# ConTrans: Learning Text-enhanced Local-global Temporal Representations for Zero-shot Temporal Action Localization

arXiv: https://arxiv.org/abs/2605.30689 · HTML: https://mlsanity.com/paper/2605.30689/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 30 of its 33 references that are in the map.
- First posted on arXiv 29 May 2026.

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

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [VQA: Visual Question Answering](https://mlsanity.com/paper/1505.00468/) (2015)
- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [End-to-End Learning of Visual Representations from Uncurated Instructional Videos](https://mlsanity.com/paper/1912.06430/) (2019)
- [Soft-NMS -- Improving Object Detection With One Line of Code](https://mlsanity.com/paper/1704.04503/) (2017)
- [BMN: Boundary-Matching Network for Temporal Action Proposal Generation](https://mlsanity.com/paper/1907.09702/) (2019)
- [ActionFormer: Localizing Moments of Actions with Transformers](https://mlsanity.com/paper/2202.07925/) (2022)
- [Prompting Visual-Language Models for Efficient Video Understanding](https://mlsanity.com/paper/2112.04478/) (2021)
- [The THUMOS Challenge on Action Recognition for Videos "in the Wild"](https://mlsanity.com/paper/1604.06182/) (2016)
- [Unified Contrastive Learning in Image-Text-Label Space](https://mlsanity.com/paper/2204.03610/) (2022)
- [Learning Salient Boundary Feature for Anchor-free Temporal Action Localization](https://mlsanity.com/paper/2103.13137/) (2021)
- [CAMP: Cross-Modal Adaptive Message Passing for Text-Image Retrieval](https://mlsanity.com/paper/1909.05506/) (2019)
- [Video Self-Stitching Graph Network for Temporal Action Localization](https://mlsanity.com/paper/2011.14598/) (2020)
- [UnLoc: A Unified Framework for Video Localization Tasks](https://mlsanity.com/paper/2308.11062/) (2023)
- [BSN++: Complementary Boundary Regressor with Scale-Balanced Relation Modeling for Temporal Action Proposal Generation](https://mlsanity.com/paper/2009.07641/) (2020)
- [Zero-Shot Temporal Action Detection via Vision-Language Prompting](https://mlsanity.com/paper/2207.08184/) (2022)
- [Action Sensitivity Learning for Temporal Action Localization](https://mlsanity.com/paper/2305.15701/) (2023)
- [Zero-Shot Video Captioning with Evolving Pseudo-Tokens](https://mlsanity.com/paper/2207.11100/) (2022)
- [ZSTAD: Zero-Shot Temporal Activity Detection](https://mlsanity.com/paper/2003.05583/) (2020)
- [ZIM: Zero-Shot Image Matting for Anything](https://mlsanity.com/paper/2411.00626/) (2024)
- [MultiCapCLIP: Auto-Encoding Prompts for Zero-Shot Multilingual Visual Captioning](https://mlsanity.com/paper/2308.13218/) (2023)
- [ZEETAD: Adapting Pretrained Vision-Language Model for Zero-Shot End-to-End Temporal Action Detection](https://mlsanity.com/paper/2311.00729/) (2023)
- [Z-GMOT: Zero-shot Generic Multiple Object Tracking](https://mlsanity.com/paper/2305.17648/) (2023)
- [Text-Enhanced Zero-Shot Action Recognition: A training-free approach](https://mlsanity.com/paper/2408.16412/) (2024)
- [LGD: Leveraging Generative Descriptions for Zero-Shot Referring Image Segmentation](https://mlsanity.com/paper/2504.14467/) (2025)
- [Zero-shot Compositional Action Recognition with Neural Logic Constraints](https://mlsanity.com/paper/2508.02320/) (2025)
- [Zero Shot Domain Adaptive Semantic Segmentation by Synthetic Data Generation and Progressive Adaptation](https://mlsanity.com/paper/2508.03300/) (2025)
- [Towards Completeness: A Generalizable Action Proposal Generator for Zero-Shot Temporal Action Localization](https://mlsanity.com/paper/2408.13777/) (2024)

## Abstract (arXiv)

Zero-shot Temporal Action Localization (ZS-TAL) aims to detect and locate previously unseen actions in untrimmed videos. However, existing approaches primarily focus on modeling long-range contextual information, often neglecting the critical relative-offset-based local correlations between video frames. Furthermore, their performance is hindered by limited feature representation capabilities due to the shallow nature of their network architectures. In this paper, we address these limitations by introducing a novel local-global multi-scale feature representation module. We propose a novel multi-scale encoder architecture, termed ConTrans, that integrates convolutional (Conv) inductive biases with transformer Self-attention to jointly capture fine-grained local dependencies and long-range global context, leading to more comprehensive feature representations than existing methods. Experimental evaluations on the ActivityNet-1.3 and THUMOS14 datasets demonstrate that ConTrans significantly outperforms existing methods, establishing a new benchmark for ZS-TAL.