相关论文: Transformer-based Cross-Modal Recipe Embeddings wi…

For many computer vision applications such as image captioning, visual question answering, and person search, learning discriminative feature representations at both image and text level is an essential yet challenging problem. Its…

In human learning, an effective skill in improving learning outcomes is learning by teaching: a learner deepens his/her understanding of a topic by teaching this topic to others. In this paper, we aim to borrow this teaching-driven learning…

Knowledge retrieval with multi-modal queries plays a crucial role in supporting knowledge-intensive multi-modal applications. However, existing methods face challenges in terms of their effectiveness and training efficiency, especially when…

Unsupervised representation learning algorithms such as word2vec and ELMo improve the accuracy of many supervised NLP models, mainly because they can take advantage of large amounts of unlabeled text. However, the supervised models only…

The adoption of Transformer-based models in natural language processing (NLP) has led to great success using a massive number of parameters. However, due to deployment constraints in edge devices, there has been a rising interest in the…

In recent years, large pre-trained Transformer-based language models have led to dramatic improvements in many natural language understanding tasks. To train these models with increasing sizes, many neural network practitioners attempt to…

Significant work has been conducted in the domain of food computing, yet these studies typically focus on single tasks such as t2t (instruction generation from food titles and ingredients), i2t (recipe generation from food images), or t2i…

When applying pre-trained large language models (LLMs) to address anomaly detection tasks, the multivariate time series (MTS) modality of anomaly detection does not align with the text modality of LLMs. Existing methods simply transform the…

The recently developed vision transformer (ViT) has achieved promising results on image classification compared to convolutional neural networks. Inspired by this, in this paper, we study how to learn multi-scale feature representations in…

Supervised learning models are typically trained on a single dataset and the performance of these models rely heavily on the size of the dataset, i.e., amount of data available with the ground truth. Learning algorithms try to generalize…

Multimodal Large Language Models (MLLMs) have demonstrated strong cross-modal reasoning capabilities, yet their potential for vision-only tasks remains underexplored. We investigate MLLMs as training-free similarity estimators for…

Meta-learning has been proposed as a framework to address the challenging few-shot learning setting. The key idea is to leverage a large number of similar few-shot tasks in order to learn how to adapt a base-learner to a new task for which…

Learning dynamic user preference has become an increasingly important component for many online platforms (e.g., video-sharing sites, e-commerce systems) to make sequential recommendations. Previous works have made many efforts to model…

Pre-trained vision-language models have notably accelerated progress of open-world concept recognition. Their impressive zero-shot ability has recently been transferred to multi-label image classification via prompt tuning, enabling to…

We present GTE, a general-purpose text embedding model trained with multi-stage contrastive learning. In line with recent advancements in unifying various NLP tasks into a single format, we train a unified text embedding model by employing…

Understanding the mechanisms underlying deep neural networks remains a fundamental challenge in machine learning and computer vision. One promising, yet only preliminarily explored approach, is feature inversion, which attempts to…

In creating sentence embeddings for Natural Language Inference (NLI) tasks, using transformer-based models like BERT leads to high accuracy, but require hundreds of millions of parameters. These models take in sentences as a sequence of…

Visual Transformers (VTs) are emerging as an architectural paradigm alternative to Convolutional networks (CNNs). Differently from CNNs, VTs can capture global relations between image elements and they potentially have a larger…

Unsupervised neural machine translation (UNMT) has recently achieved remarkable results with only large monolingual corpora in each language. However, the uncertainty of associating target with source sentences makes UNMT theoretically an…

Recent works have highlighted the strength of the Transformer architecture on sequence tasks while, at the same time, neural architecture search (NAS) has begun to outperform human-designed models. Our goal is to apply NAS to search for a…