Interpretable Embedding for Ad-hoc Video Search
This work addresses the lack of interpretability in concept-free video search, which hinders video browsing and query reformulation, by providing an interpretable embedding method.
The paper tackles the problem of interpretability in ad-hoc video search by integrating feature embedding and concept interpretation into a neural network for dual-task learning, resulting in a large margin of improvement compared to state-of-the-art approaches on TRECVid benchmarked datasets.
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 associated with a list of semantic concepts as an interpretation of video content. This paper empirically demonstrates that, by using either the embedding features or concepts, considerable search improvement is attainable on TRECVid benchmarked datasets. Concepts are not only effective in pruning false positive videos, but also highly complementary to concept-free search, leading to large margin of improvement compared to state-of-the-art approaches.