Italy

Recent developments in the field of Visual Question Answering (VQA) have witnessed promising improvements in performance through contributions in attention based networks. Most such approaches have focused on unidirectional attention that leverage over attention from textual domain (question) on visual space. These approaches mostly focused on learning high-quality attention in the visual space. In contrast, this work proposes an alternating bi-directional attention framework. First, a question to image attention helps to learn the robust visual space embedding, and second, an image to question attention helps to improve the question embedding. This attention mechanism is realized in an alternating fashion i.e. question-to-image followed by image-to-question and is repeated for maximizing performance. We believe that this process of alternating attention generation helps both the modalities and leads to better representations for the VQA task. This proposal is benchmark on TDIUC dataset and against state-of-art approaches. Our ablation analysis shows that alternate attention is the key to achieve high performance in VQA.

ICPR 2020

Multistage Attention based Visual Question Answering

attention network

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


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.

Improved Residual Networks for Image and Video Recognition

We propose a monocular vision assisted localization algorithm, that will help a UAV navigate safely in indoor corridor environments. Always, the aim is to navigate the UAV through a corridor in the forward direction by keeping it at the center with no orientation either to the left or right side. The algorithm makes use of the RGB image, captured from the UAV front camera, and passes it through a trained Deep Neural Network (DNN) to predict the position of the UAV as either on the left or center or right side of the corridor. Depending upon the divergence of the UAV with respect to an imaginary central line, known as the central bisector line (CBL) of the corridor, a suitable command is generated to bring the UAV to the center. When the UAV is at the center of the corridor, a new image is passed through another trained DNN to predict the orientation of the UAV with respect to the CBL of the corridor. If the UAV is either left or right tilted, an appropriate command is generated to rectify the orientation. We also propose a new corridor dataset, named UAVCorV1, which contains images as captured by the UAV front camera when the UAV is at all possible locations of a variety of corridors. An exhaustive set of experiments in different corridors reveal the efficacy of the proposed algorithm.

Localization of Unmanned Aerial Vehicles in Corridor Environments using Deep Learning

Nowadays many deep learning algorithms have been employed to solve different types of problems in the area of computer vision; however, most of them require a great amount of training data and tend to struggle in few-shot learning tasks. On the other hand, those methods designed for few-shot learning usually face the difficulty that once one or more samples show a relatively large bias, the predicted result may be much less reliable due to the fact that the sample will cause a large shift of class-level features during few-shot learning. To solve this problem, this paper presents a novel and Iterative Feature Selection Mechanism (IFSM) for few-shot image classification, which can be applied to lots of metric-based few-shot learners.
IFSM learns to construct a more feasible class-level feature which is less affected by samples with relatively large biases, using an iterative approach. The proposed mechanism is tested on three previous state-of-the-art few-shot learning methods, and the experimental results show that the proposed mechanism considerably improves (by 1% to 2%) the image classification accuracies of both methods on the miniImagenet, tieredImagenet or CUB benchmarks in 5-way 5-shot tasks. This approves the effectiveness and generality of the proposed mechanism.


IFSM: A Iterative Feature Selection Mechanism for Few-Shot Image Classification

Recent researches demonstrate that correlation
modeling plays a key role in high-performance multi-label
classification methods. However, existing methods do not take
full advantage of correlation information, especially correla-
tions in feature and label spaces of each image, which limits
the performance of correlation-based multi-label classification
methods. With more correlations considered, in this study, a
Fully Associative Network (FAN) is proposed for fully exploiting
correlation information, which involves both visual feature and
label correlations. Specifically, FAN introduces a robust covari-
ance pooling to summarize convolution features as global image
representation for capturing feature correlation in the multi-label
task. Moreover, it constructs an effective label correlation matrix
based on a re-weighted scheme, which is fed into a graph convo-
lution network for capturing label correlation. Then, correlation
between covariance representations (i.e., feature correlation ) and
the outputs of GCN (i.e., label correlation) are modeled for final
prediction.

More Correlations Better Performance：Fully Associative Networks for Multi-label Image Classification

Racing bib number (RBN) detection and recognition is a specific problem related to text recognition in natural scenes. In this paper, we present a novel dataset created after registering participants in a real ultrarunning competition which comprises a wide range of acquisition conditions in five different recording points, including nightlight and daylight. The dataset contains more than 3k samples of over 400 different individuals. The aim is at providing an in the wild benchmark for both RBN detection and recognition problems. To illustrate the present difficulties, the dataset is evaluated for RBN detection using different Faster R-CNN specific detection models, filtering its output with heuristics based on body detection to improve the overall detection performance. Initial results are promising, but there is still a significant room for improvement. And detection is just the first step to accomplish in the wild RBN recognition.

