A comprehensive review of binary neural network
Deep learning (DL) has recently changed the development of intelligent systems and is
widely adopted in many real-life applications. Despite their various benefits and potentials …
widely adopted in many real-life applications. Despite their various benefits and potentials …
Learning to hash: a comprehensive survey of deep learning-based hashing methods
A Singh, S Gupta - Knowledge and Information Systems, 2022 - Springer
Explosive growth of big data demands efficient and fast algorithms for nearest neighbor
search. Deep learning-based hashing methods have proved their efficacy to learn advanced …
search. Deep learning-based hashing methods have proved their efficacy to learn advanced …
Supervised discrete multiple-length hashing for image retrieval
X Nie, X Liu, J Guo, L Wang… - IEEE Transactions on Big …, 2022 - ieeexplore.ieee.org
Hashing can facilitate efficient retrieval and storage for large-scale images due to the binary
representation. In the real applications, the trade-off between retrieval accuracy and speed …
representation. In the real applications, the trade-off between retrieval accuracy and speed …
A Pedestrian is Worth One Prompt: Towards Language Guidance Person Re-Identification
Extensive advancements have been made in person ReID through the mining of semantic
information. Nevertheless existing methods that utilize semantic-parts from a single image …
information. Nevertheless existing methods that utilize semantic-parts from a single image …
Attack is the best defense: Towards preemptive-protection person re-identification
L Wang, W Zhang, D Wu, F Zhu, B Li - Proceedings of the 30th ACM …, 2022 - dl.acm.org
Person Re-IDentification (ReID) aims at retrieving images of the same person across
multiple camera views. Despite its popularity in surveillance and public safety, the leakage …
multiple camera views. Despite its popularity in surveillance and public safety, the leakage …
Binary Neural Networks in FPGAs: Architectures, Tool Flows and Hardware Comparisons
Y Su, KP Seng, LM Ang, J Smith - Sensors, 2023 - mdpi.com
Binary neural networks (BNNs) are variations of artificial/deep neural network (ANN/DNN)
architectures that constrain the real values of weights to the binary set of numbers {− 1, 1} …
architectures that constrain the real values of weights to the binary set of numbers {− 1, 1} …
Pairwise-Label-Based Deep Incremental Hashing with Simultaneous Code Expansion
Deep incremental hashing has become a subject of considerable interest due to its
capability to learn hash codes in an incremental manner, eliminating the need to generate …
capability to learn hash codes in an incremental manner, eliminating the need to generate …
Efficient hash code expansion by recycling old bits
Deep hashing methods have been intensively studied and successfully applied in large-
scale multimedia retrieval. In real-world scenarios, code length can not be set once for all if …
scale multimedia retrieval. In real-world scenarios, code length can not be set once for all if …
Multi-feature graph attention network for cross-modal video-text retrieval
Cross-modal retrieval between videos and texts has attracted growing attention due to the
rapid growth of user-generated videos on the web. To solve this problem, most approaches …
rapid growth of user-generated videos on the web. To solve this problem, most approaches …
Clustering and Separating Similarities for Deep Unsupervised Hashing
The lack of supervised information is the pivotal problem in unsupervised hashing. Most
methods leverage deep features extracted from pre-trained models to generate semantic …
methods leverage deep features extracted from pre-trained models to generate semantic …