Italy

Crowd counting plays an increasingly important role in public security. Recently, many crowd counting methods for a single image have been proposed but few studies have focused on using temporal information from image sequences of videos to improve prediction performance. In the existing methods using videos for crowd estimation, temporal features and spatial features are modeled jointly for the prediction, which makes the model less efficient in extracting spatiotemporal features and difficult to improve the performance of predictions. In order to solve these problems, this paper proposes a Parasite-Host Network (PHNet) which is composed of Parasite branch and Host branch to extract temporal features and spatial features respectively. To specifically extract the transform features in the time domain, we propose a novel architecture termed as “Relational Extractor”(RE) which models the multiplicative interaction features of adjacent frames. In addition, the Host branch extracts the spatial features from a current frame which can be replaced with any model that uses a single image for the prediction. We conducted experiments by using our PHNet on four video crowd counting benchmarks: Venice,UCSD,FDST and CrowdFlow. Experimental results show that PHNet achieves superior performance on these four datasets to the state-of-the- art methods.

ICPR 2020

PHNet: Parasite-Host Network for Video Crowd Counting

pattern recognition

crowd counting

deep learning

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

We consider the problem of object segmentation in cultural sites. Since collecting and labeling large datasets of real images is challenging, we investigate whether the use of synthetic images can be useful to achieve good segmentation performance on real data. To perform the study, we collected a new dataset comprising both real and synthetic images of 24 artworks in a cultural site. The synthetic images have been automatically generated from the 3D model of the considered cultural site using a tool developed for that purpose. Real and synthetic images have been labeled for the task of semantic segmentation of artworks. We compare three different approaches to perform object segmentation exploiting real and synthetic data. The experimental results point out that the use of synthetic data helps to improve the performances of segmentation algorithms when tested on real images. Satisfactory performance is achieved exploiting semantic segmentation together with image-to-image translation and including a small amount of real data during training. To encourage research on the topic, we publicly release the proposed dataset at the following url: https://iplab.dmi.unict.it/EGO-CH-OBJ-SEG/

Semantic Object Segmentation in Cultural Sites using Real and Synthetic Data

With the prosperous development of Convolutional Neural Networks, currently they can perform excellently on visual understanding tasks when the input images are high quality and common quality images. However, large degradation in performance always occur when the input images are low quality images. In this paper, we propose a new super-resolution method in order to improve the classification performance for low-resolution images. In an image, the regions in which pixel values vary dramatically contain more abundant high frequency contents compared to other parts. Based on this fact, we design a weight map and integrate it with a super-resolution CNN training framework. During the process of training, this weight map can find out positions of the high frequency pixels in ground truth high-resolution images. After that, the pixel-level loss function takes effect only at these found positions to minimize the difference between reconstructed high-resolution images and ground truth high-resolution images. Compared with other state-of-the-art super-resolution methods, the experiment results show that our method can recover more high frequency contents in high-resolution image reconstructing, and better improve the classification accuracy after low-resolution image preprocessing.

Improving Low-Resolution Image Classification by Super-Resolution with Enhancing High-Frequency Content

Modern convolutional networks such as ResNet and NASNet have achieved state-of-the-art results in many computer vision applications. These architectures consist of stages, which are sets of layers that operate on representations in the same resolution. It has been demonstrated that increasing the number of layers in each stage improves the prediction ability of the network. However, the resulting architecture becomes computationally expensive in terms of floating point operations, memory requirements and inference time. Thus, significant human effort is necessary to evaluate different trade-offs between depth and performance. To handle this problem, recent works have proposed to automatically design high-performance architectures, mainly by means of neural architecture search (NAS). Current NAS strategies analyze a large set of possible candidate architectures and, hence, require vast computational resources and take many GPUs days. Motivated by this, we propose a NAS approach to efficiently design accurate and low-cost convolutional architectures and demonstrate that an efficient strategy for designing these architectures is to learn the depth stage-by-stage. For this purpose, our approach increases depth incrementally in each stage taking into account its importance, such that stages with low importance are kept shallow while stages with high importance become deeper. We conduct experiments on the CIFAR and different versions of ImageNet datasets, where we show that architectures discovered by our approach achieve better accuracy and efficiency than human-designed architectures. Additionally, we show that architectures discovered on CIFAR-10 can be successfully transferred to large datasets. Compared to previous NAS approaches, our method is substantially more efficient, as it evaluates one order of magnitude fewer models and yields architectures on par with the state-of-the-art.

