Related papers: Insights into End-to-End Learning Scheme for Langu…
Face parsing is a basic task in face image analysis. It amounts to labeling each pixel with appropriate facial parts such as eyes and nose. In the paper, we present a interlinked convolutional neural network (iCNN) for solving this problem…
The field of speech recognition is in the midst of a paradigm shift: end-to-end neural networks are challenging the dominance of hidden Markov models as a core technology. Using an attention mechanism in a recurrent encoder-decoder…
The use of explicit object detectors as an intermediate step to image captioning - which used to constitute an essential stage in early work - is often bypassed in the currently dominant end-to-end approaches, where the language model is…
In many real-life tasks of application of supervised learning approaches, all the training data are not available at the same time. The examples are lifelong image classification or recognition of environmental objects during interaction of…
Large language models (LLMs) have been widely employed across various application domains, yet their black-box nature poses significant challenges to understanding how these models process input data internally to make predictions. In this…
Measuring the performance of text recognition and text line detection engines is an important step to objectively compare systems and their configuration. There exist well-established measures for both tasks separately. However, there is no…
Image compression is one of the most fundamental techniques and commonly used applications in the image and video processing field. Earlier methods built a well-designed pipeline, and efforts were made to improve all modules of the pipeline…
Continuous sign language recognition (SLR) is a challenging task that requires learning on both spatial and temporal dimensions of signing frame sequences. Most recent work accomplishes this by using CNN and RNN hybrid networks. However,…
In this work we present a novel end-to-end framework for tracking and classifying a robot's surroundings in complex, dynamic and only partially observable real-world environments. The approach deploys a recurrent neural network to filter an…
Continual learning (CL) aims to enable information systems to learn from a continuous data stream across time. However, it is difficult for existing deep learning architectures to learn a new task without largely forgetting previously…
Large-scale contrastive pre-training produces powerful Vision-and-Language Models (VLMs) capable of generating representations (embeddings) effective for a wide variety of visual and multimodal tasks. However, these pretrained embeddings…
End-to-end learning of recurrent neural networks (RNNs) is an attractive solution for dialog systems; however, current techniques are data-intensive and require thousands of dialogs to learn simple behaviors. We introduce Hybrid Code…
Current state-of-the-art systems for sequence labeling are typically based on the family of Recurrent Neural Networks (RNNs). However, the shallow connections between consecutive hidden states of RNNs and insufficient modeling of global…
In this paper, we address the problem of image captioning specifically for molecular translation where the result would be a predicted chemical notation in InChI format for a given molecular structure. Current approaches mainly follow…
Multiple instance learning (MIL) aims to learn the mapping between a bag of instances and the bag-level label. In this paper, we propose a new end-to-end graph neural network (GNN) based algorithm for MIL: we treat each bag as a graph and…
End-to-end neural machine translation has overtaken statistical machine translation in terms of translation quality for some language pairs, specially those with large amounts of parallel data. Besides this palpable improvement, neural…
Over many decades, researchers working in object recognition have longed for an end-to-end automated system that will simply accept 2D or 3D image or videos as inputs and output the labels of objects in the input data. Computer vision…
In this paper, we introduce a groundbreaking end-to-end (E2E) framework for decoding invasive brain signals, marking a significant advancement in the field of speech neuroprosthesis. Our methodology leverages the comprehensive reasoning…
End-to-end approaches for sequence tasks are becoming increasingly popular. Yet for complex sequence tasks, like speech translation, systems that cascade several models trained on sub-tasks have shown to be superior, suggesting that the…
The standard in LLM-based prediction is to use the final-layer representation as the input to a downstream predictor. However, intermediate layers may encode complementary task-relevant signals. Existing approaches therefore either search…