Discover cvjena/part_constellation_models Open Source project

Hierarchy-based Image Embeddings for Semantic Image Retrieval

361

semantic-embeddings

Convolutional (Patch) Networks for Semantic Segmentation

264

cn24

Extension of the public darknet repository with additional features and code improvements for YOLO.

123

darknet

119

artos

Adaptive Real-Time Object Detection System with HOG and CNN Features

Implementation of the Maximally Divergent Intervals algorithm for Anomaly Detection in multivariate spatio-temporal time-series.

libmaxdiv

Code for our paper "Generalized Orderless Pooling Performs Implicit Salient Matching" published at ICCV 2017.

alpha_pooling

Dataset with images from the central European flood 2013 for usage in the context of context-based image retrieval.

eu-flood-dataset

Felzenszwalb-Segmentation

An easy-to-use Matlab wrapper around the original felzenszwalb segmentation code

Benchmark for Data-Efficient Image Classification

deic

Two datasets of chimpanzee faces with curated meta data such as age, gender, and identity.

chimpanzee_faces

Code of the paper "Part Detector Discovery in Deep Convolutional Neural Networks" by Marcel Simon, Erik Rodner and Joachim Denzler

labelmefacade

LabelMeFacade Dataset

Perl

PartDetectorDisovery

Information-Theoretic Active Learning

ITAL

A duplicate-free variant of the CIFAR test set.

cifair

Nonparametric part-transfer for fine-grained recognition

finegrained-cvpr2014

This repo contains active learning query strategies as introduced in our GCPR 2013 paper.

activeLearning-GP

Automatic Query Image Disambiguation (AID)

aid

Computer vision library with interfaces for IPP and LinAL

nice-core

Images of Ecuador Moths for Fine-grained Recognition

ecuador-moths

gp-hik-core

Fast Gaussian process inference with HIK

Visualizing quantization effects in common bag-of-visual-words representations fro images.

bowInversion

Local learning for novelty detection

local_novelty_detection

Generic version of WHO for object detection with LDA models

whoGeneric

Modified version of the caffe CNN framework (https://github.com/BVLC/caffe).

caffe_pp

several tasks with chimpanzees, e.g., age recognition, identification, gender prediction, etc.

analyzing-chimpanzees

Discover (discriminative) mid-level patches in an (un-)supervised manner.

patchDiscovery

A dataset of images posted on Twitter with flood-related keywords, annotated according to their relevance regarding flood impact analysis.

twitter-flood-dataset

Custom caffe with signed power, compact bilinear and spatial transformer layer.

caffe_pp2

chiasmus-annotations

Kernel Null Foley-Sammon Transform for Novelty Detection

knfst

JeFaPaTo - A tool for the analysis of facial features

JeFaPaTo

chiasmus-detector

A data-driven approach to partitioning net ecosystem exchange (NEE) using a deep state space model DeepState

nee-partitioning

Code for "Active Learning for Deep Object Detection"

cn24-active

moth_scanner_demo

Implementation of the 4D curvature analysis for facial behavior analysis using a single Intel RealSense camera.

4DPADCurvAnalysis

Image Dataset of Costa-Rica Moths for Fine-grained Recognition

costarica-moths

Shell

scalebar

Computation of Radial Curves

corc

blob_detector

Diagonal Gaussian process approximations

gpapprox

liblinearwrapper

Matlab wrapper functionality for recent Caffe layout

caffe_tools

fve_experiments

This is a small python package to create a Electromyogram (EMG) plots for facial muscles.

electromyogram

This repository contains the source code for the method described in the following publication: Anomaly Attribution of Multivariate Time-Series using Counterfactual Reasoning

mdi-attribution

This projects main goal is to have a simple library to project information into faces while retaining the facial structure.

face-projection

Eye State Prototype Blink Matching

ESPBM

This repository contains code accompanying the paper "Gradient statistics based multi-objective optimization in Physics Informed Neural Networks"

GradStats4PINNs

Multi-view 3D facial landmarking

mvlm