ViTexQA: A Multi-frame Temporal Perception Dataset for Video Text Question Answering
- 3 October 2026
- book chapter
- Published by Springer Nature
- p. 712-730
Abstract
No abstract availableKeywords
All Related Versions
This publication has 40 references indexed in Scilit:
- DriveVA: Video Action Models are Zero-Shot Drivers2026
- Enhanced point cloud registration for workpieces using triangular constraint sampling consistency in complex industrial environmentThe Visual Computer, 2026
- Probing the limitations of multimodal language models for chemistry and materials researchNature Computational Science, 2025
- Efficient GPT-4V level multimodal large language model for deployment on edge devicesNature Communications, 2025
- HORUS: Multimodal Large Language Models Framework for Video Retrieval at VBS 20252025
- OCRBench: on the hidden mystery of OCR in large multimodal modelsScience China Information Sciences, 2024
- InternVideo2: Scaling Foundation Models for Multimodal Video Understanding2024
- PosFormer: Recognizing Complex Handwritten Mathematical Expression with Position Forest Transformer2024
- Bridging Synthetic and Real Worlds for Pre-Training Scene Text Detectors2024
- Reading Between the Lanes: Text VideoQA on the Road2023