# Multi-Pair Temporal Sentence Grounding via Multi-Thread Knowledge Transfer Network

arXiv: https://arxiv.org/abs/2412.15678 · HTML: https://mlsanity.com/paper/2412.15678/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 69 of its 194 references that are in the map.
- First posted on arXiv 20 Dec 2024.

## Builds on (most cited first, 30 of 69)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [NExT-GPT: Any-to-Any Multimodal LLM](https://mlsanity.com/paper/2309.05519/) (2023)
- [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)
- [Skip-Thought Vectors](https://mlsanity.com/paper/1506.06726/) (2015)
- [Span-based Localizing Network for Natural Language Video Localization](https://mlsanity.com/paper/2004.13931/) (2020)
- [Dense Regression Network for Video Grounding](https://mlsanity.com/paper/2004.03545/) (2020)
- [Video-of-Thought: Step-by-Step Video Reasoning from Perception to Cognition](https://mlsanity.com/paper/2501.03230/) (2024)
- [When MOE Meets LLMs: Parameter Efficient Fine-tuning for Multi-task Medical Applications](https://mlsanity.com/paper/2310.18339/) (2023)
- [A Survey of Knowledge Graph Reasoning on Graph Types: Static, Dynamic, and Multimodal](https://mlsanity.com/paper/2212.05767/) (2022)
- [DocPedia: Unleashing the Power of Large Multimodal Model in the Frequency Domain for Versatile Document Understanding](https://mlsanity.com/paper/2311.11810/) (2023)
- [ComDefend: An Efficient Image Compression Model to Defend Adversarial Examples](https://mlsanity.com/paper/1811.12673/) (2018)
- [LAS-AT: Adversarial Training with Learnable Attack Strategy](https://mlsanity.com/paper/2203.06616/) (2022)
- [Negative Sample Matters: A Renaissance of Metric Learning for Temporal Grounding](https://mlsanity.com/paper/2109.04872/) (2021)
- [Weakly Supervised Video Moment Retrieval From Text Queries](https://mlsanity.com/paper/1904.03282/) (2019)
- [UniDoc: A Universal Large Multimodal Model for Simultaneous Text Detection, Recognition, Spotting and Understanding](https://mlsanity.com/paper/2308.11592/) (2023)
- [SPTS v2: Single-Point Scene Text Spotting](https://mlsanity.com/paper/2301.01635/) (2023)
- [TextSquare: Scaling up Text-Centric Visual Instruction Tuning](https://mlsanity.com/paper/2404.12803/) (2024)
- [Adv-watermark: A Novel Watermark Perturbation for Adversarial Examples](https://mlsanity.com/paper/2008.01919/) (2020)
- [Harmonizing Visual Text Comprehension and Generation](https://mlsanity.com/paper/2407.16364/) (2024)
- [Multi-modal In-Context Learning Makes an Ego-evolving Scene Text Recognizer](https://mlsanity.com/paper/2311.13120/) (2023)
- [Spectral Feature Augmentation for Graph Contrastive Learning and Beyond](https://mlsanity.com/paper/2212.01026/) (2022)
- [Vitron: A Unified Pixel-level Vision LLM for Understanding, Generating, Segmenting, Editing](https://mlsanity.com/paper/2412.19806/) (2024)
- [LLM-ESR: Large Language Models Enhancement for Long-tailed Sequential Recommendation](https://mlsanity.com/paper/2405.20646/) (2024)
- [Fine-grained Iterative Attention Network for TemporalLanguage Localization in Videos](https://mlsanity.com/paper/2008.02448/) (2020)
- [Multi-Modal Cross-Domain Alignment Network for Video Moment Retrieval](https://mlsanity.com/paper/2209.11572/) (2022)
- [Knowledge Graph Contrastive Learning Based on Relation-Symmetrical Structure](https://mlsanity.com/paper/2211.10738/) (2022)
- [You Can Ground Earlier than See: An Effective and Efficient Pipeline for Temporal Sentence Grounding in Compressed Videos](https://mlsanity.com/paper/2303.07863/) (2023)
- [Boosting Fast Adversarial Training with Learnable Adversarial Initialization](https://mlsanity.com/paper/2110.05007/) (2021)
- [ParGo: Bridging Vision-Language with Partial and Global Views](https://mlsanity.com/paper/2408.12928/) (2024)

