Zaproś Freelancera do Projektu
Wygląda na to, że nie masz obecnie aktywnego projektu. Dlaczego nie opublikujesz projektu teraz? To nic nie kosztuje!Opublikuj Projekt
- N/AUkończonych Prac
- N/AW Budżecie
- N/ANa czas
- N/APonowny angaż
I am building computational models to perceive the induced emotion in human viewers while watching multimedia content, especially ads. My work explores using multiple modalities (audio, video, text, physiological signals) with state of the art methods to enhance real world applications in computational advertising.
Summer of Code DeveloperJun 2017 - Aug 2017 (2 months)
I worked on optimising the CNN based visual recognition pipeline for the NewsScape dataset to generate visual annotations for over 300,000 hours of news video using high performance computing resources.
Summer of Code DeveloperJun 2016 - Aug 2016 (2 months)
I developed a system in C that extracts burned in subtitles from videos and generates caption text files in the desired format.
Teaching AssistantJan 2016 - May 2016 (4 months)
I took tutorial sessions, graded exams and assignments for a core undergrad CS course on Computer Networks
Bachelors + Masters in Computer Science2013 - 2018 (5 years)
Affect Recognition in Ads with Application to Computational Advertising
Advertisements (ads) often include strongly emotional content to leave a lasting impression on the viewer. This work (i) compiles an affective ad dataset capable of evoking coherent emotions across users, as determined from the affective opinions of five experts and 14 annotators; (ii) explores the efficacy of convolutional neural network (CNN) features for encoding emotions, and observes that CNN features outperform low-level audio-visual emotion descriptors upon extensive experimentation.
Evaluating content-centric vs. user-centric ad affect recognition
Despite the fact that advertisements (ads) often include strongly emotional content, very little work has been devoted to affect recognition (AR) from ads. This work explicitly compares content-centric and user-centric ad AR methodologies, and evaluates the impact of enhanced AR on computational advertising via a user study.