# DSE-VTG: Dual-Side Enhancement for Training-Free Video Temporal Grounding

arXiv: https://arxiv.org/abs/2609.08850 · HTML: https://mlsanity.com/paper/2609.08850/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 42 of its 51 references that are in the map.
- First posted on arXiv 8 Sep 2026.

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

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [TALL: Temporal Activity Localization via Language Query](https://mlsanity.com/paper/1705.02101/) (2017)
- [Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding](https://mlsanity.com/paper/1604.01753/) (2016)
- [InternVideo: General Video Foundation Models via Generative and Discriminative Learning](https://mlsanity.com/paper/2212.03191/) (2022)
- [TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding](https://mlsanity.com/paper/2312.02051/) (2023)
- [VTimeLLM: Empower LLM to Grasp Video Moments](https://mlsanity.com/paper/2311.18445/) (2023)
- [Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Ranking](https://mlsanity.com/paper/2601.04720/) (2026)
- [UniVTG: Towards Unified Video-Language Temporal Grounding](https://mlsanity.com/paper/2307.16715/) (2023)
- [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)
- [Semantic Conditioned Dynamic Modulation for Temporal Sentence Grounding in Videos](https://mlsanity.com/paper/1910.14303/) (2019)
- [VLM2Vec-V2: Advancing Multimodal Embedding for Videos, Images, and Visual Documents](https://mlsanity.com/paper/2507.04590/) (2025)
- [Knowing Where to Focus: Event-aware Transformer for Video Grounding](https://mlsanity.com/paper/2308.06947/) (2023)
- [Compositional Temporal Grounding with Structured Variational Cross-Graph Correspondence Learning](https://mlsanity.com/paper/2203.13049/) (2022)
- [TR-DETR: Task-Reciprocal Transformer for Joint Moment Retrieval and Highlight Detection](https://mlsanity.com/paper/2401.02309/) (2024)
- [Weakly Supervised Dense Event Captioning in Videos](https://mlsanity.com/paper/1812.03849/) (2018)
- [Memory-Guided Semantic Learning Network for Temporal Sentence Grounding](https://mlsanity.com/paper/2201.00454/) (2022)
- [A Closer Look at Temporal Sentence Grounding in Videos: Dataset and Metric](https://mlsanity.com/paper/2101.09028/) (2021)
- [Cross-Sentence Temporal and Semantic Relations in Video Activity Localisation](https://mlsanity.com/paper/2107.11443/) (2021)
- [Zero-shot Natural Language Video Localization](https://mlsanity.com/paper/2110.00428/) (2021)
- [R2-Tuning: Efficient Image-to-Video Transfer Learning for Video Temporal Grounding](https://mlsanity.com/paper/2404.00801/) (2024)
- [RzenEmbed: Towards Comprehensive Multimodal Retrieval](https://mlsanity.com/paper/2510.27350/) (2025)
- [Training-free Video Temporal Grounding using Large-scale Pre-trained Models](https://mlsanity.com/paper/2408.16219/) (2024)
- [Towards Balanced Alignment: Modal-Enhanced Semantic Modeling for Video Moment Retrieval](https://mlsanity.com/paper/2312.12155/) (2023)
- [Video Activity Localisation with Uncertainties in Temporal Boundary](https://mlsanity.com/paper/2206.12923/) (2022)
- [FlashVTG: Feature Layering and Adaptive Score Handling Network for Video Temporal Grounding](https://mlsanity.com/paper/2412.13441/) (2024)
- [Language-free Training for Zero-shot Video Grounding](https://mlsanity.com/paper/2210.12977/) (2022)

## Abstract (arXiv)

Text-guided Video Temporal Grounding (VTG) aims to localize the relevant segments in an untrimmed video based on text queries, yet collecting dense temporal annotations and training task-specific models remain costly and brittle under distribution shift. Recent training-free VTG approaches mitigate this issue by directly matching pretrained vision-language representations, but they still face two fundamental information bottlenecks: frame-wise visual encoding overlooks temporal dynamics, while fixed query embeddings cannot resolve query ambiguity. To address these issues, we propose DSE-VTG, a underlineDual-underlineSide underlineEnhancement framework that addresses both without any task-specific training. On the visual side, Multi-scale Similarity Fusion (MSF) combines frame- and clip-level similarities into a unified, temporally aware similarity profile. On the textual side, Query-level Test-Time Adaptation (Q-TTA) optimizes a lightweight additive offset to adapt the query embedding to the video at test time, without finetuning the backbone or calling external large language models. Extensive experiments on three standard and two OOD benchmarks show that DSE-VTG achieves state-of-the-art performance among training-free methods. On Charades-STA, it improves mIoU over the strongest prior training-free method by 5.61 points. Under distribution shift, DSE-VTG reaches 50.86 mIoU on Charades-CG Novel-Word, surpassing the strongest supervised baseline by 2.76 mIoU. Our code will be released upon acceptance.