Himangi Mittal

Just-Go-with-the-Flow-Self-Supervised-Scene-Flow-Estimation. Self-supervised method for scene-flow estimation of LiDAR point clouds. Method is trained and tested on the nuScenes and KITTI datasets in TensorFlow. (CVPR 2020)

Depression_Detection. Detecting depression levels in employees from videos of DAIC-WOZ dataset using LSTMs and Facial Action Units as input.

UniPhy_CVPR2025. Python

Self-Supervised-Point-Cloud-Completion-via-Inpainting. Self-supervised method for completing partial LiDAR point clouds. Trained and tested on ShapeNet and SemanticKITTI in TensorFlow. (BMVC 2021)

RepLAI. Self-supervised algorithm for learning representations from ego-centric video data. Code is tested on EPIC-Kitchens-100 and Ego4D in PyTorch. (NeurIPS 2022)

Anomaly_Graph_Neural_Net. Anomaly detection algorithm for social networks using Graph Neural Networks by leveraging graph parameteres, between centrality, degree, closeness, on Enron and Twitter datasets

Scene-Graph-Generation. Prediction of action and spatial visual relationships in images between objects in the VRD-Dataset using visual, semantic, spatial, and heatmap features with structual ranking loss

awesome-self-supervised-learning. A curated list of awesome self-supervised methods

video-diffusion-pytorch. Implementation of Video Diffusion Models, Jonathan Ho's new paper extending DDPMs to Video Generation - in Pytorch

faster-rcnn.pytorch. A faster pytorch implementation of faster r-cnn

SpaceTimeEmb. Performs node classficiation using Support Vector Machine on the trajectory representations which are obtained from random-walks on a spatio-temporal graphs and Skipgram model.

pytorch-yolo-v3. A PyTorch implementation of the YOLO v3 object detection algorithm

awesome-point-cloud-analysis. A list of papers and datasets about point cloud analysis (processing)