Revisiting the domain shift and sample uncertainty in multi-source active domain transfer
Abstract Active Domain Adaptation (ADA) aims to maximally boost model adaptation in a
new target domain by actively selecting a limited number of target data to annotate. This …
new target domain by actively selecting a limited number of target data to annotate. This …
Intelligent model update strategy for sequential recommendation
Modern online platforms are increasingly employing recommendation systems to address
information overload and improve user engagement. There is an evolving paradigm in this …
information overload and improve user engagement. There is an evolving paradigm in this …
Learning in imperfect environment: Multi-label classification with long-tailed distribution and partial labels
Conventional multi-label classification (MLC) methods assume that all samples are fully
labeled and identically distributed. Unfortunately, this assumption is unrealistic in large …
labeled and identically distributed. Unfortunately, this assumption is unrealistic in large …
Unsupervised domain adaptation for video object grounding with cascaded debiasing learning
This paper addresses the Unsupervised Domain Adaptation (UDA) for the dense frame
prediction task-Video Object Grounding (VOG). This investigation springs from the …
prediction task-Video Object Grounding (VOG). This investigation springs from the …
Quantitatively measuring and contrastively exploring heterogeneity for domain generalization
Domain generalization (DG) is a prevalent problem in real-world applications, which aims to
train well-generalized models for unseen target domains by utilizing several source …
train well-generalized models for unseen target domains by utilizing several source …
ART: rule bAsed futuRe-inference deducTion
M Li, T Zhao, B Jionghao, B He, J Miao… - Proceedings of the …, 2023 - aclanthology.org
Deductive reasoning is a crucial cognitive ability of humanity, allowing us to derive valid
conclusions from premises and observations. However, existing works mainly focus on …
conclusions from premises and observations. However, existing works mainly focus on …
Evaluating Unsupervised Argument Aligners via Generation of Conclusions of Structured Scientific Abstracts
Scientific abstracts provide a concise summary of research findings, making them a valuable
resource for extracting scientific arguments. In this study, we assess various unsupervised …
resource for extracting scientific arguments. In this study, we assess various unsupervised …
KN-VLM: KNowledge-guided Vision-and-Language Model for Visual Abductive Reasoning
Visual abductive reasoning strives to deduce the most suitable hypothesis that effectively
explains the underlying visual context, garnering considerable attention in the academic …
explains the underlying visual context, garnering considerable attention in the academic …
Cross-modal Observation Hypothesis Inference
M Li, K Han, J Xu, Y Li, T Wu, Z Zhao, J Miao… - ACM Multimedia … - openreview.net
Hypothesis inference, a sophisticated cognitive process that allows humans to construct
plausible explanations for incomplete observations, is paramount to our ability to make …
plausible explanations for incomplete observations, is paramount to our ability to make …
Probabilistic Distillation Transformer: Modelling Uncertainties for Visual Abductive Reasoning
Visual abduction reasoning aims to find the most plausible explanation for incomplete
observations, and suffers from inherent uncertainties and ambiguities, which mainly stem …
observations, and suffers from inherent uncertainties and ambiguities, which mainly stem …