Deep Hashing with Category Mask for Fast Video Retrieval
This work addresses efficient video retrieval for applications like multimedia search, though it appears incremental as it builds on existing deep hashing methods with a specific optimization.
The paper tackles the problem of fast video retrieval by proposing a deep hashing framework with category masks that filter out binary bits with negative contributions to classification performance. Experimental results show the method outperforms several state-of-the-art approaches on public datasets under various evaluation metrics.
This paper proposes an end-to-end deep hashing framework with category mask for fast video retrieval. We train our network in a supervised way by fully exploiting inter-class diversity and intra-class identity. Classification loss is optimized to maximize inter-class diversity, while intra-pair is introduced to learn representative intra-class identity. We investigate the binary bits distribution related to categories and find out that the effectiveness of binary bits is highly correlated with data categories, and some bits may degrade classification performance of some categories. We then design hash code generation scheme with category mask to filter out bits with negative contribution. Experimental results demonstrate the proposed method outperforms several state-of-the-arts under various evaluation metrics on public datasets.