相关论文: Latent Variable Model for Multi-modal Translation

In multimodal unsupervised image-to-image translation tasks, the goal is to translate an image from the source domain to many images in the target domain. We present a simple method that produces higher quality images than current…

This paper studies zero-shot cross-lingual transfer of vision-language models. Specifically, we focus on multilingual text-to-video search and propose a Transformer-based model that learns contextualized multilingual multimodal embeddings.…

Generative classifiers offer potential advantages over their discriminative counterparts, namely in the areas of data efficiency, robustness to data shift and adversarial examples, and zero-shot learning (Ng and Jordan,2002; Yogatama et…

Multimodal language models attempt to incorporate non-linguistic features for the language modeling task. In this work, we extend a standard recurrent neural network (RNN) language model with features derived from videos. We train our…

Non-autoregressive machine translation (NAT) has recently made great progress. However, most works to date have focused on standard translation tasks, even though some edit-based NAT models, such as the Levenshtein Transformer (LevT), seem…

There has been relatively little attention to incorporating linguistic prior to neural machine translation. Much of the previous work was further constrained to considering linguistic prior on the source side. In this paper, we propose a…

Video-text retrieval is a class of cross-modal representation learning problems, where the goal is to select the video which corresponds to the text query between a given text query and a pool of candidate videos. The contrastive paradigm…

Multimodal learning has been lacking principled ways of combining information from different modalities and learning a low-dimensional manifold of meaningful representations. We study multimodal learning and sensor fusion from a latent…

Multi-modal machine translation aims at translating the source sentence into a different language in the presence of the paired image. Previous work suggests that additional visual information only provides dispensable help to translation,…

Multimodal machine translation involves drawing information from more than one modality, based on the assumption that the additional modalities will contain useful alternative views of the input data. The most prominent tasks in this area…

Temporal prediction is critical for making intelligent and robust decisions in complex dynamic environments. Motion prediction needs to model the inherently uncertain future which often contains multiple potential outcomes, due to…

In this paper a doubly attentive transformer machine translation model (DATNMT) is presented in which a doubly-attentive transformer decoder normally joins spatial visual features obtained via pretrained convolutional neural networks,…

Recently, vision-language joint representation learning has proven to be highly effective in various scenarios. In this paper, we specifically adapt vision-language joint learning for scene text detection, a task that intrinsically involves…

Multimodal machine translation is one of the applications that integrates computer vision and language processing. It is a unique task given that in the field of machine translation, many state-of-the-arts algorithms still only employ…

We present a deep generative model of bilingual sentence pairs for machine translation. The model generates source and target sentences jointly from a shared latent representation and is parameterised by neural networks. We perform…

The integration of large language models (LLMs) with vision-language (VL) tasks has been a transformative development in the realm of artificial intelligence, highlighting the potential of LLMs as a versatile general-purpose chatbot.…

Pretrained vision-and-language BERTs aim to learn representations that combine information from both modalities. We propose a diagnostic method based on cross-modal input ablation to assess the extent to which these models actually…

Latent traversal is a popular approach to visualize the disentangled latent representations. Given a bunch of variations in a single unit of the latent representation, it is expected that there is a change in a single factor of variation of…

In recent years, multi-modal machine translation has attracted significant interest in both academia and industry due to its superior performance. It takes both textual and visual modalities as inputs, leveraging visual context to tackle…

End-to-end optimization has achieved state-of-the-art performance on many specific problems, but there is no straight-forward way to combine pretrained models for new problems. Here, we explore improving modularity by learning a post-hoc…