Triadic temporal-semantic alignment for weakly-supervised video moment retrieval
Authors:
- Jin LiuJLJin Liu
- JiaLong XieJXJiaLong Xie
- Fengyu ZhouFZFengyu Zhou
- Shengfeng HeSHShengfeng He
- 23 July 2024
- journal article
- research article
- Published by Elsevier in Pattern Recognition
- Vol. 156
Abstract
No abstract availableKeywords
This publication has 33 references indexed in Scilit:
- Question-conditioned debiasing with focal visual context fusion for visual question answeringKnowledge-Based Systems, 2023
- Encoder–decoder cycle for visual question answering based on perception-action cyclePattern Recognition, 2023
- Topic-aware video summarization using multimodal transformerPattern Recognition, 2023
- Be flexible! learn to debias by sampling and prompting for robust visual question answeringInformation Processing & Management, 2023
- Dynamic self-attention with vision synchronization networks for video question answeringPattern Recognition, 2022
- Cascaded Prediction Network via Segment Tree for Temporal Video Grounding2021
- Exploring global diverse attention via pairwise temporal relation for video summarizationPattern Recognition, 2021
- Fine-Grained Video-Text Retrieval With Hierarchical Graph Reasoning2020
- Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset2017
- ActivityNet: A large-scale video benchmark for human activity understanding2015