# ZSTAD: Zero-Shot Temporal Activity Detection

arXiv: https://arxiv.org/abs/2003.05583 · HTML: https://mlsanity.com/paper/2003.05583/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Mar 2020.

## Built on by (most cited first, 16 of 16)

- [Zero-Shot Temporal Action Detection via Vision-Language Prompting](https://mlsanity.com/paper/2207.08184/) (2022)
- [Pseudo-Q: Generating Pseudo Language Queries for Visual Grounding](https://mlsanity.com/paper/2203.08481/) (2022)
- [Deep Learning-based Action Detection in Untrimmed Videos: A Survey](https://mlsanity.com/paper/2110.00111/) (2021)
- [Semantics-Guided Contrastive Network for Zero-Shot Object detection](https://mlsanity.com/paper/2109.06062/) (2021)
- [FitCLIP: Refining Large-Scale Pretrained Image-Text Models for Zero-Shot Video Understanding Tasks](https://mlsanity.com/paper/2203.13371/) (2022)
- [Object Priors for Classifying and Localizing Unseen Actions](https://mlsanity.com/paper/2104.04715/) (2021)
- [ZEETAD: Adapting Pretrained Vision-Language Model for Zero-Shot End-to-End Temporal Action Detection](https://mlsanity.com/paper/2311.00729/) (2023)
- [Dynamic User-controllable Privacy-preserving Few-shot Sensing Framework](https://mlsanity.com/paper/2508.03989/) (2025)
- [Open-Vocabulary Temporal Action Localization using Multimodal Guidance](https://mlsanity.com/paper/2406.15556/) (2024)
- [Exploring Scalability of Self-Training for Open-Vocabulary Temporal Action Localization](https://mlsanity.com/paper/2407.07024/) (2024)
- [Universal Prototype Transport for Zero-Shot Action Recognition and Localization](https://mlsanity.com/paper/2203.03971/) (2022)
- [Zero-shot Action Localization via the Confidence of Large Vision-Language Models](https://mlsanity.com/paper/2410.14340/) (2024)
- [Training-Free Zero-Shot Temporal Action Detection with Vision-Language Models](https://mlsanity.com/paper/2501.13795/) (2025)
- [Less than Few: Self-Shot Video Instance Segmentation](https://mlsanity.com/paper/2204.08874/) (2022)
- [OZ-TAL: Online Zero-Shot Temporal Action Localization](https://mlsanity.com/paper/2605.09976/) (2026)
- [ConTrans: Learning Text-enhanced Local-global Temporal Representations for Zero-shot Temporal Action Localization](https://mlsanity.com/paper/2605.30689/) (2026)

## Abstract (arXiv)

An integral part of video analysis and surveillance is temporal activity detection, which means to simultaneously recognize and localize activities in long untrimmed videos. Currently, the most effective methods of temporal activity detection are based on deep learning, and they typically perform very well with large scale annotated videos for training. However, these methods are limited in real applications due to the unavailable videos about certain activity classes and the time-consuming data annotation. To solve this challenging problem, we propose a novel task setting called zero-shot temporal activity detection (ZSTAD), where activities that have never been seen in training can still be detected. We design an end-to-end deep network based on R-C3D as the architecture for this solution. The proposed network is optimized with an innovative loss function that considers the embeddings of activity labels and their super-classes while learning the common semantics of seen and unseen activities. Experiments on both the THUMOS14 and the Charades datasets show promising performance in terms of detecting unseen activities.