The growing interest in generating recipes from food images has drawn substantial research attention in recent years. Existing works for recipe generation primarily utilize a two-stage training method - first predicti...
详细信息
作者：
Xu, ChunmeiJia, YuanqiChen, YoujiaHuang, WeiSoutheast University
National Mobile Communications Research Laboratory School of Information Science and Engineering Nanjing210096 China Southeast University
School of Information Science and Engineering Nanjing210096 China Fuzhou University
Fujian Key Lab for Intelligent Processing and Wireless Transmission of Media Information College of Physics and Information Engineering Fuzhou350108 China Hefei University of Technology
School of Computer Science and Information Engineering Hefei230601 China
Cell-free networks and reconfigurable intelligent surfaces (RIS) are two promising techniques for future wireless communications. The integration of RIS into cell-free networks, termed RIS-aided cell-free networks, of...
详细信息
Privacy-preserving image generation is particularly crucial in fields like healthcare, where data are both sensitive and limited. However, effective privacy preservation often compromises the visual quality and utilit...
详细信息
Knowledge graphs (KGs) are extensively utilized in numerous applications, including question-answering systems and recommender systems. However, knowledge graphs are often constructed through web crawling or crowdsour...
详细信息
Accurately recognizing gait phases, by applying proper instrumentation and measurement, is significant in walking rehabilitation training for patients with impaired mobility. In this study, seven phases of complete st...
详细信息
The growing interest in generating recipes from food images has drawn substantial research attention in recent years. Existing works for recipe generation primarily utilize a two-stage training method—first predictin...
详细信息
ISBN:
(数字)9798331510831
ISBN:
(纸本)9798331510848
The growing interest in generating recipes from food images has drawn substantial research attention in recent years. Existing works for recipe generation primarily utilize a two-stage training method—first predicting ingredients from a food image and then generating instructions from both the image and ingredients. Large Multi-modal Models (LMMs), which have achieved notable success across a variety of vision and language tasks, shed light on generating both ingredients and instructions directly from images. Nevertheless, LMMs still face the common issue of hallu-cinations during recipe generation, leading to suboptimal performance. To tackle this issue, we propose a retrieval augmented large multimodal model for recipe generation. We first introduce Stochastic Diversified Retrieval Augmentation (SDRA) to retrieve recipes semantically related to the image from an existing datastore as a supplement, integrating them into the prompt to add diverse and rich context to the input image. Additionally, Self-Consistency Ensemble Voting mechanism is proposed to determine the most confident prediction recipes as the final output. It calculates the consistency among generated recipe candidates, which use different retrieval recipes as context for generation. Extensive experiments validate the effectiveness of our proposed method, which demonstrates state-of-the-art (SOTA) performance in recipe generation on the Recipe1M dataset.
Event-level Financial Sentiment Analysis (EFSA) aims to extract all the quintuples containing five sentiment elements from a given financial news text, which has gained prominence as an emerging domain recently. ...
详细信息
Accurately predicting conversion rate (CVR) is paramount in online advertising. However, traditional models may face problems such as delayed feedback, where there is a delay of an indeterminate amount of time be...
详细信息
Graph Neural Networks (GNNs) have demonstrated impressive success across diverse fields when data satisfies in-distribution (ID) assumption. Nevertheless, GNN performance significantly declines in cases of distributio...
详细信息
ISBN:
(数字)9798350368741
ISBN:
(纸本)9798350368758
Graph Neural Networks (GNNs) have demonstrated impressive success across diverse fields when data satisfies in-distribution (ID) assumption. Nevertheless, GNN performance significantly declines in cases of distribution shifts between training and testing graph data. This degradation primarily stems from spurious correlations between irrelevant domain information and target labels in out-of-distribution (OOD) scenarios. Thus, maximizing the utilization of domain information becomes imperative. In light of this, we propose a novel approach named Domain-aware Node Representation Learning (DNRL), comprehensively incorporates domain information to bolster generalization capability. Specifically, DNRL selectively interpolates nodes with the same label but different domains, extending training data into unseen domains and alleviating the effects caused by domain-related spurious correlations. Futhermore, by introducing a domain-aware contrastive learning strategy, our method implicitly decouples domain information from node information to learn domain-independent node representations. Extensive experiments on graph out-of-distribution benchmarks demonstrate that DNRL can achieve effective OOD generalization performance across diverse domains.
Introduction of database Olfaction is one of the oldest chemosensory systems in chordates, playing crucial roles in their foraging, predator evasion, social communication, mating and parental care (Guo et al., 2023; L...
Introduction of database Olfaction is one of the oldest chemosensory systems in chordates, playing crucial roles in their foraging, predator evasion, social communication, mating and parental care (Guo et al., 2023; Li and Liberles, 2015; Liberles,2014). The initial step of olfaction is the binding and activation of olfactory receptors (ORs) by odorants in a combinatorial way (Malnic et al., 1999).
暂无评论