Links to these brilliant PhD candidates' work: Sonia Raychauduri https://
openaccess.thecvf.com/content/WACV20
24/html/Raychaudhuri_MOPA_Modular_Object_Navigation_With_PointGoal_Agents_WACV_2024_paper.html
… Bita Azari https://
openaccess.thecvf.com/content/WACV20
24/html/Azari_EmoStyle_One-Shot_Facial_Expression_Editing_Using_Continuous_Emotion_Parameters_WACV_2024_paper.html
… Sha Hu https://
openaccess.thecvf.com/content/WACV20
24/html/Hu_Embodied_Human_Activity_Recognition_WACV_2024_paper.html
…
@petitegeek
-
PhD Research in Computer Vision and Embodied AI Navigation
By
–
-
SFU Computer Science Delegation at WACV 2024 Conference
By
–
Our delegation from @SFU_CompSci at #WACV2024. Thank you @wacv_official for a wonderful conference!
-
Data Before Labels: Machine Learning Keynote Discussion
By
–
Which should come first, the data or the labels? Great keynote by @dimadamen #wacv2024
-
Social Intelligence and Empathy in Robot Design
By
–
And this is also why I named my lab Robots with Social Intelligence and Empathy (ROSIE)… I think social intelligence by itself doesn't necessarily imply the care and affective empathy we would like to see.
-
Intelligence without empathy psychopathy in AI systems
By
–
Interesting point. I think it might have to do with intelligence coupled with lack of empathy (psychopathy)
-
Moravec’s Paradox: Why Robot Demos Bore Humans
By
–
As someone working on robotics in the depths of Moravec's paradox, one issue is that demos of skills that humans find effortless are highly boring
-
Computer Science Lacks Professional Maturity Like Medicine or Law
By
–
Computer science is not a mature profession like medicine, law, engineering or accounting. The latter have accreditation, certifications, licensing, codes of ethics, professional societies, etc. The field underlying AI is different from the field underlying pharma
-
AI Image Captioning Tool for Emotional Salient Features Analysis
By
–
We also offer a captioning method to convert images into sentences describing emotionally salient features related to face, body, pose, human interactions, activity and environment. Social scientists might be interested in our manual annotation interface
-
Emotional AI: Fast Slow Emotion Recognition Vision Models
By
–
Captioning interface
Arxiv: https://
arxiv.org/abs/2309.13136
Project: https://
rosielab.github.io/emotion-captio
ns/
… Emotions Fast and Slow Arxiv: https://
arxiv.org/abs/2310.19995
Project: https://
rosielab.github.io/Fast-and-Slow/ -
Multimodal AI Shows Promise for Emotion Recognition Beyond Zero-Shot Methods
By
–
Overall, these zero shot methods do not perform nearly as well humans nor models tuned on the training data from EMOTIC (Emotions in Context). But there appears to be promise in linking vision with language to account for both affective and cognitive empathy