MV-Adapter: Multimodal Video Transfer Learning for Video Text Retrieval

arXiv:2301.07868v2 Announce Type: replace
Abstract: State-of-the-art video-text retrieval (VTR) methods typically involve fully fine-tuning a pre-trained model (e.g. CLIP) on specific datasets. However, this can result in significant storage costs in practical applications as a separate model per task must be stored. To address this issue, we present our pioneering work that enables parameter-efficient VTR using a pre-trained model, with only a small number of tunable parameters during training. Towards this goal, we propose a new method dubbed Multimodal Video …

abstract adapter applications art arxiv clip costs cs.cv datasets fine-tuning however issue multimodal per practical pre-trained model retrieval state storage storage costs text transfer transfer learning type video work