Goto

Collaborating Authors

 ssrp cross




Appendix 1 0.1 Data augmentation

Neural Information Processing Systems

Figure 1 shows some examples of augmented MSCOCO images and captions.We perform image-3 Figure 1 illustrates the visual-textual alignment mechanisms of the three variants of our proposed SSRP. NL VR2 is a challenging visual reasoning task. During testing, we adopt beam search with a beam size of 5. We apply the same training and testing settings for Up-Down (Our Impl.) and SSRP Figure 3: Illustrations of the two image retrieval methods mentioned in our paper. Figure 4: Examples of generated relationships for different augmented images. Figure 5: Example of generated relationships for different augmented sentences.