# Towards Debiasing Temporal Sentence Grounding in Video

arXiv: https://arxiv.org/abs/2111.04321 · HTML: https://mlsanity.com/paper/2111.04321/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 58 references that are in the map.
- First posted on arXiv 8 Nov 2021.

## Builds on (most cited first, 30 of 42)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering](https://mlsanity.com/paper/1612.00837/) (2016)
- [Dense-Captioning Events in Videos](https://mlsanity.com/paper/1705.00754/) (2017)
- [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)
- [Don't Just Assume; Look and Answer: Overcoming Priors for Visual Question Answering](https://mlsanity.com/paper/1712.00377/) (2017)
- [Learning 2D Temporal Adjacent Networks for Moment Localization with Natural Language](https://mlsanity.com/paper/1912.03590/) (2019)
- [Don't Take the Easy Way Out: Ensemble Based Methods for Avoiding Known Dataset Biases](https://mlsanity.com/paper/1909.03683/) (2019)
- [Span-based Localizing Network for Natural Language Video Localization](https://mlsanity.com/paper/2004.13931/) (2020)
- [RUBi: Reducing Unimodal Biases in Visual Question Answering](https://mlsanity.com/paper/1906.10169/) (2019)
- [Dense Regression Network for Video Grounding](https://mlsanity.com/paper/2004.03545/) (2020)
- [To Find Where You Talk: Temporal Sentence Localization in Video with Attention Based Location Regression](https://mlsanity.com/paper/1804.07014/) (2018)
- [Counterfactual Samples Synthesizing for Robust Visual Question Answering](https://mlsanity.com/paper/2003.06576/) (2020)
- [MAN: Moment Alignment Network for Natural Language Moment Retrieval via Iterative Graph Adjustment](https://mlsanity.com/paper/1812.00087/) (2018)
- [Semantic Conditioned Dynamic Modulation for Temporal Sentence Grounding in Videos](https://mlsanity.com/paper/1910.14303/) (2019)
- [Multilevel Language and Vision Integration for Text-to-Clip Retrieval](https://mlsanity.com/paper/1804.05113/) (2018)
- [Overcoming Language Priors in Visual Question Answering with Adversarial Regularization](https://mlsanity.com/paper/1810.03649/) (2018)
- [Interventional Video Grounding with Dual Contrastive Learning](https://mlsanity.com/paper/2106.11013/) (2021)
- [Boundary Proposal Network for Two-Stage Natural Language Video Localization](https://mlsanity.com/paper/2103.08109/) (2021)
- [Weakly Supervised Video Moment Retrieval From Text Queries](https://mlsanity.com/paper/1904.03282/) (2019)
- [MAC: Mining Activity Concepts for Language-based Temporal Localization](https://mlsanity.com/paper/1811.08925/) (2018)
- [Temporally Grounding Language Queries in Videos by Contextual Boundary-aware Prediction](https://mlsanity.com/paper/1909.05010/) (2019)
- [Localizing Moments in Video with Temporal Language](https://mlsanity.com/paper/1809.01337/) (2018)
- [ExCL: Extractive Clip Localization Using Natural Language Descriptions](https://mlsanity.com/paper/1904.02755/) (2019)
- [Cross-Modal Interaction Networks for Query-Based Moment Retrieval in Videos](https://mlsanity.com/paper/1906.02497/) (2019)
- [Weakly-Supervised Video Moment Retrieval via Semantic Completion Network](https://mlsanity.com/paper/1911.08199/) (2019)
- [Read, Watch, and Move: Reinforcement Learning for Temporally Grounding Natural Language Descriptions in Videos](https://mlsanity.com/paper/1901.06829/) (2019)
- [Video Corpus Moment Retrieval with Contrastive Learning](https://mlsanity.com/paper/2105.06247/) (2021)

## Built on by (most cited first, 11 of 11)

- [MAD: A Scalable Dataset for Language Grounding in Videos from Movie Audio Descriptions](https://mlsanity.com/paper/2112.00431/) (2021)
- [Knowing Where to Focus: Event-aware Transformer for Video Grounding](https://mlsanity.com/paper/2308.06947/) (2023)
- [MomentDiff: Generative Video Moment Retrieval from Random to Real](https://mlsanity.com/paper/2307.02869/) (2023)
- [Temporal Sentence Grounding in Videos: A Survey and Future Directions](https://mlsanity.com/paper/2201.08071/) (2022)
- [Background-aware Moment Detection for Video Moment Retrieval](https://mlsanity.com/paper/2306.02728/) (2023)
- [Bias-Conflict Sample Synthesis and Adversarial Removal Debias Strategy for Temporal Sentence Grounding in Video](https://mlsanity.com/paper/2401.07567/) (2024)
- [SVLTA: Benchmarking Vision-Language Temporal Alignment via Synthetic Video Situation](https://mlsanity.com/paper/2504.05925/) (2025)
- [Transform-Equivariant Consistency Learning for Temporal Sentence Grounding](https://mlsanity.com/paper/2305.04123/) (2023)
- [Diversified Augmentation with Domain Adaptation for Debiased Video Temporal Grounding](https://mlsanity.com/paper/2501.06746/) (2025)
- [ResidualViT for Efficient Temporally Dense Video Encoding](https://mlsanity.com/paper/2509.13255/) (2025)
- [Towards Debiasing Frame Length Bias in Text-Video Retrieval via Causal Intervention](https://mlsanity.com/paper/2309.09311/) (2023)

## Abstract (arXiv)

The temporal sentence grounding in video (TSGV) task is to locate a temporal moment from an untrimmed video, to match a language query, i.e., a sentence. Without considering bias in moment annotations (e.g., start and end positions in a video), many models tend to capture statistical regularities of the moment annotations, and do not well learn cross-modal reasoning between video and language query. In this paper, we propose two debiasing strategies, data debiasing and model debiasing, to "force" a TSGV model to capture cross-modal interactions. Data debiasing performs data oversampling through video truncation to balance moment temporal distribution in train set. Model debiasing leverages video-only and query-only models to capture the distribution bias, and forces the model to learn cross-modal interactions. Using VSLNet as the base model, we evaluate impact of the two strategies on two datasets that contain out-of-distribution test instances. Results show that both strategies are effective in improving model generalization capability. Equipped with both debiasing strategies, VSLNet achieves best results on both datasets.