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 power of GAN to model the cross-modal joint distribution and to learn compatible cross-modal features, is becoming the research hotspot. However, the existing cross-modal GAN approaches typically 1) require labeled multimodal data of massive labor cost to establish cross-modal correlation; 2) utilize the vanilla GAN model that results in unstable training procedure and meaningless synthetic features; and 3) lack of extensibility for retrieving cross-modal data of new classes. In this article, we revisit the adversarial learning in existing cross-modal GAN methods and propose Joint Feature Synthesis and Embedding (JFSE), a novel method that jointly performs multimodal feature synthesis and common embedding space learning to overcome the above three shortcomings. Specifically, JFSE deploys two coupled conditional Wassertein GAN modules for the input data of two modalities, to synthesize meaningful and correlated multimodal features under the guidance of the word embeddings of class labels. Moreover, three advanced distribution alignment schemes with advanced cycle-consistency constraints are proposed to preserve the semantic compatibility and enable the knowledge transfer in the common embedding space for both the true and synthetic cross-modal features. All these add-ons in JFSE not only help to learn more effective common embedding space that effectively captures the cross-modal correlation but also facilitate to transfer knowledge to multimodal data of new classes. Extensive experiments are conducted on four widely used cross-modal datasets, and the comparisons with more than ten state-of-the-art approaches show that our JFSE method achieves remarkably accuracy improvement on both standard retrieval and the newly explored zero-shot and generalized zero-shot retrieval tasks.

Image-sentence matching is a challenging task in the field of language and vision, which aims at measuring the similarities between images and sentence descriptions. Most existing methods independently map the global features of images and sentences into a common space to calculate the image-sentence similarity. However, the image-sentence similarity obtained by these methods may be coarse as (1) an intermediate common space is introduced to implicitly match the heterogeneous features of images and sentences in a global level, and (2) only the inter-modality relations of images and sentences are captured while the intra-modality relations are ignored. To overcome the limitations, we propose a novel Cross-Modal Hybrid Feature Fusion (CMHF) framework for directly learning the image-sentence similarity by fusing multimodal features with inter- and intra-modality relations incorporated. It can robustly capture the high-level interactions between visual regions in images and words in sentences, where flexible attention mechanisms are utilized to generate effective attention flows within and across the modalities of images and sentences. A structured objective with ranking loss constraint is formed in CMHF to learn the image-sentence similarity based on the fused fine-grained features of different modalities bypassing the usage of intermediate common space. Extensive experiments and comprehensive analysis performed on two widely used datasets - Microsoft COCO and Flickr30K - show the effectiveness of the hybrid feature fusion framework in CMHF, in which the state-of-the-art matching performance is achieved by our proposed CMHF method.

Binary codes have often been deployed to facilitate large-scale retrieval tasks, but not that often for image compression. In this paper, we propose a unified framework, BGAN+, that restricts the input noise variable of generative adversarial networks to be binary and conditioned on the features of each input image, and simultaneously learns two binary representations per image: one for image retrieval and the other serving as image compression. Compared to related methods that attempt to learn a single binary code serving both purposes, we demonstrate that choosing for two codes leads to more effective representations due to less concessions needed when balancing the requirements. The added value of using a unified framework compared to two separate frameworks lies in the synergy in data representation that is beneficial for both learning processes. When devising this framework, we also address another challenge in learning binary codes, namely that of learning supervision. While the most striking successes in image retrieval using binary codes have mostly involved discriminative models requiring labels, the proposed BGAN+ framework learns the binary codes in an unsupervised fashion, yet more effectively than the state-of-the-art supervised approaches. The proposed BGAN+ framework is evaluated on three benchmark datasets for image retrieval and two datasets on image compression. The experimental results show that BGAN+ outperforms the existing retrieval methods with significant margins and achieves promising performance for image compression, especially for low bit rates.

We present a scheme to entangle two microwave fields by using the nonlinear magnetostrictive interaction in a ferrimagnet. The magnetostrictive interaction enables the coupling between a magnon mode (spin wave) and a mechanical mode in the ferrimagnet, and the magnon mode simultaneously couples to two microwave cavity fields via the magnetic dipole interaction. The magnon-phonon coupling is enhanced by directly driving the ferrimagnet with a strong red-detuned microwave field, and the driving photons are scattered onto two sidebands induced by the mechanical motion. We show that two cavity fields can be prepared in a stationary entangled state if they are, respectively, resonant with two mechanical sidebands. The present scheme illustrates a new mechanism for creating entangled states of optical fields and enables potential applications in quantum information science and quantum tasks that require entangled microwave fields.

