Superpixel semantics representation and pre-training for vision–language tasks
- 17 November 2024
- journal article
- research article
- Published by Elsevier in Neurocomputing
- Vol. 615
Abstract
No abstract availableKeywords
Funding Information
- National Natural Science Foundation of China
This publication has 43 references indexed in Scilit:
- Mix-tower: Light visual question answering framework based on exclusive self-attention mechanismNeurocomputing, 2024
- A systematic review of hate speech automatic detection using natural language processingNeurocomputing, 2023
- Multi-level Alignment Network for Domain Adaptive Cross-modal RetrievalNeurocomputing, 2021
- Reducing Language Biases in Visual Question Answering with Visually-Grounded Question Encoder2020
- UNITER: UNiversal Image-TExt Representation Learning2020
- Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering2018
- Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image AnnotationsInternational Journal of Computer Vision, 2017
- Where to Look: Focus Regions for Visual Question Answering2016
- Deep visual-semantic alignments for generating image descriptions2015
- Microsoft COCO: Common Objects in Context2014