HAL: Improved Text-Image Matching by Mitigating Visual Semantic Hubs
نویسندگان
چکیده
منابع مشابه
An Improved Semantic Schema Matching Approach
Schema matching is a critical step in many applications, such as data warehouse loading, Online Analytical Process (OLAP), Data mining, semantic web [2] and schema integration. This task is defined for finding the semantic correspondences between elements of two schemas. Recently, schema matching has found considerable interest in both research and practice. In this paper, we present a new impr...
متن کاملan improved semantic schema matching approach
schema matching is a critical step in many applications, such as data warehouse loading, online analytical process (olap), data mining, semantic web [2] and schema integration. this task is defined for finding the semantic correspondences between elements of two schemas. recently, schema matching has found considerable interest in both research and practice. in this paper, we present a new impr...
متن کاملText Matching as Image Recognition
Matching two texts is a fundamental problem in many natural language processing tasks. An effective way is to extract meaningful matching patterns from words, phrases, and sentences to produce the matching score. Inspired by the success of convolutional neural network in image recognition, where neurons can capture many complicated patterns based on the extracted elementary visual patterns such...
متن کاملDeep Fusion LSTMs for Text Semantic Matching
Recently, there is rising interest in modelling the interactions of text pair with deep neural networks. In this paper, we propose a model of deep fusion LSTMs (DF-LSTMs) to model the strong interaction of text pair in a recursive matching way. Specifically, DF-LSTMs consist of two interdependent LSTMs, each of which models a sequence under the influence of another. We also use external memory ...
متن کاملVSE++: Improved Visual-Semantic Embeddings
We present a new technique for learning visual-semantic embeddings for crossmodal retrieval. Inspired by the use of hard negatives in structured prediction, and ranking loss functions used in retrieval, we introduce a simple change to common loss functions used to learn multi-modal embeddings. That, combined with fine-tuning and the use of augmented data, yields significant gains in retrieval p...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Proceedings of the AAAI Conference on Artificial Intelligence
سال: 2020
ISSN: 2374-3468,2159-5399
DOI: 10.1609/aaai.v34i07.6823