# Empower Words: DualGround for Structured Phrase and Sentence-Level Temporal Grounding

arXiv: https://arxiv.org/abs/2510.20244 · HTML: https://mlsanity.com/paper/2510.20244/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 38 references that are in the map.
- First posted on arXiv 23 Oct 2025.

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

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [SlowFast Networks for Video Recognition](https://mlsanity.com/paper/1812.03982/) (2018)
- [Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding](https://mlsanity.com/paper/2306.02858/) (2023)
- [Object-Centric Learning with Slot Attention](https://mlsanity.com/paper/2006.15055/) (2020)
- [TALL: Temporal Activity Localization via Language Query](https://mlsanity.com/paper/1705.02101/) (2017)
- [InternVideo2: Scaling Foundation Models for Multimodal Video Understanding](https://mlsanity.com/paper/2403.15377/) (2024)
- [ActionFormer: Localizing Moments of Actions with Transformers](https://mlsanity.com/paper/2202.07925/) (2022)
- [Learning 2D Temporal Adjacent Networks for Moment Localization with Natural Language](https://mlsanity.com/paper/1912.03590/) (2019)
- [UniVTG: Towards Unified Video-Language Temporal Grounding](https://mlsanity.com/paper/2307.16715/) (2023)
- [Local-Global Video-Text Interactions for Temporal Grounding](https://mlsanity.com/paper/2004.07514/) (2020)
- [Query-Dependent Video Representation for Moment Retrieval and Highlight Detection](https://mlsanity.com/paper/2303.13874/) (2023)
- [UMT: Unified Multi-modal Transformers for Joint Video Moment Retrieval and Highlight Detection](https://mlsanity.com/paper/2203.12745/) (2022)
- [Multilevel Language and Vision Integration for Text-to-Clip Retrieval](https://mlsanity.com/paper/1804.05113/) (2018)
- [Grounded-VideoLLM: Sharpening Fine-grained Temporal Grounding in Video Large Language Models](https://mlsanity.com/paper/2410.03290/) (2024)
- [Knowing Where to Focus: Event-aware Transformer for Video Grounding](https://mlsanity.com/paper/2308.06947/) (2023)
- [Less is More: Learning Highlight Detection from Video Duration](https://mlsanity.com/paper/1903.00859/) (2019)
- [TR-DETR: Task-Reciprocal Transformer for Joint Moment Retrieval and Highlight Detection](https://mlsanity.com/paper/2401.02309/) (2024)
- [Decoupling Static and Hierarchical Motion Perception for Referring Video Segmentation](https://mlsanity.com/paper/2404.03645/) (2024)
- [End-to-end Multi-modal Video Temporal Grounding](https://mlsanity.com/paper/2107.05624/) (2021)
- [Cross-category Video Highlight Detection via Set-based Learning](https://mlsanity.com/paper/2108.11770/) (2021)
- [Learning Trailer Moments in Full-Length Movies](https://mlsanity.com/paper/2008.08502/) (2020)
- [R2-Tuning: Efficient Image-to-Video Transfer Learning for Video Temporal Grounding](https://mlsanity.com/paper/2404.00801/) (2024)
- [Correlation-Guided Query-Dependency Calibration for Video Temporal Grounding](https://mlsanity.com/paper/2311.08835/) (2023)
- [BAM-DETR: Boundary-Aligned Moment Detection Transformer for Temporal Sentence Grounding in Videos](https://mlsanity.com/paper/2312.00083/) (2023)
- [FlashVTG: Feature Layering and Adaptive Score Handling Network for Video Temporal Grounding](https://mlsanity.com/paper/2412.13441/) (2024)
- [LLaVA-MR: Large Language-and-Vision Assistant for Video Moment Retrieval](https://mlsanity.com/paper/2411.14505/) (2024)
- [Let Me Finish My Sentence: Video Temporal Grounding with Holistic Text Understanding](https://mlsanity.com/paper/2410.13598/) (2024)
- [Watch Video, Catch Keyword: Context-aware Keyword Attention for Moment Retrieval and Highlight Detection](https://mlsanity.com/paper/2501.02504/) (2025)

## Built on by (most cited first, 4 of 4)

- [ExpAlign: Expectation-Guided Vision-Language Alignment for Open-Vocabulary Grounding](https://mlsanity.com/paper/2601.22666/) (2026)
- [Multi-Agent Self-Improving Reinforcement Learning for Video Reasoning](https://mlsanity.com/paper/2608.28675/) (2026)
- [DSE-VTG: Dual-Side Enhancement for Training-Free Video Temporal Grounding](https://mlsanity.com/paper/2609.08850/) (2026)
- [IAE-VTG: Interaction-Aligned Action-Entity Video Temporal Grounding](https://mlsanity.com/paper/2609.09736/) (2026)

## Abstract (arXiv)

Video Temporal Grounding (VTG) aims to localize temporal segments in long, untrimmed videos that align with a given natural language query. This task typically comprises two subtasks: Moment Retrieval (MR) and Highlight Detection (HD). While recent advances have been progressed by powerful pretrained vision-language models such as CLIP and InternVideo2, existing approaches commonly treat all text tokens uniformly during crossmodal attention, disregarding their distinct semantic roles. To validate the limitations of this approach, we conduct controlled experiments demonstrating that VTG models overly rely on [EOS]-driven global semantics while failing to effectively utilize word-level signals, which limits their ability to achieve fine-grained temporal alignment. Motivated by this limitation, we propose DualGround, a dual-branch architecture that explicitly separates global and local semantics by routing the [EOS] token through a sentence-level path and clustering word tokens into phrase-level units for localized grounding. Our method introduces (1) tokenrole- aware cross modal interaction strategies that align video features with sentence-level and phrase-level semantics in a structurally disentangled manner, and (2) a joint modeling framework that not only improves global sentence-level alignment but also enhances finegrained temporal grounding by leveraging structured phrase-aware context. This design allows the model to capture both coarse and localized semantics, enabling more expressive and context-aware video grounding. DualGround achieves state-of-the-art performance on both Moment Retrieval and Highlight Detection tasks across QVHighlights and Charades- STA benchmarks, demonstrating the effectiveness of disentangled semantic modeling in video-language alignment.