A comprehensive survey on cross-modal retrieval
In recent years, cross-modal retrieval has drawn much attention due to the rapid growth of
multimodal data. It takes one type of data as the query to retrieve relevant data of another …
multimodal data. It takes one type of data as the query to retrieve relevant data of another …
Adversarial cross-modal retrieval
B Wang, Y Yang, X Xu, A Hanjalic… - Proceedings of the 25th …, 2017 - dl.acm.org
Cross-modal retrieval aims to enable flexible retrieval experience across different modalities
(eg, texts vs. images). The core of cross-modal retrieval research is to learn a common …
(eg, texts vs. images). The core of cross-modal retrieval research is to learn a common …
Dual-path convolutional image-text embeddings with instance loss
Matching images and sentences demands a fine understanding of both modalities. In this
article, we propose a new system to discriminatively embed the image and text to a shared …
article, we propose a new system to discriminatively embed the image and text to a shared …
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 …
Wasserstein CNN: Learning invariant features for NIR-VIS face recognition
Heterogeneous face recognition (HFR) aims at matching facial images acquired from
different sensing modalities with mission-critical applications in forensics, security and …
different sensing modalities with mission-critical applications in forensics, security and …
Visual domain adaptation: A survey of recent advances
VM Patel, R Gopalan, R Li… - IEEE signal processing …, 2015 - ieeexplore.ieee.org
In pattern recognition and computer vision, one is often faced with scenarios where the
training data used to learn a model have different distribution from the data on which the …
training data used to learn a model have different distribution from the data on which the …
Transductive multi-view zero-shot learning
Most existing zero-shot learning approaches exploit transfer learning via an intermediate
semantic representation shared between an annotated auxiliary dataset and a target dataset …
semantic representation shared between an annotated auxiliary dataset and a target dataset …
Cycle-consistent deep generative hashing for cross-modal retrieval
In this paper, we propose a novel deep generative approach to cross-modal retrieval to
learn hash functions in the absence of paired training samples through the cycle consistency …
learn hash functions in the absence of paired training samples through the cycle consistency …
Multi-view discriminant analysis
In many computer vision systems, the same object can be observed at varying viewpoints or
even by different sensors, which brings in the challenging demand for recognizing objects …
even by different sensors, which brings in the challenging demand for recognizing objects …
Learning compact binary face descriptor for face recognition
Binary feature descriptors such as local binary patterns (LBP) and its variations have been
widely used in many face recognition systems due to their excellent robustness and strong …
widely used in many face recognition systems due to their excellent robustness and strong …