中文
相关论文

相关论文: Voluntary control of semantic neural representatio…

200 篇论文

How does visual information included in training affect language processing in audio- and text-based deep learning models? We explore how such visual grounding affects model-internal representations of words, and find substantially…

计算与语言 · 计算机科学 2025-09-22 Adrian Sauter , Willem Zuidema , Marianne de Heer Kloots

Robotic research is often built on approaches that are motivated by insights from self-examination of how we interface with the world. However, given current theories about human cognition and sensory processing, it is reasonable to assume…

机器人学 · 计算机科学 2019-05-15 Martin Hjelm

This study investigates the cognitive plausibility of a pretrained multimodal model, CLIP, in recognizing emotions evoked by abstract visual art. We employ a dataset comprising images with associated emotion labels and textual rationales of…

计算机视觉与模式识别 · 计算机科学 2024-05-13 Hanna-Sophia Widhoelzl , Ece Takmaz

While deep learning surpasses human-level performance in narrow and specific vision tasks, it is fragile and over-confident in classification. For example, minor transformations in perspective, illumination, or object deformation in the…

计算机视觉与模式识别 · 计算机科学 2022-03-15 Maryam Daniali , Edward Kim

Our daily perceptual experience is driven by different neural mechanisms that yield multisensory interaction as the interplay between exogenous stimuli and endogenous expectations. While the interaction of multisensory cues according to…

神经元与认知 · 定量生物学 2018-07-17 German I. Parisi , Jonathan Tong , Pablo Barros , Brigitte Röder , Stefan Wermter

Latent visual reasoning aims to mimic human's imagination process by meditating through hidden states of Multimodal Large Language Models. While recognized as a promising paradigm for visual reasoning, the underlying mechanisms driving its…

计算与语言 · 计算机科学 2026-02-27 You Li , Chi Chen , Yanghao Li , Fanhu Zeng , Kaiyu Huang , Jinan Xu , Maosong Sun

Museums increasingly rely on digital content to support visitors' understanding of artworks, yet little is known about how these formats shape the emotional engagement that underlies meaningful art experiences. This research presents an…

信号处理 · 电气工程与系统科学 2026-02-03 Chen Feng , Sébastien Lugan , Karine Lasaracina , Midori Sugaya , Benoît Macq

Despite participants engaging in unimodal stimuli, such as watching images or silent videos, recent work has demonstrated that multi-modal Transformer models can predict visual brain activity impressively well, even with incongruent…

神经元与认知 · 定量生物学 2025-05-27 Subba Reddy Oota , Khushbu Pahwa , Mounika Marreddy , Maneesh Singh , Manish Gupta , Bapi S. Raju

Recent advances in machine learning, particularly deep learning, have enabled autonomous systems to perceive and comprehend objects and their environments in a perceptual subsymbolic manner. These systems can now perform object detection,…

人工智能 · 计算机科学 2023-09-13 Amr Gomaa , Michael Feld

Currently virtual reality (VR) usage in training processes is increasing due to their usefulness in the learning processes based on visual information empowered. The information in virtual environments is perceived by sight, sound and…

神经元与认知 · 定量生物学 2019-08-15 Cesar R. Salas Guerra

Composed image retrieval which combines a reference image and a text modifier to identify the desired target image is a challenging task, and requires the model to comprehend both vision and language modalities and their interactions.…

计算机视觉与模式识别 · 计算机科学 2023-10-03 Shu Zhao , Huijuan Xu

Although it seems counter-intuitive, categorical colours do not exist as external physical entities but are very much the product of our brains. Our cortical machinery segments the world and associate objects to specific colour terms, which…

计算机视觉与模式识别 · 计算机科学 2017-09-20 Arash Akbarinia , C. Alejandro Parraga

There is physiological evidence that our ability to interpret human pose and action from 2D visual imagery (binocular or monocular) engages the circuitry of the motor cortices as well as the visual areas of the brain. This implies that the…

计算机视觉与模式识别 · 计算机科学 2015-03-31 David W. Arathorn

Many applications require an understanding of an image that goes beyond the simple detection and classification of its objects. In particular, a great deal of semantic information is carried in the relationships between objects. We have…

人工智能 · 计算机科学 2018-08-28 Stephan Baier , Yunpu Ma , Volker Tresp

A crucial capability of real-world intelligent agents is their ability to plan a sequence of actions to achieve their goals in the visual world. In this work, we address the problem of visual semantic planning: the task of predicting a…

计算机视觉与模式识别 · 计算机科学 2017-08-17 Yuke Zhu , Daniel Gordon , Eric Kolve , Dieter Fox , Li Fei-Fei , Abhinav Gupta , Roozbeh Mottaghi , Ali Farhadi

Unveiling visual semantics from neural signals such as EEG, MEG, and fMRI remains a fundamental challenge due to subject variability and the entangled nature of visual features. Existing approaches primarily align neural activity directly…

计算机视觉与模式识别 · 计算机科学 2025-11-07 Zehui Feng , Chenqi Zhang , Mingru Wang , Minuo Wei , Shiwei Cheng , Cuntai Guan , Ting Han

Most explanation methods in deep learning map importance estimates for a model's prediction back to the original input space. These "visual" explanations are often insufficient, as the model's actual concept remains elusive. Moreover,…

机器学习 · 计算机科学 2021-06-22 Wolfgang Stammer , Patrick Schramowski , Kristian Kersting

Deep neural perception and control networks are likely to be a key component of self-driving vehicles. These models need to be explainable - they should provide easy-to-interpret rationales for their behavior - so that passengers, insurance…

计算机视觉与模式识别 · 计算机科学 2017-04-03 Jinkyu Kim , John Canny

In this paper, we review recent approaches for explaining concepts in neural networks. Concepts can act as a natural link between learning and reasoning: once the concepts are identified that a neural learning system uses, one can integrate…

人工智能 · 计算机科学 2024-05-06 Jae Hee Lee , Sergio Lanza , Stefan Wermter

Current neuroscience focused approaches for evaluating the effectiveness of a design do not use direct visualisation of mental activity. A recurrent neural network is used as the encoder to learn latent representation from…

神经元与认知 · 定量生物学 2021-03-30 Pan Wang , Danlin Peng , Simiao Yu , Chao Wu , Peter Childs , Yike Guo , Ling Li