more research - all clean 3/11

Author: i8myh8

_data/publist.yml

@@ -1,24 +1,47 @@
 - title: "Bio-Sensing and VR"
-  image: bio.jpg
-  description: The work explores a more affective, bio-responsive experience for real-time/VR AI singularly or multiuser environments  especially where mindfulness and wellness are a goal.
+  image: t_bio.jpg
+  description: Bio and brain sensing for interactive and VR AI singularly / multiuser environments especially where mindfulness/wellness are a goal.
   page: /bioBrainVR
   highlight: 1
 
 - title: "AI Virtual Humans"
-  image: covid.jpg
+  image: t_covid.jpg
   description: For real-time/VR AI singularly or multiuser environments  especially where mindfulness and wellness are a goal.
   page: /virtualHumans
   highlight: 1
 
 - title: "AI Anonymization"
-  image: aianon.jpg
-  description: Bringing together an interdisciplinary team, we have researched and created a wholly new AI technique to anonymize interview subjects and scenes in regular and 360 videos.
-  page: /AIAnon
+  image: t_aianon.jpg
+  description: Researched and created a wholly new AI techniques to anonymize interview subjects and scenes in regular and 360 videos.
+  page: /aiAnon
   highlight: 1
 
 - title: "AI Cognitive Creativity"
-  image: aicreative.jpg
+  image: t_aicreative.jpg
   description: AI modelling aspects of human creativity in AI using cognitive science as a basis for our work
-  page: /AICreativity
+  page: /aiCreativity
+  highlight: 1
+  
+- title: "AI Modeling Animals"
+  image: t_aianimals.jpg
+  description: AI modelling of the behavoir (thinking, movement, expression, ...) of animals and humans.
+  page: /aiAnimals
+  highlight: 1
+
+- title: "XR Avatars; Edu, Coaches, Health"
+  image: t_xrAvatars.jpg
+  description: XR (VR/AR/3D) systems where a user can expressive as talking 3D avatar with gestures/facial expressions. For education, coaches and health. 
+  page: /xrAvatars
+  highlight: 1
+
+- title: "AI Modeling Thought & Language"
+  image: t_aiThought.jpg
+  description: Cognitive modelling of thought, expression and language using advanced AI systems like AI Knowledge Graphs of thought and chained RAG based LLMs.
+  page: /aiThought
+  highlight: 1
+  
+- title: "Semantic Meaning & Analysis"
+  image: t_aiMeaning.jpg
+  description: Cognitive based anaylsis and modelling of deep Semantic Meaning. 
+  page: /aiMeaning
   highlight: 1
-  

_data/research.yml

@@ -3,11 +3,9 @@
 	<div class="container-fluid">
 	  <div class="row">
 		<div class="col-sm-4">
-
-		  <p>&copy 2024 iVizlab. We are part of the <a href="https://www.sfu.ca/siat.html">School of Interactive Art and Tech </a> at <a href="https://www.sfu.ca/">Simon Fraser University</a>.</p>
+          &copy 2024 iVizlab - - - - - - - - - - - - - - - - - - - - -
+		  <p>We are part of the <a href="https://www.sfu.ca/siat.html">School of Interactive Art and Tech </a> at <a href="https://www.sfu.ca/">Simon Fraser University</a>.</p>
 		  Site made with <a href="https://jekyllrb.com">Jekyll</a>;  <a href="{{ site.url }}{{ site.baseurl }}/aboutwebsite.html">copy and modify.</a></p>
-		  <a href="{{ site.url }}{{ site.baseurl }}/media">Pix and Media</a>
-
 
 
 		   <p>  </p><p>
@@ -16,10 +14,9 @@
 		</div>
 
 		<div class="col-sm-4">
-		  Contact:<br />
-		  Steve DiPaola<br />
+		  <a href="{{ site.url }}{{ site.baseurl }}/media">Lab Pix and Media</a> - - - - - - - - - - - -<br />
+		  Contact: Steve DiPaola<br />
 		  Simon Fraser University<br />
-		  250-13450 102 Ave.<br />
 		  Surrey, BC, Canada V3T 0A3<br />
 		  <br />
 		</div>

_includes/footer.html

@@ -1,9 +1,9 @@
 ---
 title: "iVizLab - Research"
 layout: textlay
-excerpt: "iVizLab -- Research"
+excerpt: "iVizLab -- AI Anonymization"
 sitemap: false
-permalink: /AIAnon/
+permalink: /aiAnon/
 ---
 
 # AI Anonymization 
@@ -35,7 +35,7 @@ See main site at [aipaint360.org](https://aipaint360.org)
 See main site at [aipaint360.org](https://aipaint360.org)
 
