2 papers
cs.CV2025
A Knowledge Noise Mitigation Framework for Knowledge-based Visual Question Answering
Zhiyue Liu, Sihang Liu, Jinyuan Liu +1
Knowledge-based visual question answering (KB-VQA) requires a model to understand images and utilize external knowledge to provide accurate answers. Existing approaches often direc…
cs.CV2024
Don't Look Twice: Faster Video Transformers with Run-Length Tokenization
Rohan Choudhury, Guanglei Zhu, Sihan Liu +3
Transformers are slow to train on videos due to extremely large numbers of input tokens, even though many video tokens are repeated over time. Existing methods to remove such uninf…