Stage-Wise Neural Architecture Search

Since gaze estimation plays a crucial role in recognizing human intentions, it has been researched for a long time, and its accuracy is ever increasing. However, due to the wide variation in eye shapes and focusing abilities between the individuals, accuracies of most algorithms vary depending on each person in the test group, especially when the initial calibration is not well performed. To alleviate the user-dependency, we attempt to derive features that are general for most people and use them as the input to a deep network instead of using the images as the input. Specifically, we use the pupil shape as the core feature because it is directly related to the 3D eyeball rotation, and thus the gaze direction. While existing deep learning
methods learn the gaze point by extracting various features from the image, we focus on the mapping function from the eyeball rotation to the gaze point by using the pupil shape as the input. It is shown that the accuracy of gaze point estimation also becomes robust for the uncalibrated points by following the characteristics of the mapping function. Also, our gaze network learns the gaze difference to facilitate the re-calibration process to fix the calibration-drift problem that typically occurs with glass-type or head-mount devices.


User-Independent Gaze Estimation by Extracting Pupil Parameter and Its Mapping to the Gaze Angle

Activation in deep neural networks is fundamental to achieving non-linear mappings. Traditional studies mainly focus on finding fixed activations for a particular set of learning tasks or model architectures. The research on flexible activation is quite limited in both designing philosophy and application scenarios. In this study, three principles of choosing flexible activation components are proposed and a general combined form of flexible activation functions is implemented. Based on this, a novel family of flexible activation functions that can replace sigmoid or tanh in LSTM cells are implemented, as well as a new family by combining ReLU and ELUs. Also, two new regularisation terms based on assumptions as prior knowledge are introduced. It has been shown that LSTM models with proposed flexible activations P-Sig-Ramp provide significant improvements in time series forecasting, while the proposed P-E2-ReLU achieves better and more stable performance on lossy image compression tasks with convolutional auto-encoders. In addition, the proposed regularization terms improve the convergence, performance and stability of the models with flexible activation functions.

Regularized Flexible Activation Function Combinations for Deep Neural Networks


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.

Vacant Parking Space Detection based on Task Consistency and Reinforcement Learning

Face anti-spoofing is an important problem for both academic research and industrial face recognition systems. Most of the existing face anti-spoofing methods take it as a classification task on individual static images, where motion pattern differences in consecutive real or fake face sequences are ignored. In this work, we propose a novel method to identify spoofing patterns using motion information. Different from previous methods, the proposed method makes the real or fake decision on the disentangled feature level, based on the observation that motion and spoofing pattern features could be disentangled from original image frames. We design a representation disentangling frame- work for this task, which is able to reconstruct both real and fake face sequences from the input. Meanwhile, the disentangled representations could be used to classify whether the input faces are real or fake. We perform several experiments on Casia-FASD and ReplayAttack datasets. The proposed method achieves SOTA results compared with existing face anti-spoofing methods.

Disentangled Representation based Face Anti-Spoofing

High-speed camera imaging (e.g., 1,000 fps) is effective to detect and recognize objects moving at high speeds because temporally dense images obtained by a high-speed camera can usually capture the best moment for object detection and recognition. However, the latest recognition algorithms, with their high complexity, are difficult to utilize in real-time applications involving high-speed cameras because a vast number of images need to be processed with no latency. To tackle this problem, we propose a novel framework for real-time object recognition with high-speed camera imaging. The proposed framework has the key processes of population data cleansing and data ensemble. Population data cleansing improves the recognition accuracy by quantifying the recognizability and by excluding part of the images prior to the recognition process, while data ensemble improves the robustness of object recognition by merging the class probabilities with multiple images from the object tracking sequence. Experimental results with a real dataset show that our framework is more effective than existing methods.

Online Object Recognition Using CNN-based Algorithm on High-speed Camera Imaging

We address a novel problem of stylized-colorization which colorizes a given line art using a given coloring style in text. We propose a GAN- based end-to-end model for stylized-colorization where the model has one generator and two discriminators. Extensive experiments demonstrate the effectiveness of our proposed model.

Stylized-Colorization for Line Arts

Visual dialog is a typical multi-modal task which involves both vision and language. Nowadays, it faces two major difficulties. In this paper, we propose the Integrating Historical States and Co-attention (HSCA) for visual dialog to solve them. It includes two main modules, Co-ATT and MATCH. Specifically, the main purpose of the Co-ATT module is to guide the image with questions and answers in the early stage to get more specific objects. It tackles the first difficulty of the temporal sequence issue in historical information which may influence the precise answer for multi-round questions. The MATCH module is, based on a question with pronouns, to retrieve the best matching historical information block. It overcomes the second difficulty of the visual reference problem which requires to solve pronouns referring to unknowns in the text message and then to locate the objects in the given image. We quantitatively and qualitatively evaluate our model on VisDial v1.0, at the same time, ablation studies are carried out. The experimental results demonstrate that HSCA outperforms the state-of-the-art methods in many aspects.

Premium content

Downloads

Next from ICPR 2020

Semantic Object Segmentation in Cultural Sites using Real and Synthetic Data

Similar lecture

Learning from Web Data: Improving Crowd Counting via Semi-Supervised Learning