Related papers: Neural CRF transducers for sequence labeling
Ray tracing is widely employed to model the propagation of radio-frequency (RF) signal in complex environment. The modelling performance greatly depends on how accurately the target scene can be depicted, including the scene geometry and…
We propose X-NeRF, a novel method to learn a Cross-Spectral scene representation given images captured from cameras with different light spectrum sensitivity, based on the Neural Radiance Fields formulation. X-NeRF optimizes camera poses…
The phrase grounding task aims to ground each entity mention in a given caption of an image to a corresponding region in that image. Although there are clear dependencies between how different mentions of the same caption should be…
In recent years, the field of implicit neural representation has progressed significantly. Models such as neural radiance fields (NeRF), which uses relatively small neural networks, can represent high-quality scenes and achieve…
Recent works have shown that exploiting multi-scale representations deeply learned via convolutional neural networks (CNN) is of tremendous importance for accurate contour detection. This paper presents a novel approach for predicting…
Cluster random fields (CRFs) play a crucial role in the study of extremes of stationary regularly varying random fields (RFs). In particular, they appear in the Rosi\'nski representation of max-stable and $\alpha$-stable RFs. In this…
Neural fields, a category of neural networks trained to represent high-frequency signals, have gained significant attention in recent years due to their impressive performance in modeling complex 3D data, such as signed distance (SDFs) or…
Towards a safe and comfortable driving, road scene segmentation is a rudimentary problem in camera-based advance driver assistance systems (ADAS). Despite of the great achievement of Convolutional Neural Networks (CNN) for semantic…
Recent work in Dialogue Act (DA) classification approaches the task as a sequence labeling problem, using neural network models coupled with a Conditional Random Field (CRF) as the last layer. CRF models the conditional probability of the…
We propose a neural architecture with the main characteristics of the most successful neural models of the last years: bidirectional RNNs, encoder-decoder, and the Transformer model. Evaluation on three sequence labelling tasks yields…
Low-resource named entity recognition is still an open problem in NLP. Most state-of-the-art systems require tens of thousands of annotated sentences in order to obtain high performance. However, for most of the world's languages, it is…
Labeled sequence transduction is a task of transforming one sequence into another sequence that satisfies desiderata specified by a set of labels. In this paper we propose multi-space variational encoder-decoders, a new model for labeled…
We present LS-CRF, a new method for very efficient large-scale training of Conditional Random Fields (CRFs). It is inspired by existing closed-form expressions for the maximum likelihood parameters of a generative graphical model with tree…
Convolutional neural network (CNN) models have demonstrated great success in various computer vision tasks including image classification and object detection. However, some equally important tasks such as visual tracking remain relatively…
Adopting Neural Radiance Fields (NeRF) to long-duration dynamic sequences has been challenging. Existing methods struggle to balance between quality and storage size and encounter difficulties with complex scene changes such as topological…
Exploiting multiple modalities for semantic scene parsing has been shown to improve accuracy over the singlemodality scenario. However multimodal datasets often suffer from problems such as data misalignment and label inconsistencies, where…
Popular solutions to Named Entity Recognition (NER) include conditional random fields, sequence-to-sequence models, or utilizing the question-answering framework. However, they are not suitable for nested and overlapping spans with large…
Articulated objects pose a unique challenge for robotic perception and manipulation. Their increased number of degrees-of-freedom makes tasks such as localization computationally difficult, while also making the process of real-world…
In this paper we proposed an ordered patch based method using Conditional Random Field (CRF) in order to encode local properties and their spatial relationship in images to address texture classification, face recognition, and scene…
Models based on Convolutional Neural Networks (CNNs) have been proven very successful for semantic segmentation and object parsing that yield hierarchies of features. Our key insight is to build convolutional networks that take input of…