In this paper, we propose a novel Deep Semantic-Asymmetric Hashing (DSAH) approach, which exploits semantic correlation between query points and their labels in a common semantic space to form more discriminative and similarity-preserving binary codes. Experiments show that DSAH outperforms current ...
The pattern in this problem is that for each number in the list, we are trying to find its complement in the rest of the list. If we find it, we know that these two numbers add up to the target. By storing the numbers and their indices in a dictionary, we can quickly loo...
In addition, a discrete optimization algorithm is proposed to solve the discrete problems. Our major contributions can be summarized as follows: 1. A novel supervised cross-modal hashing method, i.e., DSAH, is proposed to learn the discriminative compact hash codes for large-scale retrieval ...