Movie streaming app installed on Android TV to watch timeless classics such as: Le Voyage Dans la Lun (1902), Metropolis (1927), Frankenstein (1910), Great Train
3D Web Graphics and Animations using WebGL, p5.js and Three.js 3D Animated Cube in WebGL + p5.js Planet Earth in WebGL + p5.js Textured Cube
Custom ML model to classify food / menu images, using Teachable Machines .. Sample Output: Demo Video: What’s Next: Try confusing the classifier by adding
MIDI Parser + Visualizer Parses MIDI file by extracting notes, and shows how to play the tune on piano, by highlighting corresponding keys.. Music Generation
Model built in Auto-ML Vision to recognize popular TV / Movie Characters..
Model built in AutoML Vision to detect popular cartoon characters..
Converting Still Photos into Talking Animated Characters Deep-Learning based Generative Neural Networks (GANs) to create talking animated characters from still pictures.. Here, I first converted
Converting Still Photos into Talking Videos Here, the still pictures of Hollywood actors on the left automatically “lip-sync” with the famous Bollywood actor (Raj Kapoor
Using Hand-Gestures to Move Objects in AR / VR Instead of placing Aruco Markers on real-world surfaces (like wall, posters, table), here I use hand-tracking
Real-Time Video Segmentation on Live Camera Stream to Extract Person from Background, and replace Background, w/o Hollywood style Green Screen Studio Setup.. Try Live on
Sports Activity Recognition using Transfer Learning Objective: Build a knn-classifier to recognize sports activities using Transfer Learning.. Why Transfer Learning? While pre-trained models are great
Object Detection using TensorFlow.JS COCO-SSD model.. Reference: TensorFlow.JS COCO-SSD model Types of Objects detected (includes most common objects like cat, dog, car, bus, truck, person,
Identifying Animal / Bird Species in Wild Life Documentary Films Implemented using Mobile-Net model in TensorFlow.JS Description: analyzes video frame by frame and runs Mobile-Net
Detecting Facial Expressions of Comedians using OpenCV + Dlib Real-Time Face Tracking with TensorFlow.JS Description: Captures live video stream from camera and runs TensorFlow.JS FaceMesh
Automatic Scene Generation using DC-GANs in PyTorch.. References: PyTorch Tutorial on DC-GANs Intel Image Classification Dataset – used for training the GAN model, contains scenes
Generating Anime Character Faces using DC-GAN in PyTorch.. DC-GAN stands for Deep Convolutional Generative Adversarial Networks.. References: PyTorch Tutorial on DC-GANs, Kaggle Dataset of Anime
Capturing body movements, actions and postures from dance and figure skating videos using OpenPose from CMU’s panoptic studio..
Applying Neural Style Transfer to produce artistic effects and filters in photos and videos.. Originals: Styled using: Implemented using PyTorch and Keras.. Try in Google
Trying Digital Restoration & Colorization of Old Black & White Films, using DeOldify, advance deep learning based implementation of Generative Adversarial Neural Networks called No-GANs..
Created cinematrix.in – to showcase applications of AI & Machine Learning in Multimedia & Entertainment domain.. Read the story behind this creative journey that started
Demo of Fashion Advertising created by interns from BITS Pilani, who worked in my team during Summer 2018. Displays product ads for clothing and fashion
Demo of Player Face Recognition created by interns from BITS Pilani, who worked in my team during Summer 2018. Uses Face Recognition to identify players
A cool visualization of projects posted on Kick Starter made in Kibana..
Joined SONY‘s research team in Tokyo, Japan to work on some cutting edge technologies to create personalized music recommendations..
Presented a paper on Humor Analysis in FRIENDS at EMNLP-2006 in Sydney. The paper analyses dialog transcripts and audio tracks in FRIENDS episodes for automatic