相关论文: Coarse-grain Fine-grain Coattention Network for Mu…

Fine-grained image-text alignment is a pivotal challenge in multimodal learning, underpinning key applications such as visual question answering, image captioning, and vision-language navigation. Unlike global alignment, fine-grained…

Traditional models for question answering optimize using cross entropy loss, which encourages exact answers at the cost of penalizing nearby or overlapping answers that are sometimes equally accurate. We propose a mixed objective that…

Multi-relation question answering (QA) is a challenging task, where given questions usually require long reasoning chains in KGs that consist of multiple relations. Recently, methods with explicit multi-step reasoning over KGs have been…

Graph neural networks (GNNs) excel in graph representation learning by integrating graph structure and node features. Existing GNNs, unfortunately, fail to account for the uncertainty of class probabilities that vary with the depth of the…

Deep neural network based question answering (QA) models are neither robust nor explainable in many cases. For example, a multiple-choice QA model, tested without any input of question, is surprisingly "capable" to predict the most of…

Human action video recognition has recently attracted more attention in applications such as video security and sports posture correction. Popular solutions, including graph convolutional networks (GCNs) that model the human skeleton as a…

Large language models (LLMs) need reliable test-time control of hallucinations. Existing conformal methods for LLMs typically provide only \emph{marginal} guarantees and rely on a single global threshold, which can under-cover hard prompts,…

In recent years, Multimodal Large Language Models (MLLMs) have achieved remarkable progress on a wide range of multimodal benchmarks. Despite these advances, most existing benchmarks mainly focus on single-image or multi-image…

Co-saliency detection aims to detect common salient objects from a group of relevant images. Some attempts have been made with the Fully Convolutional Network (FCN) framework and achieve satisfactory detection results. However, due to…

As artificial intelligence (AI) systems are increasingly used in ethically sensitive domains such as education, healthcare, and transportation, balancing accuracy and interpretability has become a central concern. Coarse ethics (CE)…

We present a novel deep convolutional neural network (DCNN) system for fine-grained image classification, called a mixture of DCNNs (MixDCNN). The fine-grained image classification problem is characterised by large intra-class variations…

Fact verification (FV) is a challenging task which requires to retrieve relevant evidence from plain text and use the evidence to verify given claims. Many claims require to simultaneously integrate and reason over several pieces of…

Computer vision is difficult, partly because the desired mathematical function connecting input and output data is often complex, fuzzy and thus hard to learn. Coarse-to-fine (C2F) learning is a promising direction, but it remains unclear…

Grounded text generation, encompassing tasks such as long-form question-answering and summarization, necessitates both content selection and content consolidation. Current end-to-end methods are difficult to control and interpret due to…

Existing Collaborative Filtering (CF) methods are mostly designed based on the idea of matching, i.e., by learning user and item embeddings from data using shallow or deep models, they try to capture the associative relevance patterns in…

We propose an inference procedure for deep convolutional neural networks (CNNs) when partial evidence is available. Our method consists of a general feedback-based propagation approach (feedback-prop) that boosts the prediction accuracy for…

This work introduces an original and practical paradigm for narrative comprehension, stemming from the characteristics that individual passages within narratives tend to be more cohesively related than isolated. Complementary to the common…

The integration of multi-document pre-training objectives into language models has resulted in remarkable improvements in multi-document downstream tasks. In this work, we propose extending this idea by pre-training a generic multi-document…

A well-designed fine-grained categorization system usually has three contradictory requirements: accuracy (the ability to identify objects among subordinate categories); interpretability (the ability to provide human-understandable…

Fact verification is a challenging task that requires simultaneously reasoning and aggregating over multiple retrieved pieces of evidence to evaluate the truthfulness of a claim. Existing approaches typically (i) explore the semantic…