Related papers: Interpretable Visual Understanding with Cognitive …

Alternatively inferring on the visual facts and commonsense is fundamental for an advanced VQA system. This ability requires models to go beyond the literal understanding of commonsense. The system should not just treat objects as the…

Generating consecutive descriptions for videos, i.e., Video Captioning, requires taking full advantage of visual representation along with the generation process. Existing video captioning methods focus on making an exploration of…

Recently, multi-modality scene perception tasks, e.g., image fusion and scene understanding, have attracted widespread attention for intelligent vision systems. However, early efforts always consider boosting a single task unilaterally and…

Multimodal sentiment analysis has a wide range of applications due to its information complementarity in multimodal interactions. Previous works focus more on investigating efficient joint representations, but they rarely consider the…

Cross-view image translation is challenging because it involves images with drastically different views and severe deformation. In this paper, we propose a novel approach named Multi-Channel Attention SelectionGAN (SelectionGAN) that makes…

Recently, Transformer-based methods have shown impressive performance in single image super-resolution (SISR) tasks due to the ability of global feature extraction. However, the capabilities of Transformers that need to incorporate…

Convolutional neural networks (CNN) are known to learn an image representation that captures concepts relevant to the task, but do so in an implicit way that hampers model interpretability. However, one could argue that such a…

Visual perception plays a pivotal role in enabling autonomous behavior, offering a cost-effective and efficient alternative to complex multi-sensor systems. However, robust segmentation remains a challenge in complex scenarios. To address…

Neural networks have greatly boosted performance in computer vision by learning powerful representations of input data. The drawback of end-to-end training for maximal overall performance are black-box models whose hidden representations…

Recently, large pretrained language models have achieved compelling performance on commonsense benchmarks. Nevertheless, it is unclear what commonsense knowledge the models learn and whether they solely exploit spurious patterns. Feature…

Classifying images with an interpretable decision-making process is a long-standing problem in computer vision. In recent years, Prototypical Part Networks has gained traction as an approach for self-explainable neural networks, due to…

Artificial agents today can answer factual questions. But they fall short on questions that require common sense reasoning. Perhaps this is because most existing common sense databases rely on text to learn and represent knowledge. But much…

This paper presents a novel concept learning framework for enhancing model interpretability and performance in visual classification tasks. Our approach appends an unsupervised explanation generator to the primary classifier network and…

Deep learning models have achieved strong performance in medical image analysis, but their internal decision processes remain difficult to interpret. Concept Bottleneck Models (CBMs) partially address this limitation by structuring…

Infrared and visible image fusion (IVIF) is a fundamental task in multi-modal perception that aims to integrate complementary structural and textural cues from different spectral domains. In this paper, we propose FusionNet, a novel…

Commonsense reasoning aims to empower machines with the human ability to make presumptions about ordinary situations in our daily life. In this paper, we propose a textual inference framework for answering commonsense questions, which…

Visual commonsense reasoning task aims at leading the research field into solving cognition-level reasoning with the ability of predicting correct answers and meanwhile providing convincing reasoning paths, resulting in three sub-tasks…

Capsule Networks, as alternatives to Convolutional Neural Networks, have been proposed to recognize objects from images. The current literature demonstrates many advantages of CapsNets over CNNs. However, how to create explanations for…

A graph neural network (GNN) for image understanding based on multiple cues is proposed in this paper. Compared to traditional feature and decision fusion approaches that neglect the fact that features can interact and exchange information,…

This paper proposes a method to modify traditional convolutional neural networks (CNNs) into interpretable CNNs, in order to clarify knowledge representations in high conv-layers of CNNs. In an interpretable CNN, each filter in a high…