相关论文: Amortized Context Vector Inference for Sequence-to…

We explore the performance of latent variable models for conditional text generation in the context of neural machine translation (NMT). Similar to Zhang et al., we augment the encoder-decoder NMT paradigm by introducing a continuous latent…

Attention mechanism has been used as an ancillary means to help RNN or CNN. However, the Transformer (Vaswani et al., 2017) recently recorded the state-of-the-art performance in machine translation with a dramatic reduction in training time…

Sound event localization frameworks based on deep neural networks have shown increased robustness with respect to reverberation and noise in comparison to classical parametric approaches. In particular, recurrent architectures that…

In this work, we propose several attention formulations for multivariate sequence data. We build on top of the recently introduced 2D-Attention and reformulate the attention learning methodology by quantifying the relevance of…

Recurrent neural network models with an attention mechanism have proven to be extremely effective on a wide variety of sequence-to-sequence problems. However, the fact that soft attention mechanisms perform a pass over the entire input…

The recognition network in deep latent variable models such as variational autoencoders (VAEs) relies on amortized inference for efficient posterior approximation that can scale up to large datasets. However, this technique has also been…

Variational autoencoders (VAEs) have been widely applied for text modeling. In practice, however, they are troubled by two challenges: information underrepresentation and posterior collapse. The former arises as only the last hidden state…

The attention mechanism has become a cornerstone of modern deep learning architectures, where keys and values are typically derived from the same underlying sequence or representation. This work explores a less conventional scenario, when…

Standard sequence mixing layers used in language models struggle to balance efficiency and performance. Self-attention performs well on long context tasks but has expensive quadratic compute and linear memory costs, while linear attention…

Visual attention, which assigns weights to image regions according to their relevance to a question, is considered as an indispensable part by most Visual Question Answering models. Although the questions may involve complex relations among…

Many vision-language tasks can be reduced to the problem of sequence prediction for natural language output. In particular, recent advances in image captioning use deep reinforcement learning (RL) to alleviate the "exposure bias" during…

Vision Transformers (ViTs) have achieved state-of-the-art performance in image classification, yet their attention mechanisms often remain opaque and exhibit dense, non-structured behaviors. In this work, we adapt our previously proposed…

Neural sequence-to-sequence networks with attention have achieved remarkable performance for machine translation. One of the reasons for their effectiveness is their ability to capture relevant source-side contextual information at each…

It has been widely accepted that Long Short-Term Memory (LSTM) network, coupled with attention mechanism and memory module, is useful for aspect-level sentiment classification. However, existing approaches largely rely on the modelling of…

We propose a novel attentive sequence to sequence translator (ASST) for clip localization in videos by natural language descriptions. We make two contributions. First, we propose a bi-directional Recurrent Neural Network (RNN) with a finely…

The dominant paradigm in spatiotemporal action detection is to classify actions using spatiotemporal features learned by 2D or 3D Convolutional Networks. We argue that several actions are characterized by their context, such as relevant…

Modern learning systems increasingly rely on amortized learning - the idea of reusing computation or inductive biases shared across tasks to enable rapid generalization to novel problems. This principle spans a range of approaches,…

This paper presents a novel spatiotemporal transformer network that introduces several original components to detect actions in untrimmed videos. First, the multi-feature selective semantic attention model calculates the correlations…

Despite the progress made in sentence-level NMT, current systems still fall short at achieving fluent, good quality translation for a full document. Recent works in context-aware NMT consider only a few previous sentences as context and may…

Meta-learning is a framework in which machine learning models train over a set of datasets in order to produce predictions on new datasets at test time. Probabilistic meta-learning has received an abundance of attention from the research…