Generalization capacity of natural language video localization (NLVL) models

• Main Author: Dhanyamraju, Harsh Rao
• Other Authors: Sun Aixin
• Format: Final Year Project
• Language: English
• Published: Nanyang Technological University 2024
• Subjects: Computer and Information Science; Temporal sentence grounding in video; Natural language video localisation; Generalization; Multimodal; Video moment retrieval; Bias; Deep learning; Artificial intelligence; NLVL; TSGV; VMR; Charades-STA-merged; Charades-ego-STA; Charades-STA; Computer vision; Natural language processing; Information retrieval
• Online Access: https://hdl.handle.net/10356/175072
• Institution: Nanyang Technological University

Generalization is a critical feature of any machine learning model. Natural Language Video Localization (NLVL) tasks involve processing diverse video content, text queries, and timestamp distributions, making generalization a crucial aspect of model performance. Many NLVL datasets, such as Charades-...