Zero-Shot Cross-Modal Retrieval (ZS-CMR) is an emerging research hotspot that aims to retrieve data of new classes across different modality data. It is challenging for not only the heterogeneous distributions across different modalities, but also the inconsistent semantics across seen and unseen ...
Zero-Shot Learning of Class Semantics via Temporal Attention 论文链接: [https://arxiv.org/abs/1809.00116] 概述: 这篇论文研究了如何利用视频中的动态信息进行ZSL。作者提出了一个基于时间注意力机制的模型,可以学习到类别的语义信息。 Learning Semantic Models for Cross-Modal Zero-Shot Sketch Data Retrieval...
Learning Semantic Models for Cross-Modal Zero-Shot Sketch Data Retrieval 论文链接: [https://www.sciencedirect.com/science/article/abs/pii/S0031320318303701] 概述: 这篇论文研究了如何进行跨模态的零次学习,特别是在草图数据检索的任务中。 以上这些论文只是零次学习领域的冰山一角,具体选择哪篇论文取决于你...
Zero-shot learning through cross-modal transfer[J]. Advances in neural information processing systems, 2013, 26. 1. 整体概要 这是多模态的一篇早年的paper,整体的工作就是来做图像识别,但其它的方式只是识别训练过的图像类别。一个例子就是区别是狗还是猫,当训练完模型后,再给一张狗的图像,就算是这个图像...
Zero-Shot Cross-Modal Retrieval (ZS-CMR) is an emerging research hotspot that aims to retrieve data of new classes across different modality data. It is ch... K Lin,X Xu,L Gao,... - Aaai Conference on Artificial Intelligence: Aaai 被引量: 0发表: 2020年 Attribute-Guided Network for Cr...
WAD-CMSN: Wasserstein distance-based cross-modal semantic network for zero-shot sketch-based image retrieval Zero-shot sketch-based image retrieval (ZSSBIR) aims at retrieving natural images given free hand-drawn sketches that may not appear during training. Previ... G Xu,Z Hu,J Cai - 《Inte...
Thus, the Zero-Shot Sketch Based Image Retrieval (ZS-SBIR) task introduced in this paper provides a more realistic setup for the sketch-based retrieval task. Towards this end, we propose a new benchmark for the ZS-SBIR task by cre- ating a careful split of the Sketchy database. We...
On cross-modal retrieval tasks, we have not observed as clear a benefit of the Lu setup compared to Uu or UU (Fig- ure 3). For very long tuning schedules, Uu or UU sometimes overtake Lu on these tasks. Our results suggest that the pro- posed Lu setup can still save...
As an important part of ZSIH, we formulate a generative hashing scheme in reconstructing semantic knowledge representations for zero-shot retrieval. To the best of our knowledge, ZSIH is the first zero-shot hashing work suitable for SBIR and cross-modal search. Comprehensive experiments are ...
根据上述观察,作者通过 Generalized Zero-Shot Classification(GZSC)的Aligned Cross-Modal Representations(ACMR),提出了一种新的 VAE 网络。 整体概念图 创新点 提出了 ACMR,并在四个公开数据集上都取得了 SOTA 的性能 提出了一种新的 Vision-Semantic Alignment(VSA)方法,用于加强跨模态特征对齐 提出了一种新的 ...