 {% for publi in site.data.publist %}
-  {% if publi.research contains 'AIAnon' %}
+  {% if publi.research contains 'aiAnon' %}
   <pubtit>{{ publi.title }}</pubtit> by
   {{ publi.authors }} --   <pubtit>{{ publi.type }}</pubtit> -- {{ publi.description }}
   <br> <a href="{{ publi.url }}">{{ publi.display }}

_pages/r_AiAnon.md

@@ -1,9 +1,9 @@
 ---
 title: "iVizLab - Research"
 layout: textlay
-excerpt: "iVizLab -- Research"
+excerpt: "iVizLab -- AI Cognitive Creativity"
 sitemap: false
-permalink: /AICreativity/
+permalink: /aiCreativity/
 ---
 
 # AI Cognitive Creativity

_pages/r_AiCreativity.md

@@ -18,8 +18,7 @@ Reseachers: Steve DiPaola, Mahdi Davoodikakhki, Andrey Goncharov, Nilay Ozge Yal
 Our open-source toolkit / cognitive research in AI 3D Virtual Human (embodied IVA : Intelligence Virtual Agents) : a real-time system that can converse with a human by sensing their emotions and conversation ( via facial emotion recognition, voice stress, semantics of the speech and words) and respond affectively, emotionally (voice, facial animation, gesture, etc) to a user in front of it via a host of gestural, motion and bio-sensor systems, with several in lab AI systems and give a coherent, personality-based conversational answers via speech, expression and gesture. The system uses Unity and SmartBody (USC) API who we have collaborated with for years. We use cognitive modeling, empathy modelling, NLP and a variety of AI-based modules in our system (see papers).
 
 
-Our **affective real-time 3D AI virtual human** setup with face emotion recognition, movement recognition and data glove recognition. See overview video or specific videos or papers below
-
+Our **affective real-time 3D AI virtual human** setup with face emotion recognition, movement recognition and hand gesture recognition. 
 <br>
 <iframe width="450" height="230" src="https://www.youtube.com/embed/RMLD7jccv_w?rel=0" frameborder="0" allowfullscreen></iframe>
 <br>

_pages/r_VitualHumans.md

@@ -0,0 +1,40 @@
+---
+title: "iVizLab - Research"
+layout: textlay
+excerpt: "iVizLab -- AI Modeling Animals"
+sitemap: false
+permalink: /aiAnimals/
+---
+
+# AI Modeling Animals 
+
+
+RESEARCH :: See [Related papers](#paperSection) ::  Related Projects: [Research]({{ site.url }}{{ site.baseurl }}/research)
+
+Reseachers: Steve DiPaola, Bill Kraus
+
+
+**The Research:**
+Our AI work here is in simulating complex (human and) animal behavoir using both Action Selection AI and Neural Networks (see papers). Technology is becoming increasingly incorporated into exhibit design. Both on the floor and extended online. Our AI work focuses on the design of  VR AI interactive exhibits for an aquarium gallery. The goal was to use technology to better immerse and engage the visitors in complicated educational concepts about the life of wild belugas. We were interested in encouraging deeper exploration of the content than what is typically possible via wall signage or a video display. The beluga simulation uses extremely realistic graphics and is based on an intelligent system that allows the virtual belugas to learn and alter their behaviour based on the visitor interaction. It was informed by research data from the live belugas, (e.g. voice recordings tied to mother/calf behavior) obtained from interviews with the marine mammal scientists and education staff. Observation and visitor studies determined that visitors rarely visit alone, so the interface was designed to encourage collaboration. It allows visitors and their companions to engage in “what-if” scenarios of wild beluga emergent behavior via a 3D interactive that uses artificial intelligence, physically based animation, and real-time graphics. The program could be linked to the aquarium web site to allow for an extension of the aquarium visitor experience.
+<br> 
+<img src="{{ site.url }}{{ site.baseurl }}/images/res/whale1.jpg" class="img-responsive" width="70%"/>
+<img src="{{ site.url }}{{ site.baseurl }}/images/res/whale2.jpg" class="img-responsive" width="70%"/>
+<img src="{{ site.url }}{{ site.baseurl }}/images/res/whale3.jpg" class="img-responsive" width="70%"/>
+
+<br>
+
+
+<div id="paperSection"></div>
+
+
+**------  PAPERS: AI Modeling Animals  ------**
+
+
+{% for publi in site.data.publist %}
+  {% if publi.research contains 'aiAnimals' %}
+  <pubtit>{{ publi.title }}</pubtit> by
+  {{ publi.authors }} --   <pubtit>{{ publi.type }}</pubtit> -- {{ publi.description }}
+  <br> <a href="{{ publi.url }}">{{ publi.display }}
+  {% endif %}  
+{% endfor %}
+

