# Video-Text Temporal Localization via Multi-Scale Convolution and Dynamic Routing

arXiv: https://arxiv.org/abs/2607.05093 · HTML: https://mlsanity.com/paper/2607.05093/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 27 references that are in the map.
- First posted on arXiv 6 Jul 2026.

## Builds on (most cited first, 7 of 7)

- [Deep Neural Networks for Rank-Consistent Ordinal Regression Based On Conditional Probabilities](https://mlsanity.com/paper/2111.08851/) (2021)
- [On the Consistency of Ordinal Regression Methods](https://mlsanity.com/paper/1408.2327/) (2014)
- [Deep Relative Attributes](https://mlsanity.com/paper/1512.04103/) (2015)
- [Context-Aware Transformers For Spinal Cancer Detection and Radiological Grading](https://mlsanity.com/paper/2206.13173/) (2022)
- [SpineNetV2: Automated Detection, Labelling and Radiological Grading Of Clinical MR Scans](https://mlsanity.com/paper/2205.01683/) (2022)
- [Relative Attribute Classification with Deep Rank SVM](https://mlsanity.com/paper/2009.07717/) (2020)
- [A Stronger Baseline For Automatic Pfirrmann Grading Of Lumbar Spine MRI Using Deep Learning](https://mlsanity.com/paper/2210.14597/) (2022)

## Abstract (arXiv)

Video-text temporal localization requires precise alignment between natural language queries and corresponding video segments, a fundamental challenge in multimodal understanding. We present a novel framework that addresses two critical limitations of existing methods: inadequate modeling of hierarchical temporal structure and inability to handle complex many-to-many correspondences between modalities. Our approach introduces a multi-scale temporal convolutional encoder that captures motion patterns across different temporal granularities - from instantaneous frame transitions to extended action sequences. We further propose a capsule-based dynamic routing mechanism that iteratively refines segment-query associations through structured agreement updates, enabling flexible modeling of non-monotonic alignments. These components are unified through a multi-task learning objective that jointly optimizes temporal boundary regression, cross-modal semantic alignment, and capsule diversity. Extensive experiments on ActivityNet Captions demonstrate significant improvements, achieving 42.9% Recall@0.5 and 41.1% mean IoU, surpassing strong transformer-based baselines while maintaining computational efficiency. Our results validate that combining hierarchical temporal modeling with structured semantic routing provides an effective solution for fine-grained video-language understanding.