HorNet: A Hierarchical Offshoot Recurrent Network for Improving Person Re-ID via Image Captioning

no code implementations • 14 Aug 2019 • Shi-Yang Yan, Jun Xu, Yuai Liu, Lin Xu

Then the proposed HorNet can learn the visual and language representation from both the images and captions jointly, and thus enhance the performance of person re-ID.

Generative Adversarial Network Image Captioning +1

Learning with Batch-wise Optimal Transport Loss for 3D Shape Recognition

no code implementations • CVPR 2019 • Lin Xu, Han Sun, Yuai Liu

It can accelerate the convergence rate significantly while achieving a state-of-the-art recognition performance.

3D Shape Recognition Metric Learning +1