Posts by Collection

Realtime object detection with YOLO part1: theory [in Vietnamese]

Published: January 10, 2017

YOLO is a realtime object detectors.

Realtime object detection with YOLO part2: training [in Vietnamese]

Published: March 15, 2017

Train YOLO model to identify poker cards.

Entropy, Cross Entropy, Kullback–Leibler divergence

Published: August 15, 2017

Entropy

Quadrilateral detection from polygon or segmentation masks

Published: November 13, 2017

In some applications we need to detect the quadrilateral objects in the image, for example detecting a document, an ID card, or anything whose the shape is quadrilateral. By using some techniques such as contour detection, edge detection, connected components etc. we can identifiy the object but it is not always a 4-edges polygon.

How to reduce the prediction time of deep learning models

Published: March 13, 2018

When we need speedup the prediction time?

Expectation Maximization algorithm

Published: May 19, 2018

I. Expectation Maximization

Deep learning basing on EM

Published: November 20, 2018

Training settings for object detection using CNN models. (a) is supervisedlearning which uses instance-level labels (red bounding boxes in the image). (b) isweakly-supervised learning where only image-level labels (”train”) are used. (c) is mix-supervised learning where both image-level labels (”train”) and instance-level labels(red bounding boxes) are used. (d) is semi-supervised learning where instance-levellabeled images and unlabeled images are used

Binding the Simple Query Interface

Text retrieval relevance feedback techniques for bag-of-words model in CBIR

Region-based semi-automatic annotation using the Bag of Words representation of the keywords

The AROUND project: Adapting robotic disaster response to developing countries

Using SR-tree in a Content-based and Location-based Image Retrieval System

Clusters-based relevance feedback for CBIR

PEDIVHANDI: multimodal indexation and retrieval system for lecture videos

Cluster-based relevance feedback for CBIR: a combination of query point movement and query expansion

Interactive knowledge learning for ancient images

Bag of subjects: Lecture videos multimodal indexing

Multi-modal and cross-modal for lecture videos retrieval

Keyword visual representation for image retrieval and image annotation

Comic characters detection using deep learning

Adaptive Edit-Distance and Regression Approach for Post-OCR Text Correction

Digital Comics Image Indexing Based on Deep Learning

Semi-supervised Object Detection via Expectation Maximization

Multi-task model for comic book image analysis

Deep Statistical Analysis of OCR Errors for Effective Post-OCR Processing

Comic MTL: optimized multi-task learning for comic book image analysis

What do we expect from panel extraction ?

Confidence crite-rion for speech balloon segmentation

Post-OCR Error Detection by Generating Plausible Candidates

An adaptive document recognition system for lettrines

Neural Machine Translation with BERT for Post-OCR Error De-tection and Correction

A learning approach with incomplete pixel-level labels for deep neural networks

Text block segmentation in comic speech bubbles

Competition: Multimodal Emotion Recognition on Comics scenes

ICDAR 2021 Competition on Historical Map Segmentation

Manga-MTL: multimodal multitask transfer learning for mangas