PFAN++: Bi-Directional Image-Text Retrieval with Position Focused Attention Network

Meditation experience has previously been shown to improve performance on behavioral assessments of attention, but the neural bases of this improvement are unknown. Two prominent, strongly competing networks exist in the human cortex: a dorsal attention network, that is activated during focused attention, and a default mode network, that is suppressed during attentionally demanding tasks. Prior studies suggest that strong anti-correlations between these networks indicate good brain health. In addition, a third network, a ventral attention network, serves as a “circuit-breaker” that transiently disrupts and redirects focused attention to permit salient stimuli to capture attention. Here, we used functional magnetic resonance imaging to contrast cortical network activation between experienced focused attention Vipassana meditators and matched controls. Participants performed two attention tasks during scanning: a sustained attention task and an attention-capture task. Meditators demonstrated increased magnitude of differential activation in the dorsal attention vs. default mode network in a sustained attention task, relative to controls. In contrast, there were no evident attention network differences between meditators and controls in an attentional reorienting paradigm. A resting state functional connectivity analysis revealed a greater magnitude of anticorrelation between dorsal attention and default mode networks in the meditators as compared to both our local control group and a n = 168 Human Connectome Project dataset. These results demonstrate, with both task- and rest-based fMRI data, increased stability in sustained attention processes without an associated attentional capture cost in meditators. Task and resting-state results, which revealed stronger anticorrelations between dorsal attention and default mode networks in experienced mediators than in controls, are consistent with a brain health benefit of long-term meditation practice.

Download Full-text

Position Focused Attention Network for Image-Text Matching

Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence ◽

10.24963/ijcai.2019/526 ◽

2019 ◽

Cited By ~ 9

Author(s):

Yaxiong Wang ◽

Hao Yang ◽

Xueming Qian ◽

Lin Ma ◽

Jing Lu ◽

...

Keyword(s):

Visual Image ◽

Focused Attention ◽

Practical Application ◽

Image Region ◽

Attention Network ◽

Cross Domain ◽

Joint Embedding ◽

Visual Text ◽

Public Datasets ◽

Text Matching

Image-text matching tasks have recently attracted a lot of attention in the computer vision field. The key point of this cross-domain problem is how to accurately measure the similarity between the visual and the textual contents, which demands a fine understanding of both modalities. In this paper, we propose a novel position focused attention network (PFAN) to investigate the relation between the visual and the textual views. In this work, we integrate the object position clue to enhance the visual-text joint-embedding learning. We first split the images into blocks, by which we infer the relative position of region in the image. Then, an attention mechanism is proposed to model the relations between the image region and blocks and generate the valuable position feature, which will be further utilized to enhance the region expression and model a more reliable relationship between the visual image and the textual sentence. Experiments on the popular datasets Flickr30K and MS-COCO show the effectiveness of the proposed method. Besides the public datasets, we also conduct experiments on our collected practical news dataset (Tencent-News) to validate the practical application value of proposed method. As far as we know, this is the first attempt to test the performance on the practical application. Our method can achieve the state-of-art performance on all of these three datasets.

Download Full-text

SMAN: Stacked Multimodal Attention Network for Cross-Modal Image-Text Retrieval

IEEE Transactions on Cybernetics ◽

10.1109/tcyb.2020.2985716 ◽

2020 ◽

pp. 1-12

Author(s):

Zhong Ji ◽

Haoran Wang ◽

Jungong Han ◽

Yanwei Pang

Keyword(s):

Text Retrieval ◽

Attention Network ◽

Multimodal Attention

Download Full-text

Ras al Khaimah: further archaeological discoveries

Antiquity ◽

10.1017/s0003598x00150070 ◽

1976 ◽

Vol 50 (200) ◽

pp. 216-222

Author(s):

Beatrice De Cardi

Keyword(s):

United Arab Emirates ◽

The State ◽

Focused Attention ◽

North East ◽

The North ◽

History Of ◽

The City

Ras a1 Khaimah is the most northerly of the seven states comprising the United Arab Emirates and its Ruler, H. H. Sheikh Saqr bin Mohammad al-Qasimi, is keenly interested in the history of the state and its people. Survey carried out there jointly with Dr D. B. Doe in 1968 had focused attention on the site of JuIfar which lies just north of the present town of Ras a1 Khaimah (de Cardi, 1971, 230-2). Julfar was in existence in Abbasid times and its importance as an entrep6t during the sixteenth and seventeenth centuries-the Portuguese Period-is reflected by the quantity and variety of imported wares to be found among the ruins of the city. Most of the sites discovered during the survey dated from that period but a group of cairns near Ghalilah and some long gabled graves in the Shimal area to the north-east of the date-groves behind Ras a1 Khaimah (map, FIG. I) clearly represented a more distant past.

Download Full-text

Neurofeedback-Training bei Kindern mit Aufmerksamkeitsdefizit-/ Hyperaktivitätsstörung (ADHS)

Zeitschrift für Kinder- und Jugendpsychiatrie und Psychotherapie ◽

10.1024/1422-4917/a000070 ◽

2010 ◽

Vol 38 (6) ◽

pp. 409-420 ◽

Cited By ~ 10

Author(s):

Holger Gevensleben ◽

Gunther H. Moll ◽

Hartmut Heinrich

Keyword(s):

Attention Network Test ◽

Sich Eine ◽

Neurofeedback Training ◽

Attention Network ◽

Klinische Wirksamkeit

Im Rahmen einer multizentrischen, randomisierten, kontrollierten Studie evaluierten wir die klinische Wirksamkeit eines Neurofeedback-Trainings (NF) bei Kindern mit einer Aufmerksamkeitsdefizit-/Hyperaktivitätsstörung (ADHS) und untersuchten die einem erfolgreichen Training zugrunde liegenden neurophysiologischen Wirkmechanismen. Als Vergleichstraining diente ein computergestütztes Aufmerksamkeitstraining, das dem Setting des Neurofeedback-Trainings in den wesentlichen Anforderungen und Rahmenbedingungen angeglichen war. Auf Verhaltensebene (Eltern- und Lehrerbeurteilung) zeigte sich das NF-Training nach Trainingsende dem Kontrolltraining sowohl hinsichtlich der ADHS-Kernsymptomatik als auch in assoziierten Bereichen überlegen. Für das Hauptzielkriterium (Verbesserung im FBB-HKS Gesamtwert) ergab sich eine mittlere Effektstärke (von 0.6). Sechs Monate nach Trainingsende (follow-up) konnte das gleiche Ergebnismuster gefunden werden. Die Ergebnisse legen somit den Schluss nahe, dass NF einen klinisch wirksamen Therapiebaustein zur Behandlung von Kindern mit ADHS darstellt. Auf neurophysiologischer Ebene (EEG; ereignisbezogene Potentiale, EPs) konnten für die beiden Neurofeedback-Protokolle Theta/Beta-Training und Training langsamer kortikaler Potentiale spezifische Effekte aufgezeigt werden. So war für das Theta/Beta-Training beispielsweise die Abnahme der Theta-Aktivität mit einer Reduzierung der ADHS-Symptomatik assoziiert. Für das SCP-Training wurde u. a. im Attention Network Test eine Erhöhung der kontingenten negativen Variation beobachtet, die die mobilisierten Ressourcen bei Vorbereitungsprozessen widerspiegelt. EEG- und EP-basierte Prädiktorvariablen konnten ermittelt werden. Der vorliegende Artikel bietet einen Gesamtüberblick über die in verschiedenen Publikationen unserer Arbeitsgruppe beschriebenen Ergebnisse der Studie und zeigt zukünftige Fragestellungen auf.

Download Full-text