A review on multimodal zero‐shot learning
Multimodal learning provides a path to fully utilize all types of information related to the
modeling target to provide the model with a global vision. Zero‐shot learning (ZSL) is a …
modeling target to provide the model with a global vision. Zero‐shot learning (ZSL) is a …
Ternary adversarial networks with self-supervision for zero-shot cross-modal retrieval
Given a query instance from one modality (eg, image), cross-modal retrieval aims to find
semantically similar instances from another modality (eg, text). To perform cross-modal …
semantically similar instances from another modality (eg, text). To perform cross-modal …
Deep multimodal transfer learning for cross-modal retrieval
Cross-modal retrieval (CMR) enables flexible retrieval experience across different
modalities (eg, texts versus images), which maximally benefits us from the abundance of …
modalities (eg, texts versus images), which maximally benefits us from the abundance of …
Joint feature synthesis and embedding: Adversarial cross-modal retrieval revisited
X Xu, K Lin, Y Yang, A Hanjalic… - IEEE Transactions on …, 2020 - ieeexplore.ieee.org
Recently, generative adversarial network (GAN) has shown its strong ability on modeling
data distribution via adversarial learning. Cross-modal GAN, which attempts to utilize the …
data distribution via adversarial learning. Cross-modal GAN, which attempts to utilize the …
Learning cross-aligned latent embeddings for zero-shot cross-modal retrieval
Abstract 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 …
aims to retrieve data of new classes across different modality data. It is challenging for not …
Pan: Prototype-based adaptive network for robust cross-modal retrieval
In practical applications of cross-modal retrieval, test queries of the retrieval system may vary
greatly and come from unknown category. Meanwhile, due to the cost and difficulty of data …
greatly and come from unknown category. Meanwhile, due to the cost and difficulty of data …
Zero-shot cross-media embedding learning with dual adversarial distribution network
Existing cross-media retrieval methods are mainly based on the condition where the training
set covers all the categories in the testing set, which lack extensibility to retrieve data of new …
set covers all the categories in the testing set, which lack extensibility to retrieve data of new …
Zero-shot cross-modal retrieval by assembling autoencoder and generative adversarial network
Conventional cross-modal retrieval models mainly assume the same scope of the classes
for both the training set and the testing set. This assumption limits their extensibility on zero …
for both the training set and the testing set. This assumption limits their extensibility on zero …
Alignment efficient image-sentence retrieval considering transferable cross-modal representation learning
Traditional image-sentence cross-modal retrieval methods usually aim to learn consistent
representations of heterogeneous modalities, thereby to search similar instances in one …
representations of heterogeneous modalities, thereby to search similar instances in one …
Multimodal disentanglement variational autoencoders for zero-shot cross-modal retrieval
Zero-Shot Cross-Modal Retrieval (ZS-CMR) has recently drawn increasing attention as it
focuses on a practical retrieval scenario, ie, the multimodal test set consists of unseen …
focuses on a practical retrieval scenario, ie, the multimodal test set consists of unseen …