Tilak's repositories
Car-Damage-Analysis-App
Assessing external car damage, i.e., severity and location using Deep Learning and deploy it using flask and tensorflow serving.
Object-detection-and-segmentation-for-self-driving-cars
Utilize bdd100k dataset and mask r-cnn to detect and recognize objects for self driving cars
2D-Road-Object-Detection
Road Object Detection using Deep Learning, based on tensorflow framework and BDD100k dataset
Monocular-Depth-Estimation-Argoverse
Monocular depth estimation from ArgoAI's Lidar based Depth dataset - Depth predictions up-to 200m
GazeTracking
đź‘€ Webcam-based Eye Tracking system
Triplet_Loss_Classification
Utilize Triplet Loss and mean shift based calibration for Classification - This project shows a working concept for pose classification
Argoverse-Monocular_depth-dataset-creation
Creation of monocular depth dataset using Argoverse
argoverse-api
Official GitHub repository for Argoverse dataset
Autonomous-takeoff-and-landing-using-Deep-Reinforcement-Learning
Autonomous takeoff and landing of a Quad-copter using Deep Reinforcement Learning
av2-api
The official GitHub repository for the Argoverse 2 dataset.
bevfusion
BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation
CenterCLIP
[SIGIR 2022] CenterCLIP: Token Clustering for Efficient Text-Video Retrieval. Also, a text-video retrieval toolbox based on CLIP + fast pyav video decoding.
Deploying-a-Sentiment-Analysis-Model-with-Amazon-SageMaker
Deploying a Sentiment Analysis Model with Amazon SageMaker
Diver-Fatigue-Detection
Drowsiness detection using dlib landmarks
Dog-breed-classifier-CNN-project
Build a pipeline to process real-world, user-supplied images. Given an image of a dog, algorithm will identify an estimate of the canine’s breed. If supplied an image of a human, the code will identify the resembling dog breed.
Drivable-Area_Segmentation
Drivable Area Segmentation using Deep Learning and BDD100k dataset
emoca
Official repository accompanying a CVPR 2022 paper EMOCA: Emotion Driven Monocular Face Capture And Animation. EMOCA takes a single image of a face as input and produces a 3D reconstruction. EMOCA sets the new standard on reconstructing highly emotional images in-the-wild
Face-Generation-using-GANs
Use generative adversarial networks to generate new images of faces.
Face-Recognition-API
Face Recognition app utilizing triplet loss on webcam feed with tensorflow serving
Image-Captioning
Use CNN with LSTM to extract captions for images
Lane-Segmentation
Deep Learning based Lane Segmentation using BDD100K.
LAVIS
LAVIS - A One-stop Library for Language-Vision Intelligence
MeMViT
Code Release for MeMViT Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognition, CVPR 2022
MICA
MICA - Towards Metrical Reconstruction of Human Faces [ECCV2022]
OneFormer
[Preprint] OneFormer: One Transformer to Rule Universal Image Segmentation, 2022