Related papers: Semantic Fusion with Fuzzy-Membership Features for…
Current multi-modal image fusion methods typically rely on task-specific models, leading to high training costs and limited scalability. While generative methods provide a unified modeling perspective, they often suffer from slow inference…
Extending pre-trained text Large Language Models (LLMs)'s speech understanding or generation abilities by introducing various effective speech tokens has attracted great attention in the speech community. However, building a unified speech…
A speech emotion recognition algorithm based on multi-feature and Multi-lingual fusion is proposed in order to resolve low recognition accuracy caused by lack of large speech dataset and low robustness of acoustic features in the…
Despite the success of conventional collaborative filtering (CF) approaches for recommendation systems, they exhibit limitations in leveraging semantic knowledge within the textual attributes of users and items. Recent focus on the…
This paper aims to bring a new lightweight yet powerful solution for the task of Emotion Recognition and Sentiment Analysis. Our motivation is to propose two architectures based on Transformers and modulation that combine the linguistic and…
The large-scale pretrained model CLIP, trained on 400 million image-text pairs, offers a promising paradigm for tackling vision tasks, albeit at the image level. Later works, such as DenseCLIP and LSeg, extend this paradigm to dense…
When autonomous agents observe different domains of a shared environment, each signal they exchange mixes relevant and irrelevant dimensions. No existing mechanism lets the receiver evaluate which dimensions to absorb. We introduce…
This study investigates a hybrid method for text classification that integrates deep feature extraction from large language models, multi-scale fusion through feature pyramids, and structured modeling with graph neural networks to enhance…
Marrying topic models and language models exposes language understanding to a broader source of document-level context beyond sentences via topics. While introducing topical semantics in language models, existing approaches incorporate…
Word similarity has many applications to social science and cultural analytics tasks like measuring meaning change over time and making sense of contested terms. Yet traditional similarity methods based on cosine similarity between word…
Using a vocabulary that is shared across languages is common practice in Multilingual Neural Machine Translation (MNMT). In addition to its simple design, shared tokens play an important role in positive knowledge transfer, assuming that…
Robust semantic perception for autonomous vehicles relies on effectively combining multiple sensors with complementary strengths and weaknesses. State-of-the-art sensor fusion approaches to semantic perception often treat sensor data…
We present an effective method for fusing visual-and-language representations for several question answering tasks including visual question answering and visual entailment. In contrast to prior works that concatenate unimodal…
In traditional ELM and its improved versions suffer from the problems of outliers or noises due to overfitting and imbalance due to distribution. We propose a novel hybrid adaptive fuzzy ELM(HA-FELM), which introduces a fuzzy membership…
Topic modeling is admittedly a convenient way to monitor markets trend. Conventionally, Latent Dirichlet Allocation, LDA, is considered a must-do model to gain this type of information. By given the merit of deducing keyword with token…
The main objective of this paper is to develop a new semantic Network structure, based on the fuzzy sets theory, used in Artificial Intelligent system in order to provide effective on-line assistance to users of new technological systems.…
Semantic associations such as the link between "bird" and "flew" are foundational for language modeling as they enable models to go beyond memorization and instead generalize and generate coherent text. Understanding how these associations…
Models for semantic segmentation require a large amount of hand-labeled training data which is costly and time-consuming to produce. For this purpose, we present a label fusion framework that is capable of improving semantic pixel labels of…
We present a novel metric for the evaluation of the morphological plausibility of subword segmentation. Unlike the typically used morpheme boundary or retrieval F-score, which requires gold segmentation data that is either unavailable or of…
Language models typically tokenize text into subwords, using a deterministic, hand-engineered heuristic of combining characters into longer surface-level strings such as 'ing' or whole words. Recent literature has repeatedly shown the…