NCAR Climate and Global Dynamics seminar (4/27/21)

During my summer UG research internship, I explored the use of vision transformers (ViTs) for object detection, focusing on mitigating the computational requirements of transformer models. This project successfully achieved multiple objectives and identified crucial features for future advancements in object detection using ViTs.

A submission to the experiment coding competition "MARVIN" organised by Think Cognitive Think Science

A multiple object tracker based on CNN

Simple implementation of multiple object tracking using Kalman filter and SSD Object detector

Using DeepSort with YOLOv3 to perform multiple objects tracking

A solution for NFL Health & Safety -- Helmet Assignment Kaggle, based on helmet mapping and multiple object tracking.

Human-following robot that identifies a target user and controls driving with hand gestures in crowded environments.

My bachelor thesis on the topic of multiple object tracking.

Multiple Object Tracking, Team 4, Model Implementation, 2025 HAI S1

vision datasets stats for common vision tasks and datasets.

Accepted for CVPR 2019 Tracking Challenge, workshop "4th BMTT MOTChallenge Workshop - How crowded can it get?"

Multiple object tracking library

Software for counting objects from drones

Real time face recognition with multiple object tracking

Multi-object tracking system for retail environments using YOLOv12, BoT-SORT, and homography-based cross-camera re-identification. Features post-processing heuristics and spatiotemporal matching for robust visitor trajectory generation.

cell cycle analysis

Project implemented as part of master thesis Semantic segmentation and tracking of human silhouettes on video sequences for heart rate estimation algorithm

Unofficial implementation of the Motion Feature SORT algorithm