Insaf Ismath's repositories
CLIP
CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image
covid-people-graph
Gihan Jayatilaka*, Jameel Hassan*, Suren Sritharan*, Janith Senananayaka, Harshana Weligampola, et. al., 2021. Holistic Interpretation of Public Scenes Using Computer Vision and Temporal Graphs to Identify Social Distancing Violations. arXiv preprint. https://arxiv.org/pdf/2112.06428.pdf
detectron2-deepsort-pytorch
MOT tracking using deepsort and yolov3 with pytorch
EveryPixelMatters
Implementation of ECCV 2020 paper "Every Pixel Matters: Center-aware Feature Alignment for Domain Adaptive Object Detector"
kpts_with_person_tracking
YOLOv7 pose estimation with SORT person tracking
lightweight-human-pose-estimation.pytorch
Fast and accurate human pose estimation in PyTorch. Contains implementation of "Real-time 2D Multi-Person Pose Estimation on CPU: Lightweight OpenPose" paper.
mmpose
OpenMMLab Pose Estimation Toolbox and Benchmark.
openpose
OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation
pyskl
A toolbox for skeleton-based action recognition.
PyTorch-YOLOv3
Minimal PyTorch implementation of YOLOv3
simple-HRNet
Multi-person Human Pose Estimation with HRNet in Pytorch
SmartSolarTracker
Designed a solar panel system which tracks the sun in a single axis. A PIC16F877A programmed using Assembly language was used. Assembly language, PIC
STAN
Official PyTorch implementation of the paper "Revisiting Temporal Modeling for CLIP-based Image-to-Video Knowledge Transferring"
t81_558_deep_learning
Washington University (in St. Louis) Course T81-558: Applications of Deep Neural Networks
Video-LLaVA
PG-Video-LLaVA: Pixel Grounding in Large Multimodal Video Models
ViFi-CLIP
[CVPR 2023] Official repository of paper titled "Fine-tuned CLIP models are efficient video learners".
webvid
Large-scale text-video dataset. 10 million captioned short videos.
X-CLIP
An official implementation for "X-CLIP: End-to-End Multi-grained Contrastive Learning for Video-Text Retrieval"
yolov4-deepsort
Object tracking implemented with YOLOv4, DeepSort, and TensorFlow.
yolov7
Implementation of paper - YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors