Not All Inputs Are Valid: Towards Open-Set Video Moment Retrieval using Language
Open Access
- 28 October 2024
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 28-37
Abstract
Video Moment Retrieval (VMR) targets to retrieve the specific moment corresponding to a sentence query from an untrimmed video. Although recent respectable works have made remarkable progress in this task, they implicitly are rooted in the closed-set assumption that all the given queries as video-relevant. Given an OOD query in open-set scenarios, they still utilize it for wrong retrieval, which might lead to irrecoverable losses in high-risk scenarios, e.g., criminal activity detection. To this end, we creatively explore a brand-new VMR setting termed Open-Set Video Moment Retrieval (OS-VMR), where we should not only retrieve the precise moments based on ID query, but also reject OOD queries. In this paper, we make the first attempt to step toward OS-VMR and propose a novel model OpenVMR, which first distinguishes ID and OOD queries based on the normalizing flow technology, and then conducts moment retrieval based on ID queries. Specifically, we first learn the ID distribution by constructing a normalizing flow, and assume the ID query distribution obeys the multi-variate Gaussian distribution. Then, we introduce an uncertainty score to search the ID-OOD separating boundary. After that, we refine the ID-OOD boundary by pulling together ID query features. Besides, video-query matching and frame-query matching are designed for coarse-grained and fine-grained cross-modal interaction, respectively. Finally, a positive-unlabeled learning module is introduced for moment retrieval. Experimental results on three VMR datasets show the effectiveness of our OpenVMR.Keywords
All Related Versions
This publication has 44 references indexed in Scilit:
- Rethinking Reconstruction Autoencoder-Based Out-of-Distribution Detection2022
- Multi-stage Aggregated Transformer Network for Temporal Language Localization in Videos2021
- Out-of-Distribution Detection Using Union of 1-Dimensional Subspaces2021
- Hyperparameter-Free Out-of-Distribution Detection Using Cosine Similarity2021
- Dense Regression Network for Video Grounding2020
- Multi-Modal Domain Adaptation for Fine-Grained Action Recognition2020
- Learning from positive and unlabeled data: a surveyMachine Learning, 2020
- Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset2017
- Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding2016
- Script Data for Attribute-Based Recognition of Composite Activities2012