• Stars
    star
    2
  • Language
    Jupyter Notebook
  • License
    MIT License
  • Created over 3 years ago
  • Updated over 3 years ago

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

Implementation for Temporal Relational Reasoning in Videos. This is a NYU course project for DS-GA 3001.004/.005 Introduction to Computer Vision (Spring 2021)

More Repositories

1

Awesome-Multimodal-LLM-Autonomous-Driving

[WACV 2024 Survey Paper] Multimodal Large Language Models for Autonomous Driving
210
star
2

lanenet-lane-detection-pytorch

Unofficial implemention of lanenet model for real time lane detection Pytorch Version
Python
127
star
3

waymo_to_semanticKITTI

Convert waymo open dataset 3D segmentation format to SemanticKITTI format.
Python
14
star
4

ViTASD

Official Implementation of ViTASD: Robust Vision Transformer Baselines for Autism Spectrum Disorder Facial Diagnosis
Python
10
star
5

Chromosome_Classification_Deep_Learning_Method

It is a project based on IJCNN's paper Automatic Chromosome Classification using Deep Attention Based Sequence Learning of Chromosome Bands and process some new methods
Jupyter Notebook
9
star
6

Gomoku-XYH19

A AI project about Gomoku
Python
6
star
7

VCog-Bench

What is the Visual Cognition Gap between Humans and Multimodal LLMs?
Python
4
star
8

MAE-ViT-pytorch

MAE-ViT-pytorch, structure is based on https://github.com/rwightman/pytorch-image-models
Python
4
star
9

Infant-Pose-pytorch

Apply OpenPose and Infant Key-point Dataset to Evaluate Infant Posture
C++
3
star
10

contour-aware-Unet

The realization of different classes of Unet framework including contour-aware-Unet, DCAN, Dual Unet, Attention Unet, Unet++
Jupyter Notebook
2
star
11

MVLM-PyTorch

Python
2
star
12

Crossing_Aggregation_Network

It is a U-Net based network which absorb ideas from deep aggregation layers(DLA), Unet++, ET-Net......
Python
2
star
13

SEC-UNET_SEMANTIC_EMBEDDING_AND_CONTOUR_ASSIST_UNET_FOR_BACTERIA_SEGMENTATION-AND-DETECTION

The number of bacterial types is a critical monitoring indicator for indoor air quality standards. It is a challenging task to cultivate and count colonies of bacteria which is expertise required and time-consuming. In this work, we investigate several U-Net improvement approaches. We are motivated by the assumption that contour information and semantic embedding branch can enhance U-Net's segmentation capacity for blurred and overlapping objects. Therefore, we propose Semantic Embedding and Contour Assist U-Net (SEC-U-Net) for direct bacteria segmentation and a shallow CNN for bacteria classification. This algorithm designed the detection of bacteria as a two-stage segmentation and classification task. Experimental results demonstrate the proposed method outperforms the state-of-the-art improved U-Net approaches on our bacteria dataset. Proposed SEC-U-NET+CNN based training presented over 91% and 85% precision rate for E.coli and S.aureus, respectively.
Jupyter Notebook
2
star
14

IrohXu

1
star
15

A-miniature-relational-database-with-order

NYU Courant Database Systems, CSCI-GA.2433-011 Course Project Assignment
Python
1
star
16

irohxu.github.io

github.io for Iroh Cao
CSS
1
star
17

Chromosome_Segmentation_U-Net

It is a U-Net based project to handle the chromosome segmentation problem
Jupyter Notebook
1
star