Related papers: Contextual information integration for stance dete…
In this paper we explore two ways of using context for object detection. The first model focusses on people and the objects they commonly interact with, such as fashion and sports accessories. The second model considers more general object…
Impressive milestones have been achieved in text matching by adopting a cross-attention mechanism to capture pertinent semantic connections between two sentence representations. However, regular cross-attention focuses on word-level links…
Feature disentanglement of the foreground target objects and the background surrounding context has not been yet fully accomplished. The lack of network interpretability prevents advancing for feature disentanglement and better…
Prior studies show that adopting the annotation diversity shaped by different backgrounds and life experiences and incorporating them into the model learning, i.e. multi-perspective approach, contribute to the development of more…
Stance detection, as the task of determining the viewpoint of a social media post towards a target as 'favor' or 'against', has been understudied in the challenging yet realistic scenario where there is limited labeled data for a certain…
Scene Text Recognition (STR) models have achieved high performance in recent years on benchmark datasets where text images are presented with minimal noise. Traditional STR recognition pipelines take a cropped image as sole input and…
Monocular depth estimation and semantic segmentation are two fundamental goals of scene understanding. Due to the advantages of task interaction, many works study the joint task learning algorithm. However, most existing methods fail to…
Stance detection classifies stance relations (namely, Favor, Against, or Neither) between comments and targets. Pretrained language models (PLMs) are widely used to mine the stance relation to improve the performance of stance detection…
The exponential rise of social media and digital news in the past decade has had the unfortunate consequence of escalating what the United Nations has called a global topic of concern: the growing prevalence of disinformation. Given the…
Many name tagging approaches use local contextual information with much success, but fail when the local context is ambiguous or limited. We present a new framework to improve name tagging by utilizing local, document-level, and…
We propose a new architecture for adapting a sentence-level sequence-to-sequence transformer by incorporating multiple pretrained document context signals and assess the impact on translation performance of (1) different pretraining…
Despite the great success of face recognition techniques, recognizing persons under unconstrained settings remains challenging. Issues like profile views, unfavorable lighting, and occlusions can cause substantial difficulties. Previous…
Vision systems that deploy Deep Neural Networks (DNNs) are known to be vulnerable to adversarial examples. Recent research has shown that checking the intrinsic consistencies in the input data is a promising way to detect adversarial…
Semantic segmentation is still a challenging task for parsing diverse contexts in different scenes, thus the fixed classifier might not be able to well address varying feature distributions during testing. Different from the mainstream…
Current face recognition systems typically operate via classification into known identities obtained from supervised identity annotations. There are two problems with this paradigm: (1) current systems are unable to benefit from often…
Text Spotting in the wild consists of detecting and recognizing text appearing in images (e.g. signboards, traffic signals or brands in clothing or objects). This is a challenging problem due to the complexity of the context where texts…
In this paper, we aim to extract commonsense knowledge to improve machine reading comprehension. We propose to represent relations implicitly by situating structured knowledge in a context instead of relying on a pre-defined set of…
Current deep learning methods for object recognition are purely data-driven and require a large number of training samples to achieve good results. Due to their sole dependence on image data, these methods tend to fail when confronted with…
Road obstacle detection is an important problem for vehicle driving safety. In this paper, we aim to obtain robust road obstacle detection based on spatio-temporal context modeling. Firstly, a data-driven spatial context model of the…
In-context learning (ICL) using large language models for tasks with many labels is challenging due to the limited context window, which makes it difficult to fit a sufficient number of examples in the prompt. In this paper, we use a…