Towards Visual Feature Translation

  title={Towards Visual Feature Translation},
  author={Jie Hu and R. Ji and H. Liu and Shengchuan Zhang and Cheng Deng and Q. Tian},
  journal={2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  • Jie Hu, R. Ji, +3 authors Q. Tian
  • Published 2019
  • Computer Science
  • 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Most existing visual search systems are deployed based upon fixed kinds of visual features, which prohibits the feature reusing across different systems or when upgrading systems with a new type of feature. Such a setting is obviously inflexible and time/memory consuming, which is indeed mendable if visual features can be ``translated" across systems. In this paper, we make the first attempt towards visual feature translation to break through the barrier of using features across different… Expand
Compatibility-aware Heterogeneous Visual Search
Multi-scale Gem Pooling with N-Pair Center Loss for Fine-Grained Image Search
Information Competing Process for Learning Diversified Representations
Asymmetric metric learning for knowledge transfer


Lost in quantization: Improving particular object retrieval in large scale image databases
Aggregating Local Deep Features for Image Retrieval
Three things everyone should know to improve object retrieval
CNN Features Off-the-Shelf: An Astounding Baseline for Recognition
Deep Image Retrieval: Learning Global Representations for Image Search
SIFT Meets CNN: A Decade Survey of Instance Retrieval
  • L. Zheng, Y. Yang, Q. Tian
  • Computer Science, Medicine
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2018
Large-Scale Image Retrieval with Attentive Deep Local Features
Fine-Tuning CNN Image Retrieval with No Human Annotation
Cross-view action recognition via view knowledge transfer
NetVLAD: CNN Architecture for Weakly Supervised Place Recognition