## Built on by (most cited first, 15 of 15)

- [Taylor Series-Inspired Local Structure Fitting Network for Few-shot Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2504.02454/) (2025)
- [Unveiling the Fragility of Vision-Language Models: Multi-Modal Adversarial Synergy via Texture-Constrained Perturbations and Cross-Modal Optimization](https://mlsanity.com/paper/2605.26501/) (2026)
- [Adaptive Multi-prompt Contrastive Network for Few-shot Out-of-distribution Detection](https://mlsanity.com/paper/2506.17633/) (2025)
- [Rethinking Weakly-supervised Video Temporal Grounding From a Game Perspective](https://mlsanity.com/paper/2605.26441/) (2026)
- [Disentangling Adversarial Prompts: A Semantic-Graph Defense for Robust LLM Security](https://mlsanity.com/paper/2605.27823/) (2026)
- [Towards Unified Vision-Language Models with Incomplete Multi-Modal Inputs](https://mlsanity.com/paper/2605.27894/) (2026)
- [Fewer Steps, Better Performance: Efficient Cross-Modal Clip Trimming for Video Moment Retrieval Using Language](https://mlsanity.com/paper/2605.29793/) (2026)
- [SciEducator: Scientific Video Understanding and Educating via Deming-Cycle Multi-Agent System](https://mlsanity.com/paper/2511.17943/) (2025)
- [CogniVerse: Revolutionizing Multi-Modal Retrieval-Augmented Generation with Cognitive Reflection and Geometric Reasoning](https://mlsanity.com/paper/2605.29602/) (2026)
- [Annotations Are Not All You Need: A Cross-modal Knowledge Transfer Network for Unsupervised Temporal Sentence Grounding](https://mlsanity.com/paper/2605.30742/) (2026)
- [Immuno-VLM: Immunizing Large Vision-Language Models via Generative Semantic Antibodies for Open-World Trustworthiness](https://mlsanity.com/paper/2605.30745/) (2026)
- [SLAP: The Semantic Least Action Principle for Variational Video-Language Modeling](https://mlsanity.com/paper/2605.30750/) (2026)
- [Hierarchical Semantic-Augmented Navigation: Optimal Transport and Graph-Driven Reasoning for Vision-Language Navigation](https://mlsanity.com/paper/2606.01565/) (2026)
- [Learning from Few Samples: A Novel Approach for High-Quality Malcode Generation](https://mlsanity.com/paper/2508.18148/) (2025)
- [Turing Patterns for Multimedia: Reaction-Diffusion Multi-Modal Fusion for Language-Guided Video Moment Retrieval](https://mlsanity.com/paper/2606.01615/) (2026)

## Abstract (arXiv)

Given some video-query pairs with untrimmed videos and sentence queries, temporal sentence grounding (TSG) aims to locate query-relevant segments in these videos. Although previous respectable TSG methods have achieved remarkable success, they train each video-query pair separately and ignore the relationship between different pairs. We observe that the similar video/query content not only helps the TSG model better understand and generalize the cross-modal representation but also assists the model in locating some complex video-query pairs. Previous methods follow a single-thread framework that cannot co-train different pairs and usually spends much time re-obtaining redundant knowledge, limiting their real-world applications. To this end, in this paper, we pose a brand-new setting: Multi-Pair TSG, which aims to co-train these pairs. In particular, we propose a novel video-query co-training approach, Multi-Thread Knowledge Transfer Network, to locate a variety of video-query pairs effectively and efficiently. Firstly, we mine the spatial and temporal semantics across different queries to cooperate with each other. To learn intra- and inter-modal representations simultaneously, we design a cross-modal contrast module to explore the semantic consistency by a self-supervised strategy. To fully align visual and textual representations between different pairs, we design a prototype alignment strategy to 1) match object prototypes and phrase prototypes for spatial alignment, and 2) align activity prototypes and sentence prototypes for temporal alignment. Finally, we develop an adaptive negative selection module to adaptively generate a threshold for cross-modal matching. Extensive experiments show the effectiveness and efficiency of our proposed method.