No abstract

Recently, deep hashing methods have attracted much attention in multimedia retrieval task. Some of them can even perform cross-modal retrieval. However, almost all existing deep cross-modal hashing methods are pairwise optimizing methods, which means that they become time-consuming if they are extended to large scale datasets. In this paper, we propose a novel tri-stage deep cross-modal hashing method – Dual Deep Neural Networks Cross-Modal Hashing, i.e., DDCMH, which employs two deep networks to generate hash codes for different modalities. Specifically, in Stage 1, it leverages a single-modal hashing method to generate the initial binary codes of textual modality of training samples; in Stage 2, these binary codes are treated as supervised information to train an image network, which maps visual modality to a binary representation; in Stage 3, the visual modality codes are reconstructed according to a reconstruction procedure, and used as supervised information to train a text network, which generates the binary codes for textual modality. By doing this, DDCMH can make full use of inter-modal information to obtain high quality binary codes, and avoid the problem of pairwise optimization by optimizing different modalities independently. The proposed method can be treated as a framework which can extend any single-modal hashing method to perform cross-modal search task. DDCMH is tested on several benchmark datasets. The results demonstrate that it outperforms both deep and shallow state-of-the-art hashing methods.

Hemorrhagic fever with renal syndrome (HFRS), caused by hantavirus, is occasionally seen in tropical areas. The virus is carried by specific rodent host species. Hemorrhagic fever with renal syndrome is characterized by renal failure and hemorrhagic manifestations, and its complications may be severe, including massive bleeding, multi-organ dysfunction, and possibly death. In this patient case, a 46-year-old woman diagnosed with HFRS initially presented with fever, impaired function, and thrombocytopenia. Four days after symptom onset, the patient complained of abrupt right lower abdominal pain and numbness. Magnetic resonance imaging revealed a spinal subarachnoid hemorrhage (SAH) beyond the T7 to S2 vertebrae. No cases of spinal SAH in HFRS have been reported until now. This case demonstrates that when a patient’s symptoms are atypical, bleeding-related complications must be considered.

Consistent hashing is a technique that can minimize key remapping when the number of hash buckets changes. The paper proposes a fast consistent hash algorithm (called power consistent hash) that has O(1) expected time for key lookup, independent of the number of buckets. Hash values are computed in real time. No search data structure is constructed to store bucket ranges or key mappings. The algorithm has a lightweight design using O(1) space with superior scalability. In particular, it uses two auxiliary hash functions to achieve distribution uniformity and O(1) expected time for key lookup. Furthermore, it performs consistent hashing such that only a minimal number of keys are remapped when the number of buckets changes. Consistent hashing has a wide range of use cases, including load balancing, distributed caching, and distributed key-value stores. The proposed algorithm is faster than well-known consistent hash algorithms with O(log n) lookup time.