中文
相关论文

相关论文: Behind the Machine's Gaze: Neural Networks with Bi…

200 篇论文

Automated Aesthetic Quality Assessment (AQA) treats images primarily as static pixel vectors, aligning predictions with human-rating scores largely through semantic perception. However, this paradigm diverges from human aesthetic cognition,…

计算机视觉与模式识别 · 计算机科学 2026-04-20 Liwen Yu , Chi Liu , Xiaotong Han , Congcong Zhu , Minghao Wang , Sheng Shen

Top-down visual attention mechanisms have been used extensively in image captioning and visual question answering (VQA) to enable deeper image understanding through fine-grained analysis and even multiple steps of reasoning. In this work,…

计算机视觉与模式识别 · 计算机科学 2018-03-15 Peter Anderson , Xiaodong He , Chris Buehler , Damien Teney , Mark Johnson , Stephen Gould , Lei Zhang

Explainability in artificial intelligence (XAI) remains a crucial aspect for fostering trust and understanding in machine learning models. Current visual explanation techniques, such as gradient-based or class-activation-based methods,…

计算机视觉与模式识别 · 计算机科学 2025-08-01 Mahadev Prasad Panda , Matteo Tiezzi , Martina Vilas , Gemma Roig , Bjoern M. Eskofier , Dario Zanca

Retinal image of surrounding objects varies tremendously due to the changes in position, size, pose, illumination condition, background context, occlusion, noise, and nonrigid deformations. But despite these huge variations, our visual…

计算机视觉与模式识别 · 计算机科学 2017-02-14 Saeed Reza Kheradpisheh , Mohammad Ganjtabesh , Timothée Masquelier

The prevalence of employing attention mechanisms has brought along concerns on the interpretability of attention distributions. Although it provides insights about how a model is operating, utilizing attention as the explanation of model…

计算机视觉与模式识别 · 计算机科学 2022-09-16 Tristan Gomez , Suiyi Ling , Thomas Fréour , Harold Mouchère

In recent years, channel attention mechanism has been widely investigated due to its great potential in improving the performance of deep convolutional neural networks (CNNs) in many vision tasks. However, in most of the existing methods,…

计算机视觉与模式识别 · 计算机科学 2022-06-02 Yue Zhao , Junzhou Chen , Zirui Zhang , Ronghui Zhang

Although deep convolutional networks have been widely studied for head and neck (HN) organs at risk (OAR) segmentation, their use for routine clinical treatment planning is limited by a lack of robustness to imaging artifacts, low soft…

计算机视觉与模式识别 · 计算机科学 2021-03-01 Harini Veeraraghavan , Jue Jiang , Sharif Elguindi , Sean L. Berry , Ifeanyirochukwu Onochie , Aditya Apte , Laura Cervino , Joseph O. Deasy

Scene graph generation is a sophisticated task because there is no specific recognition pattern (e.g., "looking at" and "near" have no conspicuous difference concerning vision, whereas "near" could occur between entities with different…

计算机视觉与模式识别 · 计算机科学 2022-03-18 Xiaoguang Chang , Teng Wang , Changyin Sun , Wenzhe Cai

Automatically generating a natural language description of an image has attracted interests recently both because of its importance in practical applications and because it connects two major artificial intelligence fields: computer vision…

计算机视觉与模式识别 · 计算机科学 2016-03-15 Quanzeng You , Hailin Jin , Zhaowen Wang , Chen Fang , Jiebo Luo

The eye fixation patterns of human observers are a fundamental indicator of the aspects of an image to which humans attend. Thus, manipulating fixation patterns to guide human attention is an exciting challenge in digital image processing.…

计算机视觉与模式识别 · 计算机科学 2017-12-19 Leon A. Gatys , Matthias Kümmerer , Thomas S. A. Wallis , Matthias Bethge

We propose a novel attention based deep learning architecture for visual question answering task (VQA). Given an image and an image related natural language question, VQA generates the natural language answer for the question. Generating…

计算机视觉与模式识别 · 计算机科学 2016-04-05 Kan Chen , Jiang Wang , Liang-Chieh Chen , Haoyuan Gao , Wei Xu , Ram Nevatia

Visual navigation for autonomous agents is a core task in the fields of computer vision and robotics. Learning-based methods, such as deep reinforcement learning, have the potential to outperform the classical solutions developed for this…

计算机视觉与模式识别 · 计算机科学 2021-03-23 Zachary Seymour , Kowshik Thopalli , Niluthpol Mithun , Han-Pang Chiu , Supun Samarasekera , Rakesh Kumar

Convolutional layers are an integral part of many deep neural network solutions in computer vision. Recent work shows that replacing the standard convolution operation with mechanisms based on self-attention leads to improved performance on…

计算机视觉与模式识别 · 计算机科学 2020-12-21 Souvik Kundu , Hesham Mostafa , Sharath Nittur Sridhar , Sairam Sundaresan

Biological systems leverage top-down feedback for visual processing, yet most artificial vision models succeed in image classification using purely feedforward or recurrent architectures, calling into question the functional significance of…

神经元与认知 · 定量生物学 2025-08-12 Antonino Greco , Marco D'Alessandro , Karl J. Friston , Giovanni Pezzulo , Markus Siegel

While exploring visual scenes, humans' scanpaths are driven by their underlying attention processes. Understanding visual scanpaths is essential for various applications. Traditional scanpath models predict the where and when of gaze shifts…

计算机视觉与模式识别 · 计算机科学 2024-08-07 Xianyu Chen , Ming Jiang , Qi Zhao

Recurrent neural networks with differentiable attention mechanisms have had success in generative and classification tasks. We show that the classification performance of such models can be enhanced by guiding a randomly initialized model…

机器学习 · 计算机科学 2017-12-18 Jack Lindsey

Vision-Language-Action (VLA) models improve action generation by conditioning policies on rich vision-language information. However, current auto-regressive policies are constrained by three bottlenecks: (1) architectural bias drives models…

机器人学 · 计算机科学 2026-03-31 Yichi Zhang , Weihao Yuan , Yizhuo Zhang , Xidong Zhang , Jia Wan

Visual search is a fundamental natural task for humans and other animals. We investigated the decision processes humans use in covert (single-fixation) search with briefly presented displays having well-separated potential target locations.…

神经元与认知 · 定量生物学 2025-04-16 Anqi Zhang , Wilson S. Geisler

Efficient attention deployment in visual search is limited by human visual memory, yet this limitation can be offset by exploiting the environment's structure. This paper introduces a computational cognitive model that simulates how the…

人机交互 · 计算机科学 2024-09-16 Saku Sourulahti , Christian P Janssen , Jussi PP Jokinen

We conduct large-scale studies on `human attention' in Visual Question Answering (VQA) to understand where humans choose to look to answer questions about images. We design and test multiple game-inspired novel attention-annotation…

机器学习 · 统计学 2016-06-20 Abhishek Das , Harsh Agrawal , C. Lawrence Zitnick , Devi Parikh , Dhruv Batra