# Bias-Conflict Sample Synthesis and Adversarial Removal Debias Strategy for Temporal Sentence Grounding in Video

arXiv: https://arxiv.org/abs/2401.07567 · HTML: https://mlsanity.com/paper/2401.07567/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 39 references that are in the map.
- First posted on arXiv 15 Jan 2024.

## Builds on (most cited first, 23 of 23)

- [Decoupled Weight Decay Regularization](https://mlsanity.com/paper/1711.05101/) (2017)
- [Span-based Localizing Network for Natural Language Video Localization](https://mlsanity.com/paper/2004.13931/) (2020)
- [Local-Global Video-Text Interactions for Temporal Grounding](https://mlsanity.com/paper/2004.07514/) (2020)
- [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)
- [Semantic Conditioned Dynamic Modulation for Temporal Sentence Grounding in Videos](https://mlsanity.com/paper/1910.14303/) (2019)
- [Temporally Grounding Language Queries in Videos by Contextual Boundary-aware Prediction](https://mlsanity.com/paper/1909.05010/) (2019)
- [Deconfounded Video Moment Retrieval with Causal Intervention](https://mlsanity.com/paper/2106.01534/) (2021)
- [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)
- [Uncovering Hidden Challenges in Query-Based Video Moment Retrieval](https://mlsanity.com/paper/2009.00325/) (2020)
- [Natural Language Video Localization: A Revisit in Span-based Question Answering Framework](https://mlsanity.com/paper/2102.13558/) (2021)
- [Fine-grained Iterative Attention Network for TemporalLanguage Localization in Videos](https://mlsanity.com/paper/2008.02448/) (2020)
- [Reducing the Vision and Language Bias for Temporal Sentence Grounding](https://mlsanity.com/paper/2207.13457/) (2022)
- [Greedy Gradient Ensemble for Robust Visual Question Answering](https://mlsanity.com/paper/2107.12651/) (2021)
- [Self-Regulated Learning for Egocentric Video Activity Anticipation](https://mlsanity.com/paper/2111.11631/) (2021)
- [Relation-aware Video Reading Comprehension for Temporal Language Grounding](https://mlsanity.com/paper/2110.05717/) (2021)
- [Frame-wise Cross-modal Matching for Video Moment Retrieval](https://mlsanity.com/paper/2009.10434/) (2020)
- [Parallel Attention Network with Sequence Matching for Video Grounding](https://mlsanity.com/paper/2105.08481/) (2021)
- [Can Shuffling Video Benefit Temporal Bias Problem: A Novel Training Framework for Temporal Grounding](https://mlsanity.com/paper/2207.14698/) (2022)
- [Latent Adversarial Debiasing: Mitigating Collider Bias in Deep Neural Networks](https://mlsanity.com/paper/2011.11486/) (2020)
- [Towards Debiasing Temporal Sentence Grounding in Video](https://mlsanity.com/paper/2111.04321/) (2021)
- [A Closer Look at Debiased Temporal Sentence Grounding in Videos: Dataset, Metric, and Approach](https://mlsanity.com/paper/2203.05243/) (2022)

## Built on by (most cited first, 7 of 7)

- [Boosting Temporal Sentence Grounding via Causal Inference](https://mlsanity.com/paper/2507.04958/) (2025)
- [Diversified Augmentation with Domain Adaptation for Debiased Video Temporal Grounding](https://mlsanity.com/paper/2501.06746/) (2025)
- [Weakly Supervised Temporal Sentence Grounding via Positive Sample Mining](https://mlsanity.com/paper/2505.06557/) (2025)
- [SMART: Shot-Aware Multimodal Video Moment Retrieval with Audio-Enhanced MLLM](https://mlsanity.com/paper/2511.14143/) (2025)
- [SlotVTG: Object-Centric Adapter for Generalizable Video Temporal Grounding](https://mlsanity.com/paper/2603.25733/) (2026)
- [Distorted or Fabricated? A Survey on Hallucination in Video LLMs](https://mlsanity.com/paper/2604.12944/) (2026)
- [EVIDENT: Routing MLLM Adaptation through Entity-Grounded Visual Evidence for Cross-Domain Video Temporal Grounding](https://mlsanity.com/paper/2605.26104/) (2026)

## Abstract (arXiv)

Temporal Sentence Grounding in Video (TSGV) is troubled by dataset bias issue, which is caused by the uneven temporal distribution of the target moments for samples with similar semantic components in input videos or query texts. Existing methods resort to utilizing prior knowledge about bias to artificially break this uneven distribution, which only removes a limited amount of significant language biases. In this work, we propose the bias-conflict sample synthesis and adversarial removal debias strategy (BSSARD), which dynamically generates bias-conflict samples by explicitly leveraging potentially spurious correlations between single-modality features and the temporal position of the target moments. Through adversarial training, its bias generators continuously introduce biases and generate bias-conflict samples to deceive its grounding model. Meanwhile, the grounding model continuously eliminates the introduced biases, which requires it to model multi-modality alignment information. BSSARD will cover most kinds of coupling relationships and disrupt language and visual biases simultaneously. Extensive experiments on Charades-CD and ActivityNet-CD demonstrate the promising debiasing capability of BSSARD. Source codes are available at https://github.com/qzhb/BSSARD.