Italy

We propose an innovative method for combining sparse optical ﬂow tracking and descriptor matching algorithms.
The proposed approach solves the following problems that are inherent to keypoint-based and optical ﬂow based tracking algorithms: spatial jitter, extreme scale transformation, extreme perspective transformation, degradation in the number of tracking points, and drifting of tracking points. Our algorithm provides smooth object-position tracking under six degrees of freedom transformations with a small computational cost for providing a high-quality real-time AR experience on mobile platforms. We experimentally demonstrate that our approach outperforms the state-of-the-art tracking algorithms while offering faster computational time. A mobile augmented reality (AR) application, which is developed using our approach, delivers planar object tracking with 30 FPS on modern mobile phones for a camera resolution of 1280 720. Finally, we compare the performance of our AR application with that of the Vuforia-based AR application on the same planar objects database. The test results show that our AR application delivers better AR experience than Vuforia in terms of a smooth transition of object-pose between video frames.

ICPR 2020

Mobile Augmented Reality: Fast, Precise, and Smooth Planar Object Tracking

binary descriptors

planar object tracking

optical flow

ICPR 2020 is the premier international conference on Pattern Recognition, gathering leading researchers from around the world to present their latest achievements in Pattern Analysis and Recognition, applied Artificial Intelligence and Machine Learning. The topic of the year is " Putting Artificial intelligence to work on Patterns". 
For the first time, ICPR has employed a two-round review process similar to journal submissions, with new papers allowed to be submitted in either the first or second round and papers submitted in the first round and not accepted allowed to be revised and re-submitted for second round review. 

In this edition of the **ICPR 2020** Conference, there are 1407 Oral/Poster presentations organized in five Tracks: 
- Artificial Intelligence, Machine Learning for Pattern Analysis; 
- Biometrics, Human Analysis and Behavior Understanding; Computer Vision, Robotics and Intelligent Systems; 
- Document and Media Analysis; and 
- Image and Signal Processing. 

The **ICPR 2020** Main Conference program also includes 7 Keynotes from prominent world-renowned scientists, 8 Tutorials, 28 Demos, 8 Challenges, 2 Panels, as well as an Industry/Sponsor Exhibition. In addition, 41 Workshops on a range of important current and emerging research topics complete the ICPR 2020 program. 


poster


Encoded (or ciphered) manuscripts are a special type of historical documents that contain encrypted text. The automatic recognition of this kind of documents is challenging because: 1) the cipher alphabet changes from one document to another, 2) there is a lack of annotated corpus for training and 3) touching symbols make the symbol segmentation difficult and complex. To overcome these difficulties, we propose a novel method for handwritten ciphers recognition based on few-shot object detection. Our method first detects all symbols of a given alphabet in a line image, and then a decoding step maps the symbol similarity scores to the final sequence of transcribed symbols. By training on synthetic data, we show that the proposed architecture is able to recognize handwritten ciphers with unseen alphabets. In addition, if few labeled pages with the same alphabet are used for fine tuning, our method surpasses existing unsupervised and supervised HTR methods for ciphers recognition.

A Few-shot Learning Approach for Historical Ciphered Manuscript Recognition

Typically, real-world requirements to deploy face recognition models in unconstrained surveillance scenarios demand to identify low-resolution faces with extremely low computational cost. In the last years, several methods based on complex deep learning models have been proposed with promising recognition results but at a high computational cost. Inspired by the compactness and computation efficiency of lightweight deep face networks and their high accuracy on general face recognition tasks, in this work we propose to benchmark two recently introduced lightweight face models on low-resolution surveillance imagery to enable efficient system deployment. In this way, we conduct a comprehensive evaluation on the two typical settings: LR-to-HR and LR-to-LR matching. In addition, we investigate the effect of using trained models with down-sampled synthetic data from high-resolution images, as well as the combination of different models, for face recognition on real low-resolution images. Experimental results show that the used lightweight face models achieve state-of-the-art results on low-resolution benchmarks with low memory footprint and computational complexity. Moreover, we observed that combining models trained with different degradations improves the recognition accuracy on low-resolution surveillance imagery, which is feasible due to their low computational cost.

Lightweight Low-Resolution Face Recognition for Surveillance Applications


This paper studies the problem of Person Re-Identification (ReID)
for large-scale applications. Recent research efforts have been devoted
to building complicated part models, which introduce considerably
high computational cost and memory consumption, inhibiting its practicability
in large-scale applications. This paper aims to develop a novel learning
strategy to find efficient feature embeddings while maintaining the
balance of accuracy and model complexity. More specifically, we find
by enhancing the classical triplet loss together with cross-entropy
loss, our method can explore the hard examples and build a discriminant
feature embedding yet compact enough for large-scale applications.
Our method is carried out progressively using Bayesian optimization,
and we call it the Progressive Learning Algorithm (PLA). Extensive
experiments on three large-scale datasets show that our PLA is comparable
or better than the state-of-the-arts. Especially, on the challenging
Market-1501 dataset, we achieve Rank-1=94.7%/mAP=89.4% while saving
at least 30\% parameters than strong part models.

