Related papers: Morphological Inflection Generation with Hard Mono…

Attention is a general reasoning mechanism than can flexibly deal with image information, but its memory requirements had made it so far impractical for high resolution image generation. We present Grid Partitioned Attention (GPA), a new…

Diverse and extensive work has recently been conducted on text-conditioned human motion generation. However, progress in the reverse direction, motion captioning, has seen less comparable advancement. In this paper, we introduce a novel…

The success of Transformer language models is widely credited to their dot-product attention mechanism, which interweaves a set of key design principles: mixing information across positions (enabling multi-token interactions),…

Correctly capturing the symmetry transformations of data can lead to efficient models with strong generalization capabilities, though methods incorporating symmetries often require prior knowledge. While recent advancements have been made…

Due to the lack of large-scale text-3D correspondence data, recent text-to-3D generation works mainly rely on utilizing 2D diffusion models for synthesizing 3D data. Since diffusion-based methods typically require significant optimization…

We investigate inflection structure of a synthetic language using Latin as an example. We construct a bipartite graph in which one group of vertices correspond to dictionary headwords and the other group to inflected forms encountered in a…

This thesis presents a constraint-based morphological disambiguation approach that is applicable to languages with complex morphology--specifically agglutinative languages with productive inflectional and derivational morphological…

Question Generation is the task of automatically creating questions from textual input. In this work we present a new Attentional Encoder--Decoder Recurrent Neural Network model for automatic question generation. Our model incorporates…

Grouping has been commonly used in deep metric learning for computing diverse features. However, current methods are prone to overfitting and lack interpretability. In this work, we propose an improved and interpretable grouping method to…

Traffic flow forecasting has been regarded as a key problem of intelligent transport systems. In this work, we propose a hybrid multimodal deep learning method for short-term traffic flow forecasting, which can jointly and adaptively learn…

This research delves into the problem of interactive editing of human motion generation. Previous motion diffusion models lack explicit modeling of the word-level text-motion correspondence and good explainability, hence restricting their…

This work proposes an extensive analysis of the Transformer architecture in the Neural Machine Translation (NMT) setting. Focusing on the encoder-decoder attention mechanism, we prove that attention weights systematically make alignment…

Human language is a rich multimodal signal consisting of spoken words, facial expressions, body gestures, and vocal intonations. Learning representations for these spoken utterances is a complex research problem due to the presence of…

Different from the emotion recognition in individual utterances, we propose a multimodal learning framework using relation and dependencies among the utterances for conversational emotion analysis. The attention mechanism is applied to the…

Word segmentation, the problem of finding word boundaries in speech, is of interest for a range of tasks. Previous papers have suggested that for sequence-to-sequence models trained on tasks such as speech translation or speech recognition,…

Transformers have become the go-to architecture for language and vision tasks, yet their theoretical properties, especially memorization capacity, remain elusive. This paper investigates the memorization abilities of multi-head attention…

The flow-based generative model is a deep learning generative model, which obtains the ability to generate data by explicitly learning the data distribution. Theoretically its ability to restore data is stronger than other generative…

Sequence-to-sequence models with soft attention have been successfully applied to a wide variety of problems, but their decoding process incurs a quadratic time and space cost and is inapplicable to real-time sequence transduction. To…

Object-centric architectures usually apply a differentiable module to the entire feature map to decompose it into sets of entity representations called slots. Some of these methods structurally resemble clustering algorithms, where the…

Deep Implicit Functions (DIFs) have gained popularity in 3D computer vision due to their compactness and continuous representation capabilities. However, addressing dense correspondences and semantic relationships across DIF-encoded shapes…