TGCRBNW: A dataset for runner bib number detection (and recognition) in the wild

Data distributions in streaming environments are usually not stationary. In order to maintain a high predictive quality at all times, online learning models need to adapt to distributional changes, which are known as concept drift. The timely and robust identification of concept drift can be difficult, as we never have access to the true distribution of streaming data. In this work, we propose a novel framework for the detection of real concept drift, called ERICS. By treating the parameters of a predictive model as random variables, we show that concept drift corresponds to a change in the distribution of optimal parameters. To this end, we adopt common measures from information theory. The proposed framework is completely model-agnostic. By choosing an appropriate base model, ERICS is also capable to detect concept drift at the input level, which is a significant advantage over existing approaches. An evaluation on several synthetic and real-world data sets suggests that the proposed framework identifies concept drift more effectively and precisely than various existing works.

Learning Parameter Distributions to Detect Concept Drift in Data Streams

Facial Expression Recognition (FER) is a challenging
task because many factors of variation such as pose,
illumination and identity-specific attributes are entangled with
the expression information in an expressive face image. Recent
works show that the performance of a FER algorithm
can be improved by disentangling the expression information
from identity features. In this paper, we present Transferbased
Expression Recognition Generative Adversarial Network
(TER-GAN) that combines the effectiveness of a novel feature
disentanglement technique with the concept of identity-invariant
expression representation learning for FER. More specifically,
TER-GAN learns a disentangled expression representation by
extracting expression features from one image and transferring
the expression information to the identity of another image. To
improve the feature disentanglement process and to learn an
identity-invariant expression representation, we introduce a novel
expression consistency loss and an identity consistency loss that
exploit expression and identity information from both real and
synthetic images. We evaluated the performance of our proposed
facial expression recognition technique by employing four public
facial expression databases, CK+, Oulu-CASIA, MMI, BU-3DFE.
The experimental results show the effectiveness of the proposed
technique.

Facial Expression Recognition By Using a Disentangled Identity-Invariant Expression
Representation

Vision is the first indicator for coaches to assess the quality of a sport gesture. However, gesture analysis using computer vision is often restricted to laboratory experiments, far from the real conditions in which athletes train on a daily basis. In this perspective, we introduce 3D ball trajectories analysis using a single camera with very few acquisition constraints. A key point of the proposal is the estimation of the apparent ball size for obtaining ball to camera distance. For this purpose, a 2D CNN is trained using a generated dataset that enables a reliable ball size extraction, even in case of high motion blur. The final objective is not only to be able to determine ball trajectories, but most importantly to retrieve their relevant physical parameters. Those kinematics parameters could help coaches and players to better analyze strokes with strong rotation effects during training sessions or matches. With a precise estimation of those trajectories, it is indeed possible to extract the ball tangential and rotation speed, related to the so-called Magnus effect. Validation experiments for characterizing table tennis strokes are presented on both a synthetic dataset and on real video sequences.

Extraction and analysis of 3D kinematic parameters of Table Tennis ball from a single camera

Video object segmentation(VOS) has been a fundamental topic in recent years, and many deep learning-based methods have achieved state-of-the-art performance on multiple benchmarks. However, most of these methods rely on pixel-level matching between the template and the searched frames on the whole image while the targets only occupy a small region. Calculating on the entire image brings lots of additional computation cost. Besides, the whole image may contain some distracting information resulting in many false-positive matching points. We propose an efficient siamese dynamic mask estimation network for fast video object 
segmentation. The VOS is decoupled into two tasks, i.e., mask feature learning
and dynamic kernel prediction.

Siamese Dynamic Mask Estimation Network for Fast Video Object Segmentation

State-of-the-art, high capacity deep neural networks not only require large amounts of labelled training data, they are also highly susceptible to labelling errors in this data, typically resulting in large efforts and costs and therefore limiting the applicability of deep learning. To alleviate this issue, we propose a novel meta training and labelling scheme that is able to use inexpensive unlabelled data by taking advantage of the generalization power of deep neural networks. We show experimentally that by solely relying on one network architecture and our proposed scheme of combining self-training with pseudolabels, both label quality and resulting model accuracy, can be improved significantly. Our method achieves state-of-the-art results, while being architecture agnostic and therefore broadly applicable. Compared to other methods dealing with erroneous labels, our approach does neither require another network to be trained, nor does it necessarily need an additional, highly accurate reference label set. Instead of removing samples from a labelled set, our technique uses additional sensor data without the need for manual labelling. Furthermore, our approach can be used for semi-supervised learning.

Premium content

Downloads

Next from ICPR 2020

Improved Residual Networks for Image and Video Recognition

Similar lecture

Question Agnostic Attention for Visual Question Answering