_pages/r_aiAnimals.md

@@ -0,0 +1,53 @@
+---
+title: "iVizLab - Research"
+layout: textlay
+excerpt: "iVizLab -- Semantic Meaning & Analysis"
+sitemap: false
+permalink: /aiMeaning/
+---
+
+# Semantic Meaning & Analysis
+
+
+RESEARCH :: See [Related papers](#paperSection) ::  Related Projects: [Research]({{ site.url }}{{ site.baseurl }}/research)
+
+Reseachers: Steve DiPaola, Suk Choi, Meehae Song, Nouf Abukhodair, Vanessa Utz
+
+
+**The Research:**
+Early Deep Learning systems are trained on huge datasets including text/image pairs that while can embed simple meaning, are still mainly trained on nouns like people, things, ... Our main research area is to go beyond that to deeper Semantic Meaning & Analysis work . Which parses and models more multimodal and deeper semantic meaning to AI work. We do this by both analyzing meaning space ( cognitive science of the arts, gesture, emotion, empathy, creativity, behavior, ...) but also then build models from cognitively and rigorously mapping these spaces that we can then use in our new emerging systems (with application in health, the arts, and education.
+<br><br>
+Our work into a new method to understand, measure and model "aesthic emotion" (see studies and papers)
+<img src="{{ site.url }}{{ site.baseurl }}/images/res/s1.jpg" class="img-responsive" width="70%"/>
+<img src="{{ site.url }}{{ site.baseurl }}/images/res/s2.jpg" class="img-responsive" width="70%"/>
+<img src="{{ site.url }}{{ site.baseurl }}/images/res/s3.jpg" class="img-responsive" width="70%"/>
+Reverse engineering generative visual Ai systems to better understand current meaning making to improve them. Here an emotionally complex prompt “an angry man punching a bag in a crowded joyful gym” and diffusion based output where we then used an advanced system to reverse detect and heatmap the meaning of every word back through the system
+<img src="{{ site.url }}{{ site.baseurl }}/images/res/s4.jpg" class="img-responsive" width="70%"/>
+<img src="{{ site.url }}{{ site.baseurl }}/images/res/s5.jpg" class="img-responsive" width="70%"/>
+Deep studies with eye tracking, on how an art viewer perceives (cognitively) artwork where we AI redraw masterwork (switch left/right eye detail & lost and found edges near chin). See several papers and over 200 press articles on our findings - like this one [Magic of Rembrandt's Painting Technique Revealed](https://www.livescience.com/9920-magic-rembrandt-painting-technique-revealed.html).
+<img src="{{ site.url }}{{ site.baseurl }}/images/res/s6.jpg" class="img-responsive" width="70%"/>
+Additional studies on deep meaning in aesthics, emotions, creativity, empathy, ... ( see papers).
+<img src="{{ site.url }}{{ site.baseurl }}/images/res/s7.jpg" class="img-responsive" width="70%"/>
+<img src="{{ site.url }}{{ site.baseurl }}/images/res/s8.jpg" class="img-responsive" width="70%"/>
+
+<iframe width="450" height="230" src="https://www.youtube.com/embed/N4Xr6Zm7Fes?rel=0" frameborder="0" allowfullscreen></iframe>
+<iframe width="450" height="230" src="https://www.youtube.com/embed/O_FaV-6hahM?rel=0" frameborder="0" allowfullscreen></iframe>
+
+
+<br>
+
+
+<div id="paperSection"></div>
+
+
+**------  PAPERS: Semantic Meaning & Analysis  ------**
+
+
+{% for publi in site.data.publist %}
+  {% if publi.research contains 'aiMeaning' %}
+  <pubtit>{{ publi.title }}</pubtit> by
+  {{ publi.authors }} --   <pubtit>{{ publi.type }}</pubtit> -- {{ publi.description }}
+  <br> <a href="{{ publi.url }}">{{ publi.display }}
+  {% endif %}  
+{% endfor %}
+

