Hypotheses Tree Building for One-Shot Temporal Sentence Localization
Open Access
- 26 June 2023
- journal article
- research article
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 37 (2) , 1640-1648
Abstract
Given an untrimmed video, temporal sentence localization (TSL) aims to localize a specific segment according to a given sentence query. Though respectable works have made decent achievements in this task, they severely rely on dense video frame annotations, which require a tremendous amount of human effort to collect. In this paper, we target another more practical and challenging setting: one-shot temporal sentence localization (one-shot TSL), which learns to retrieve the query information among the entire video with only one annotated frame. Particularly, we propose an effective and novel tree-structure baseline for one-shot TSL, called Multiple Hypotheses Segment Tree (MHST), to capture the query-aware discriminative frame-wise information under the insufficient annotations. Each video frame is taken as the leaf-node, and the adjacent frames sharing the same visual-linguistic semantics will be merged into the upper non-leaf node for tree building. At last, each root node is an individual segment hypothesis containing the consecutive frames of its leaf-nodes. During the tree construction, we also introduce a pruning strategy to eliminate the interference of query-irrelevant nodes. With our designed self-supervised loss functions, our MHST is able to generate high-quality segment hypotheses for ranking and selection with the query. Experiments on two challenging datasets demonstrate that MHST achieves competitive performance compared to existing methods.Keywords
All Related Versions
This publication has 9 references indexed in Scilit:
- Hierarchical Local-Global Transformer for Temporal Sentence GroundingIEEE Transactions on Multimedia, 2023
- Exploring Optical-Flow-Guided Motion and Detection-Based Appearance for Temporal Sentence GroundingIEEE Transactions on Multimedia, 2023
- Multi-Modal Cross-Domain Alignment Network for Video Moment RetrievalIEEE Transactions on Multimedia, 2022
- End-to-End Modeling via Information Tree for One-Shot Natural Language Spatial Video Grounding2022
- ANIMC: A Soft Approach for Autoweighted Noisy and Incomplete Multiview ClusteringIEEE Transactions on Artificial Intelligence, 2021
- Weakly Supervised Temporal Adjacent Network for Language GroundingIEEE Transactions on Multimedia, 2021
- Local Correspondence Network for Weakly Supervised Temporal Sentence GroundingIEEE Transactions on Image Processing, 2021
- Multiple hypothesis tracking for multiple target trackingIEEE Aerospace and Electronic Systems Magazine, 2004
- An efficient implementation of Reid's multiple hypothesis tracking algorithm and its evaluation for the purpose of visual trackingIEEE Transactions on Pattern Analysis and Machine Intelligence, 1996