In this article, we address the problem of visual question generation (VQG), a challenge in which a computer is required to generate meaningful questions about an image targeting a given answer. The existing approaches typically treat the VQG task as a reversed visual question answer (VQA) task, requiring the exhaustive match among all the image regions and the given answer. To reduce the complexity, we propose an innovative answer-centric approach termed radial graph convolutional network (Radial-GCN) to focus on the relevant image regions only. Our Radial-GCN method can quickly find the core answer area in an image by matching the latent answer with the semantic labels learned from all image regions. Then, a novel sparse graph of the radial structure is naturally built to capture the associations between the core node (i.e., answer area) and peripheral nodes (i.e., other areas); the graphic attention is subsequently adopted to steer the convolutional propagation toward potentially more relevant nodes for final question generation. Extensive experiments on three benchmark data sets show the superiority of our approach compared with the reference methods. Even in the unexplored challenging zero-shot VQA task, the synthesized questions by our method remarkably boost the performance of several state-of-the-art VQA methods from 0% to over 40%. The implementation code of our proposed method and the successfully generated questions are available at https://github.com/Wangt-CN/VQG-GCN.

A major challenge in matching images and text is that they have intrinsically different data distributions and feature representations. Most existing approaches are based either on embedding or classification, the first one mapping image and text instances into a common embedding space for distance measuring, and the second one regarding image-text matching as a binary classification problem. Neither of these approaches can, however, balance the matching accuracy and model complexity well. We propose a novel framework that achieves remarkable matching performance with acceptable model complexity. Specifically, in the training stage, we propose a novel Multi-modal Tensor Fusion Network (MTFN) to explicitly learn an accurate image-text similarity function with rank-based tensor fusion rather than seeking a common embedding space for each image-text instance. Then, during testing, we deploy a generic Cross-modal Re-ranking (RR) scheme for refinement without requiring additional training procedure. Extensive experiments on two datasets demonstrate that our MTFN-RR consistently achieves the state-of-the-art matching performance with much less time complexity.

In this paper, we propose a novel approach to video captioning based on adversarial learning and long short-term memory (LSTM). With this solution concept, we aim at compensating for the deficiencies of LSTM-based video captioning methods that generally show potential to effectively handle temporal nature of video data when generating captions but also typically suffer from exponential error accumulation. Specifically, we adopt a standard generative adversarial network (GAN) architecture, characterized by an interplay of two competing processes: a 'generator' that generates textual sentences given the visual content of a video and a 'discriminator' that controls the accuracy of the generated sentences. The discriminator acts as an 'adversary' toward the generator, and with its controlling mechanism, it helps the generator to become more accurate. For the generator module, we take an existing video captioning concept using LSTM network. For the discriminator, we propose a novel realization specifically tuned for the video captioning problem and taking both the sentences and video features as input. This leads to our proposed LSTM-GAN system architecture, for which we show experimentally to significantly outperform the existing methods on standard public datasets.

Video captioning, in essential, is a complex natural process, which is affected by various uncertainties stemming from video content, subjective judgment, and so on. In this paper, we build on the recent progress in using encoder-decoder framework for video captioning and address what we find to be a critical deficiency of the existing methods that most of the decoders propagate deterministic hidden states. Such complex uncertainty cannot be modeled efficiently by the deterministic models. In this paper, we propose a generative approach, referred to as multimodal stochastic recurrent neural networks (MS-RNNs), which models the uncertainty observed in the data using latent stochastic variables. Therefore, MS-RNN can improve the performance of video captioning and generate multiple sentences to describe a video considering different random factors. Specifically, a multimodal long short-term memory (LSTM) is first proposed to interact with both visual and textual features to capture a high-level representation. Then, a backward stochastic LSTM is proposed to support uncertainty propagation by introducing latent variables. Experimental results on the challenging data sets, microsoft video description and microsoft research video-to-text, show that our proposed MS-RNN approach outperforms the state-of-the-art video captioning benchmarks.

Cross-modal retrieval aims to enable flexible retrieval experience across different modalities (e.g., texts vs. images). The core of crossmodal retrieval research is to learn a common subspace where the items of different modalities can be directly compared to each other. In this paper, we present a novel Adversarial Cross-Modal Retrieval (ACMR) method, which seeks an effective common subspace based on adversarial learning. Adversarial learning is implemented as an interplay between two processes. The first process, a feature projector, tries to generate a modality-invariant representation in the common subspace and to confuse the other process, modality classifier, which tries to discriminate between different modalities based on the generated representation. We further impose triplet constraints on the feature projector in order to minimize the gap among the representations of all items from different modalities with same semantic labels, while maximizing the distances among semantically different images and texts. Through the joint exploitation of the above, the underlying cross-modal semantic structure of multimedia data is better preserved when this data is projected into the common subspace. Comprehensive experimental results on four widely used benchmark datasets show that the proposed ACMR method is superior in learning effective subspace representation and that it significantly outperforms the state-of-the-art cross-modal retrieval methods.