Positive and Negative Set Designs in Contrastive Feature Learning for Temporal Action Segmentation
YC Chen, WT Chu - IEEE Transactions on Circuits and Systems …, 2024 - ieeexplore.ieee.org
When data labels are scarce, contrastive learning is often used to learn representations in a
weakly-supervised or unsupervised way. In contrastive learning, not only the learning …
weakly-supervised or unsupervised way. In contrastive learning, not only the learning …
Parameter Adaptive Contrastive Hashing for multimedia retrieval
Y Chen, Y Long, Z Yang, J Long - Neural Networks, 2025 - Elsevier
With the emergence of massive amounts of multi-source heterogeneous data on the Internet,
quickly retrieving effective information from this extensive data has become a hot research …
quickly retrieving effective information from this extensive data has become a hot research …
Person in Uniforms Re-Identification
Person in Uniforms Re-identification (PU-ReID) is an emerging computer vision task for
various intelligent video surveillance applications. PU-ReID is much understudied due to the …
various intelligent video surveillance applications. PU-ReID is much understudied due to the …
Dual Self-Paced Hashing for Image Retrieval
In recent years, image hashing has attracted more and more attention in practical retrieval
applications due to its low storage cost and high query speed. Although existing hashing …
applications due to its low storage cost and high query speed. Although existing hashing …
Unsupervised Deep Triplet Hashing for Image Retrieval
L Meng, Q Zhang, R Yang… - IEEE Signal Processing …, 2024 - ieeexplore.ieee.org
Deep hashing enhances image retrieval accuracy by integrating hash encoding with deep
neural networks. However, existing unsupervised deep hashing methods primarily rely on …
neural networks. However, existing unsupervised deep hashing methods primarily rely on …