InstructStep: Fine-Grained Localization of Step Content and Relation in Instructional Video
Open Access
- 27 October 2025
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 3163-3172
Abstract
No abstract availableFunding Information
- Beijing Natural Science Foundation (4242028,L251032,L231012)
- Aviation Science Foundation of China (202400550M5002)
- Open Project of Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, Anhui University (MMC202401)
- National Natural Science Foundation of China (62376021,62006015)
- Natural Science Foundation of Hebei Province (F2025105036)
- CEFLA Audio-Video Restoration and Evaluation Key Lab of Ministry of Culture and Tourism
This publication has 26 references indexed in Scilit:
- VTimeLLM: Empower LLM to Grasp Video Moments2024
- Reciprocal Teacher-Student Learning via Forward and Feedback Knowledge DistillationIEEE Transactions on Multimedia, 2024
- MulKD: Multi-layer Knowledge Distillation via collaborative learningEngineering Applications of Artificial Intelligence, 2024
- Adapted large language models can outperform medical experts in clinical text summarizationNature Medicine, 2024
- Exploring Video Frame Redundancies for Efficient Data Sampling and Annotation in Instance Segmentation2023
- A dataset for medical instructional video classification and question answeringScientific Data, 2023
- Knowledge Distillation: A SurveyInternational Journal of Computer Vision, 2021
- Frame-Wise Cross-Modal Matching for Video Moment RetrievalIEEE Transactions on Multimedia, 2021
- Localizing Moments in Video with Natural Language2017
- Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset2017