Name: Satish Kumar
Type: User
Company: Vision Research Lab, ECE
Bio: PhD Candidate, University of California Santa Barbara,
Previously at Samsung Research Institute
Location: University of California, Santa Barbara
Blog: bisque.ece.ucsb.edu
Satish Kumar's Projects
Animal detection in the wild from overhead (Drone and hot air balloon) thermal/infrared images
Paper template and author instructions for BMVC
PyTorch CZSL framework containing GQA, the open-world setting, and the CGE and CompCos methods.
Deformable DETR: Deformable Transformers for Methane Detection.
FAIR's research platform for object detection research, implementing popular algorithms like Mask R-CNN and RetinaNet.
End-to-End Object Detection with Transformers
My summary of papers to read
Implementation for E2E image detection and recognition algorithm - Faster RCNN (Pytorch)
Prototype of FPaxos, built upon LibPaxos3
GTNet:Guided Transformer Network for Detecting Human-Object Interactions
This is a pyramid oauth provider that uses oauthlib
For creating a panorama from multiple images
Salinity and turbidity detection of water ponds using Satellite imagery
This paper describes LOCL: Learning Object-Attribute (O-A) Composition using Localization – that generalizes composition zero shot learning to objects in cluttered/more realistic settings.
Official code repository for NeurIPS 2022 paper "SatMAE: Pretraining Transformers for Temporal and Multi-Spectral Satellite Imagery"
A platform to create an online marketplace
Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow
Deep Learning based Remote Sensing Methods for Methane Detection in Airborne Hyperspectral Imagery
MethaneMapper: Spectral Absorption aware Hyperspectral Transformer for Methane Detection
computes the pearson correlation of multi dimension in pytorch
Latex code for making neural networks diagrams
Code for my medium article
Second-order Attention Network for Single Image Super-resolution (CVPR-2019)
The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
StressNet: Detecting Stress in Thermal Videos
As a part of the HAKE project (HAKE-Object), code for Symmetry and Group in Attribute-Object Compositions (CVPR2020).
This repository is a curated collection of the most exciting and influential CVPR 2024 papers. 🔥 [Paper + Code + Demo]
TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks