Interpretable Embedding for Ad-hoc Video Search

arXiv:2402.11812v1 Announce Type: new
Abstract: Answering query with semantic concepts has long been the mainstream approach for video search. Until recently, its performance is surpassed by concept-free approach, which embeds queries in a joint space as videos. Nevertheless, the embedded features as well as search results are not interpretable, hindering subsequent steps in video browsing and query reformulation. This paper integrates feature embedding and concept interpretation into a neural network for unified dual-task learning. In this way, an embedding is …

abstract arxiv concept concepts cs.cv cs.mm embedded embedding features free performance queries query search search results semantic space type video videos