Related papers: Augmented Transformers with Adaptive n-grams Embed…

Identifying objects in an image and their mutual relationships as a scene graph leads to a deep understanding of image content. Despite the recent advancement in deep learning, the detection and labeling of visual object relationships…

Models based on the transformer architecture, such as BERT, have marked a crucial step forward in the field of Natural Language Processing. Importantly, they allow the creation of word embeddings that capture important semantic information…

Large Language Models (LLMs) have demonstrated impressive capabilities in answering questions, but they lack domain-specific knowledge and are prone to hallucinations. Retrieval Augmented Generation (RAG) is one approach to address these…

Graph-structured scene descriptions can be efficiently used in generative models to control the composition of the generated image. Previous approaches are based on the combination of graph convolutional networks and adversarial methods for…

Recent advances in multilingual dependency parsing have brought the idea of a truly universal parser closer to reality. However, cross-language interference and restrained model capacity remain major obstacles. To address this, we propose a…

Image super-resolution generation aims to generate a high-resolution image from its low-resolution image. However, more complex neural networks bring high computational costs and memory storage. It is still an active area for offering the…

The representation learning on textual graph is to generate low-dimensional embeddings for the nodes based on the individual textual features and the neighbourhood information. Recent breakthroughs on pretrained language models and graph…

Constructing 4D language fields is crucial for embodied AI, augmented/virtual reality, and 4D scene understanding, as they provide enriched semantic representations of dynamic environments and enable open-vocabulary querying in complex…

Irregular scene text recognition has attracted much attention from the research community, mainly due to the complexity of shapes of text in natural scene. However, recent methods either rely on shape-sensitive modules such as bounding box…

Recent advancements in attention mechanisms have replaced recurrent neural networks and its variants for machine translation tasks. Transformer using attention mechanism solely achieved state-of-the-art results in sequence modeling. Neural…

Graph Anomaly Detection (GAD) aims to identify atypical graph entities, such as nodes, edges, or substructures, that deviate significantly from the majority. While existing text-rich approaches typically integrate structural context into…

In this paper, we introduce LDGen, a novel method for integrating large language models (LLMs) into existing text-to-image diffusion models while minimizing computational demands. Traditional text encoders, such as CLIP and T5, exhibit…

We propose gated language experts and curriculum training to enhance multilingual transformer transducer models without requiring language identification (LID) input from users during inference. Our method incorporates a gating mechanism…

Much theoretical work has described the ability of transformers to represent formal languages. However, linking theoretical results to empirical performance is not straightforward due to the complex interplay between the architecture, the…

Research on text-to-image generation (TTI) still predominantly focuses on the English language due to the lack of annotated image-caption data in other languages; in the long run, this might widen inequitable access to TTI technology. In…

Effectively encoding multi-scale contextual information is crucial for accurate semantic segmentation. Existing transformer-based segmentation models combine features across scales without any selection, where features on sub-optimal scales…

Inspired by the success of Deep Learning based approaches to English scene text recognition, we pose and benchmark scene text recognition for three Indic scripts - Devanagari, Telugu and Malayalam. Synthetic word images rendered from…

Although the Transformer translation model (Vaswani et al., 2017) has achieved state-of-the-art performance in a variety of translation tasks, how to use document-level context to deal with discourse phenomena problematic for Transformer…

A critical challenge to image-text retrieval is how to learn accurate correspondences between images and texts. Most existing methods mainly focus on coarse-grained correspondences based on co-occurrences of semantic objects, while failing…

Machine reading comprehension is a task to model relationship between passage and query. In terms of deep learning framework, most of state-of-the-art models simply concatenate word and character level representations, which has been shown…