Video and audio are images: A cross-modal mixer for original data on video–audio retrieval
Authors:
- Zichen YuanZYZichen Yuan
- Qi ShenQSQi Shen
- Bingyi ZhengBZBingyi Zheng
- Yuting LiuYLYuting Liu
- Linying JiangLJLinying Jiang
- Guibing GuoGGGuibing Guo
- 8 June 2024
- journal article
- research article
- Published by Elsevier in Knowledge-Based Systems
- Vol. 299
Abstract
No abstract availableKeywords
All Related Versions
This publication has 22 references indexed in Scilit:
- ViSTA: Vision and Scene Text Aggregation for Cross-Modal Retrieval2022
- Exploring Heterogeneous Clues for Weakly-Supervised Audio-Visual Video Parsing2021
- Augment Your Batch: Improving Generalization Through Instance Repetition2020
- Self-Supervised Spatiotemporal Learning via Video Clip Order Prediction2019
- Tracking Emerges by Colorizing Videos2018
- Learning and Using the Arrow of Time2018
- Unsupervised Feature Learning via Non-parametric Instance Discrimination2018
- Self-Supervised Video Representation Learning with Odd-One-Out Networks2017
- Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset2017
- Anticipating Visual Representations from Unlabeled Video2016