NUS-WIDE
Canonical28papers using it
2016first seen
The NUS-WIDE dataset is a large-scale benchmark that contains images and their associated tags, used to evaluate cross-modal retrieval methods in multimedia applications.
Papers using NUS-WIDE (28)
- PromptHash: Affinity-Prompted Collaborative Cross-Modal Learning for
Adaptive Hashing RetrievalDeep Hamming Hashing Integrating Transformer and Attention MechanismFeature Fusion Mamba Hashing via Decoupling for Cross-Modal RetrievalMambaHash: Visual State Space Deep Hashing Model for Large-Scale Image RetrievalBinary Generative Adversarial Networks for Image RetrievalSupervised Matrix Factorization for Cross-Modality HashingDeep Priority HashingEmbarrassingly Simple Binary Representation LearningHybridHash: Hybrid Convolutional and Self-Attention Deep Hashing for
Image RetrievalTransitive Hashing Network for Heterogeneous Multimedia RetrievalDeep Saliency HashingCreating Something from Nothing: Unsupervised Knowledge Distillation for
Cross-Modal HashingTransformer-based Clipped Contrastive Quantization Learning for
Unsupervised Image RetrievalEfficient Cross-Modal Retrieval via Deep Binary Hashing and QuantizationDeep Triplet QuantizationDeep Unsupervised Image Hashing by Maximizing Bit EntropyPush for Quantization: Deep Fisher HashingDeep Supervised Hashing with Triplet LabelsLeveraging High-Resolution Features for Improved Deep Hashing-based
Image RetrievalLearning Discriminative Hashing Codes for Cross-Modal Retrieval based on
Multi-view FeaturesDeep Reinforcement Learning with Label Embedding Reward for Supervised
Image HashingTransHash: Transformer-based Hamming Hashing for Efficient Image
RetrievalVision Transformer Hashing for Image RetrievalHard Example Guided Hashing for Image RetrievalAsymmetric Scalable Cross-modal HashingDeep Metric Multi-View Hashing for Multimedia RetrievalCentral Similarity Multi-View Hashing for Multimedia RetrievalRank-Consistency Deep Hashing for Scalable Multi-Label Image Search