Naturally Constrained Online Expectation Maximization



Accurate prediction of epileptic seizures has remained elusive, despite the many advances in machine learning and time-series classification. In this work, we develop a convolutional network module that exploits Electroencephalogram (EEG) scalograms to distinguish between the pre-seizure and normal brain activities. Since these scalograms have rectangular image shapes with many more temporal bins than spectral bins, the presented module uses “semi-dilated convolutions” to create a proportional non-square receptive field. The proposed semidilated convolutions support exponential expansion of the receptive field over the long dimension (image width, i.e. time) while maintaining high resolution over the short dimension (image height, i.e., frequency). The proposed architecture comprises a set of co-operative semi-dilated convolutional blocks, each block has a stack of parallel semi-dilated convolutional modules with different dilation rates. Results show that our proposed solution outperforms the state-of-the-art methods, achieving seizure prediction sensitivity scores of 88.45% and 89.52% for the American Epilepsy Society and Melbourne University EEG datasets, respectively.

Epileptic Seizure Prediction: A Semi-Dilated Convolutional Neural Network Architecture

In a Convolutional Neural Network, each neuron in the output feature map takes input from the neurons in its receptive field. This receptive field concept plays a vital role in today’s deep neural networks. However, inspired by neuro-biological research, it has been proposed to add inhibitory neurons outside the receptive field, which may enhance the performance of neural network models. In this paper, we begin with deep network architectures such as VGG and ResNet, and propose an approach to add lateral inhibition in each output neuron to reduce its impact on its neighbours, both in fine-tuning pre-trained models and training from scratch. Our experiments show that notable improvements upon prior baseline deep models can be achieved. A key feature of our approach is that it is easy to add to baseline models; it can be adopted in any model containing convolution layers, and we demonstrate its value in applications including object recognition and semantic segmentation of aerial images, where we show state-of-the-art result on the Aeroscape dataset. On semantic segmentation tasks, our enhancement achieves 13.43% higher mIoU than a single baseline model on a single source (the Aeroscape dataset) and 7.03% higher the previous state-of-the art result, which was an ensemble model trained on multiple sources. Our experiments illustrate the potential impact of using inhibitory neurons in deep learning models, and they also show better results than the baseline models that have standard convolutional layers.

Enhancing Semantic Segmentation of Aerial Images with Inhibitory Neurons

Self-attention and encoder-decoder have been widely used in the deep neural network for monocular depth estimation. The self-attention mechanism is capable of capturing long-range dependencies, while the encoder-decoder structure can capture detailed structural information by gradually recovering spatial information. In this work, we combine the advantages of both methods. Specifically, our proposed model, DGNet, extends EMANet by adding an effective decoder module to progressively refine the coarse depth map. In the decoder stage, we design a dynamic guided upsampling module that employs a dynamically generated kernel conditioned on low-level features to guide the upsampling of the coarse depth map.

Dynamic Guided Network for Monocular Depth Estimation


We present a novel deep neural model for text detection in document images. For robust text detection in noisy scanned documents, the advantages of multi-task learning are adopted by adding an auxiliary task of text enhancement. Namely, our proposed model is designed to perform noise reduction and text region enhancement as well as text detection. Moreover, we enrich the training data for the model with synthesized document images that are fully labeled for text detection and enhancement, thus overcome the insufficiency of labeled document image data. For the effective exploitation of the synthetic and real data, the training process is separated in two phases. The first phase is training only synthetic data in a fully-supervised manner. Then real data with only detection labels are added in the second phase. The enhancement task for the real data is weakly-supervised with information from their detection labels. Our methods are demonstrated in a real document dataset with performances exceeding those of other text detection methods. Moreover, ablations are conducted and the results confirm the effectiveness of the synthetic data, auxiliary task, and weak-supervision. Whereas the existing text detection studies mostly focus on the text in scenes, our proposed method is optimized to the applications for the text in scanned documents.

DUET: Detection Utilizing Enhancement for Text in Scanned or Captured Documents

Understanding video content and generating caption with context is an important and challenging task. Unlike prior methods that typically attempt to generate generic video captions without context, our architecture contextualizes captioning by infusing extracted information from relevant text data. 
We propose an end-to-end sequence-to-sequence model which generates video captions based on visual input, and mines relevant knowledge such as names and locations from contextual text. In contrast to previous approaches, we
do not preprocess the text further, and let the model directly learn to attend over it. Guided
by the visual input, the model is able to copy words from the contextual text via a pointer-generator
network, allowing to produce more specific video captions. 
We show competitive performance on the News Video Dataset and, through ablation studies, validate the efficacy of contextual video captioning as well as individual design choices in our model architecture.

Enriching Video Captions With Contextual Text


Contextualized representations from a pre-trained language model are central to achieve a high performance on downstream NLP task. The pre-trained BERT and A Lite BERT (ALBERT) models can be fine-tuned to give state-of-the-art results in sentence-pair regressions such as semantic textual similarity (STS) and natural language inference (NLI). Although BERT-based models yield the [CLS] token vector as a reasonable sentence embedding, the search for an optimal sentence embedding scheme remains an active research area in computational linguistics. This paper explores on sentence embedding models for BERT and ALBERT. In particular, we take a modified BERT network with siamese and triplet network structures called Sentence-BERT (SBERT) and replace BERT with ALBERT to create Sentence-ALBERT (SALBERT). We also experiment with an outer CNN sentence-embedding network for SBERT and SALBERT. We evaluate performances of all sentence-embedding models considered using the STS and NLI datasets. The empirical results indicate that our CNN architecture improves ALBERT models substantially more than BERT models for STS benchmark. Despite significantly fewer model parameters, ALBERT sentence embedding is highly competitive to BERT in downstream NLP evaluations.

Downloads

Next from ICPR 2020

A Few-shot Learning Approach for Historical Ciphered Manuscript Recognition

Similar lecture

Revisiting Optical Flow Estimation in 360 Videos