Comprehension](https://mlsanity.com/paper/1804.09541/) (2018)
- [VALUE: A Multi-Task Benchmark for Video-and-Language Understanding Evaluation](https://mlsanity.com/paper/2106.04632/) (2021)
- [Video Corpus Moment Retrieval with Contrastive Learning](https://mlsanity.com/paper/2105.06247/) (2021)
- [A Hierarchical Multi-Modal Encoder for Moment Localization in Video Corpus](https://mlsanity.com/paper/2011.09046/) (2020)
- [Parallel Attention Network with Sequence Matching for Video Grounding](https://mlsanity.com/paper/2105.08481/) (2021)

## Built on by (most cited first, 1 of 1)

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

## Abstract (arXiv)

The current state-of-the-art methods for video corpus moment retrieval (VCMR) often use similarity-based feature alignment approach for the sake of convenience and speed. However, late fusion methods like cosine similarity alignment are unable to make full use of the information from both query texts and videos. In this paper, we combine feature alignment with feature fusion to promote the performance on VCMR.