Related papers: CVSNet: A Computer Implementation for Central Visu…

Modern computer vision is all about the possession of powerful image representations. Deeper and deeper convolutional neural networks have been built using larger and larger datasets and are made publicly available. A large swath of…

Given a question-image input, the Visual Commonsense Reasoning (VCR) model can predict an answer with the corresponding rationale, which requires inference ability from the real world. The VCR task, which calls for exploiting the…

Since the emergence of deep learning, the computer vision field has flourished with models improving at a rapid pace on more and more complex tasks. We distinguish three main ways to improve a computer vision model: (1) improving the data…

Neural networks have enabled state-of-the-art approaches to achieve incredible results on computer vision tasks such as object detection. However, such success greatly relies on costly computation resources, which hinders people with cheap…

Despite the success of convolution- and attention-based models in vision tasks, their rigid receptive fields and complex architectures limit their ability to model irregular spatial patterns and hinder interpretability, therefore posing…

Convolutional Neural Networks (CNNs) have become the state of the art method for image classification in the last ten years. Despite the fact that they achieve superhuman classification accuracy on many popular datasets, they often perform…

Visual Commonsense Reasoning (VCR) predicts an answer with corresponding rationale, given a question-image input. VCR is a recently introduced visual scene understanding task with a wide range of applications, including visual question…

Vision-brain understanding aims to extract semantic information about brain signals from human perceptions. Existing deep learning methods for vision-brain understanding are usually introduced in a traditional learning paradigm missing the…

Convolutional neural networks have enabled major progresses in addressing pixel-level prediction tasks such as semantic segmentation, depth estimation, surface normal prediction and so on, benefiting from their powerful capabilities in…

Conventional neural network models (CNN), loosely inspired by the primate visual system, have been shown to predict neural responses in the visual cortex. However, the relationship between CNNs and the visual system is incomplete due to…

Features play a crucial role in computer vision. Initially designed to detect salient elements by means of handcrafted algorithms, features are now often learned by different layers in Convolutional Neural Networks (CNNs). This paper…

Visual saliency is a fundamental problem in both cognitive and computational sciences, including computer vision. In this CVPR 2015 paper, we discover that a high-quality visual saliency model can be trained with multiscale features…

A split-transform-merge strategy has been broadly used as an architectural constraint in convolutional neural networks for visual recognition tasks. It approximates sparsely connected networks by explicitly defining multiple branches to…

Deep learning architectures are showing great promise in various computer vision domains including image classification, object detection, event detection and action recognition. In this study, we investigate various aspects of…

Despite advancements in artificial intelligence, object recognition models still lag behind in emulating visual information processing in human brains. Recent studies have highlighted the potential of using neural data to mimic brain…

Recently, very deep convolutional neural networks (CNNs) have been attracting considerable attention in image restoration. However, as the depth grows, the long-term dependency problem is rarely realized for these very deep models, which…

The widespread use of deep neural networks has achieved substantial success in many tasks. However, there still exists a huge gap between the operating mechanism of deep learning models and human-understandable decision making, so that…

Visual understanding requires comprehending complex visual relations between objects within a scene. Here, we seek to characterize the computational demands for abstract visual reasoning. We do this by systematically assessing the ability…

Convolutional neural networks (CNNs) have recently emerged as promising models of the ventral visual stream, despite their lack of biological specificity. While current state-of-the-art models of the primary visual cortex (V1) have surfaced…

Existing methods for visual reasoning attempt to directly map inputs to outputs using black-box architectures without explicitly modeling the underlying reasoning processes. As a result, these black-box models often learn to exploit biases…