_pages/r_aiMeaning.md

@@ -0,0 +1,44 @@
+---
+title: "iVizLab - Research"
+layout: textlay
+excerpt: "iVizLab -- AI Modeling Thought & Langauge"
+sitemap: false
+permalink: /aiThought/
+---
+
+# AI Modeling Thought & Langauge
+
+
+RESEARCH :: See [Related papers](#paperSection) ::  Related Projects: [Research]({{ site.url }}{{ site.baseurl }}/research)
+
+Reseachers: Steve DiPaola, Rafael Arias Gonzalez, Nilay Yalcin, Maryam Ahmadzadeh
+
+
+**The Research:**
+Our AI work in cognitive modelling of thought, expression and language using advanced AI systems like AI Knowledge Graphs of thought and chained RAG based LLMs. Here allowing the public to talk faithfully (as possible) to inspiring historical figures like our Picasso and Van Gogh. With Van Gogh, we used our specific AI pre-processing of times of his life, historical events/people and the 700 letters he wrote in his own words to his brother Theo into a knowledge system that then goes through additional 3D facial expression, body gesture, talking, voice AI systems.
+<br> 
+<img src="{{ site.url }}{{ site.baseurl }}/images/res/vg1.jpg" class="img-responsive" width="70%"/>
+<img src="{{ site.url }}{{ site.baseurl }}/images/res/vg2.jpg" class="img-responsive" width="70%"/>
+
+Our VR talking, expressing animated character even dynamically morph into painted form based on his emotional state.
+<img src="{{ site.url }}{{ site.baseurl }}/images/res/vg3.jpg" class="img-responsive" width="70%"/>
+
+Talking with our Virtual AI Picasso live (created with ivizlab research and [Virtro](https://www.virtro.ca/))
+<iframe width="550" height="330" src="https://www.youtube.com/embed/Up7rLNkDkRo?rel=0" frameborder="0" allowfullscreen></iframe>
+<br>
+
+
+<div id="paperSection"></div>
+
+
+**------  PAPERS: AI Modeling Thought & Langauge  ------**
+
+
+{% for publi in site.data.publist %}
+  {% if publi.research contains 'aiThought' %}
+  <pubtit>{{ publi.title }}</pubtit> by
+  {{ publi.authors }} --   <pubtit>{{ publi.type }}</pubtit> -- {{ publi.description }}
+  <br> <a href="{{ publi.url }}">{{ publi.display }}
+  {% endif %}  
+{% endfor %}
+

_pages/r_aiThought.md

@@ -0,0 +1,46 @@
+---
+title: "iVizLab - Research"
+layout: textlay
+excerpt: "iVizLab; XR Avatars; Edu, Coaches, Health"
+permalink: /xrAvatars/
+---
+
+# XR Avatars; Edu, Coaches, Health
+
+
+RESEARCH :: See [Related papers](#paperSection) ::  Related Projects: [Publications]({{ site.url }}{{ site.baseurl }}/research)
+
+Reseachers: Steve DiPaola, Mahdi Davoodikakhki, Andrey Goncharov, Nilay Ozge Yalcin 
+
+
+**The Research**
+XR (VR/AR/3D) systems where a person (at home or work) can fully expressive themselves as a 3D avatar in desktop or full VR. With and without motion tracking their gestures and facial expressions. For education (fully credited university  XR class), as coaches for the elderly and others, and as a trainer in health (like we did here with nurses during covid).
+
+<br>
+Our work with fully credited university XR class during COVID (COGS100 at SFU) using XR systems with full mocap avatars, interactive multimedia, ...
+<iframe width="450" height="230" src="https://www.youtube.com/embed/RMLD7jccv_w?rel=0" frameborder="0" allowfullscreen></iframe>
+<iframe width="450" height="230" src="https://www.youtube.com/embed/mkWEz01Z1kw?rel=0" frameborder="0" allowfullscreen></iframe>
+
+Fully reacting AR coaches in front of you, to discuss the Climate Change or here to be there for an elderly women to help her as an assistant (so she can stay & live well in her home rather than a nursing home). 
+<iframe width="450" height="230" src="https://www.youtube.com/embed/JS58OBE0TwM?rel=0" frameborder="0" allowfullscreen></iframe>
+<iframe width="450" height="230" src="https://www.youtube.com/embed/2NmsT3VgZXg?rel=0" frameborder="0" allowfullscreen></iframe>
+
+Full motion tracked VR interactive for health training nurses (during COVID).
+<iframe width="450" height="230" src="https://www.youtube.com/embed/xB1ZPNC1Vdo?t=16?rel=0" frameborder="0" allowfullscreen></iframe>
+
+<div id="paperSection"></div>
+
+
+<br><br>
+**------  PAPERS: XR Avatars; Edu, Coaches, Health  ------**
+
+
+
+{% for publi in site.data.publist %}
+  {% if publi.research contains 'xrAvatar' %}
+  <pubtit>{{ publi.title }}</pubtit> by
+  {{ publi.authors }} --   <pubtit>{{ publi.type }}</pubtit> -- {{ publi.description }}
+  <br> <a href="{{ publi.url }}">{{ publi.display }}
+  {% endif %}  
+{% endfor %}
+

_pages/r_xrAvatars.md

@@ -25,8 +25,8 @@ permalink: /research/
 
 <div class="col-sm-6 clearfix">
 
-  <strong> [{{ publi.title }}]( {{ publi.page | relative_url }} )
-  
+  <strong> [{{ publi.title }}]( {{ publi.page | relative_url }} ) 
+  </strong>
   <img src="{{ site.url }}{{ site.baseurl }}/images/res/{{ publi.image }}" class="img-responsive" width="33%" style="float: left" />
   <p>{{ publi.description }}</p>