# Semantic Video Moments Retrieval at Scale: A New Task and a Baseline

arXiv: https://arxiv.org/abs/2210.08389 · HTML: https://mlsanity.com/paper/2210.08389/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 32 of its 48 references that are in the map.
- First posted on arXiv 15 Oct 2022.

## Builds on (most cited first, 30 of 32)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [Temporal Segment Networks: Towards Good Practices for Deep Action Recognition](https://mlsanity.com/paper/1608.00859/) (2016)
- [TSM: Temporal Shift Module for Efficient Video Understanding](https://mlsanity.com/paper/1811.08383/) (2018)
- [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)
- [Deep metric learning using Triplet network](https://mlsanity.com/paper/1412.6622/) (2014)
- [Multi-modal Transformer for Video Retrieval](https://mlsanity.com/paper/2007.10639/) (2020)
- [Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks](https://mlsanity.com/paper/1711.10305/) (2017)
- [BMN: Boundary-Matching Network for Temporal Action Proposal Generation](https://mlsanity.com/paper/1907.09702/) (2019)
- [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)
- [Temporal Action Detection with Structured Segment Networks](https://mlsanity.com/paper/1704.06228/) (2017)
- [Unsupervised Representation Learning by Sorting Sequences](https://mlsanity.com/paper/1708.01246/) (2017)
- [SpeedNet: Learning the Speediness in Videos](https://mlsanity.com/paper/2004.06130/) (2020)
- [Single Shot Temporal Action Detection](https://mlsanity.com/paper/1710.06236/) (2017)
- [TURN TAP: Temporal Unit Regression Network for Temporal Action Proposals](https://mlsanity.com/paper/1703.06189/) (2017)
- [Polysemous Visual-Semantic Embedding for Cross-Modal Retrieval](https://mlsanity.com/paper/1906.04402/) (2019)
- [RSPNet: Relative Speed Perception for Unsupervised Video Representation Learning](https://mlsanity.com/paper/2011.07949/) (2020)
- [Video Cloze Procedure for Self-Supervised Spatio-Temporal Learning](https://mlsanity.com/paper/2001.00294/) (2020)
- [Read, Watch, and Move: Reinforcement Learning for Temporally Grounding Natural Language Descriptions in Videos](https://mlsanity.com/paper/1901.06829/) (2019)
- [Tree-Structured Policy based Progressive Reinforcement Learning for Temporally Language Grounding in Video](https://mlsanity.com/paper/2001.06680/) (2020)
- [Temporal Gaussian Mixture Layer for Videos](https://mlsanity.com/paper/1803.06316/) (2018)
- [Improving Spatiotemporal Self-Supervision by Deep Reinforcement Learning](https://mlsanity.com/paper/1807.11293/) (2018)
- [Universal Weighting Metric Learning for Cross-Modal Matching](https://mlsanity.com/paper/2010.03403/) (2020)
- [CONQUER: Contextual Query-aware Ranking for Video Corpus Moment Retrieval](https://mlsanity.com/paper/2109.10016/) (2021)
- [Accurate Temporal Action Proposal Generation with Relation-Aware Pyramid Network](https://mlsanity.com/paper/2003.04145/) (2020)
- [Cross-modal Embeddings for Video and Audio Retrieval](https://mlsanity.com/paper/1801.02200/) (2018)
- [Video Re-localization](https://mlsanity.com/paper/1808.01575/) (2018)
- [Deep Concept-wise Temporal Convolutional Networks for Action Localization](https://mlsanity.com/paper/1908.09442/) (2019)

## Abstract (arXiv)

Motivated by the increasing need of saving search effort by obtaining relevant video clips instead of whole videos, we propose a new task, named Semantic Video Moments Retrieval at scale (SVMR), which aims at finding relevant videos coupled with re-localizing the video clips in them. Instead of a simple combination of video retrieval and video re-localization, our task is more challenging because of several essential aspects. In the 1st stage, our SVMR should take into account the fact that: 1) a positive candidate long video can contain plenty of irrelevant clips which are also semantically meaningful. 2) a long video can be positive to two totally different query clips if it contains clips relevant to two queries. The 2nd re-localization stage also exhibits different assumptions from existing video re-localization tasks, which hold an assumption that the reference video must contain semantically similar segments corresponding to the query clip. Instead, in our scenario, the retrieved long video can be a false positive one due to the inaccuracy of the first stage. To address these challenges, we propose our two-stage baseline solution of candidate videos retrieval followed by a novel attention-based query-reference semantically alignment framework to re-localize target clips from candidate videos. Furthermore, we build two more appropriate benchmark datasets from the off-the-shelf ActivityNet-1.3 and HACS for a thorough evaluation of SVMR models. Extensive experiments are carried out to show that our solution outperforms several reference solutions.