Italy

Human pose estimation - the process of recognizing human keypoints in a given image - is one of the most important tasks in computer vision and has a wide range of applications including movement diagnostics, surveillance, or self-driving vehicle. The accuracy of human keypoint prediction is increasingly improved thanks to the burgeoning development of deep learning. Most existing methods solved human pose estimation by generating heatmaps in which the ith heatmap indicates the location confidence of the ith keypoint. In this paper, we introduce novel network structures referred to as multi-resolution representation learning for human keypoint prediction. At different resolutions in the learning process, our networks branch off and use extra layers to learn heatmap generation. We firstly consider the architectures for generating the multi-resolution heatmaps after obtaining the lowest-resolution feature maps. Our second approach allows learning during the process of feature extraction in which the heatmaps are generated at each resolution of the feature extractor. The first and second approaches are referred to as multi-resolution heatmap learning and multi-resolution feature map learning respectively. Our architectures are simple yet effective, achieving good performance. We conducted experiments on two common benchmarks for human pose estimation: MSCOCO and MPII dataset.

ICPR 2020

Simple Multi-Resolution Representation Learning for Human Pose Estimation

multi-resolution feature map learning

multi-resolution heatmap learning

human pose estimation

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

Context is known to be one of crucial factors effecting the performance improvement of semantic segmentation. However, state-of-the-art segmentation models built upon fully convolutional networks are inherently weak in encoding contextual information because of stacked local operations such as convolution and pooling. Failing to capture context leads to inferior segmentation performance. Despite many context modules have been proposed to relieve this problem, they still operate in a local manner or use the same contextual information in different positions (due to upsampling). In this paper, we introduce the idea of Multi-Direction Convolution (MDC)—a novel operator capable of encoding rich contextual information. This operator is inspired by an observation that the standard convolution only slides along the spatial dimension (x, y direction) where the channel dimension (z direction) is fixed, which renders slow growth of the receptive field (RF). If considering the channel-fixed convolution to be one-direction, MDC is multi-direction in the sense that MDC slides along both spatial and channel dimensions, i.e., it slides along x, y when z is fixed, along x, z when y is fixed, and along y, z when x is fixed. In this way, MDC is able to encode rich contextual information with the fast increase of the RF. Compared to existing context modules, the encoded context is position-sensitive because no upsampling is required. MDC is also efficient and easy to implement. It can be implemented with few standard convolution layers with permutation. We show through extensive experiments that MDC effectively and selectively enlarges the RF and outperforms existing contextual modules on two standard benchmarks, including Cityscapes and PASCAL VOC2012.

Multi-Direction Convolution for Semantic Segmentation

Self-supervised learning is a thriving research direction since it can relieve the burden of human labeling for machine learning by seeking for supervision from data
instead of human annotation. Although demonstrating promising performance in various applications, we observe that the existing methods usually model the auxiliary learning tasks as classification tasks with finite discrete labels, leading to
insufficient supervisory signals, which in turn restricts the representation quality. In this paper, to solve the above problem and make full use of the supervision from data, we design a regression model to predict the continuous parameters of a group of transformations, i.e., image rotation, translation, and scaling. Surprisingly, this naive modification stimulates tremendous potential from data and the resulting supervisory signal has largely improved the performance of image representation learning. Extensive experiments on four image datasets, including CIFAR10, CIFAR100, STL10, and SVHN, indicate that our proposed algorithm outperforms the state-of-the-art unsupervised learning methods by a large margin in terms of classification accuracy. Crucially, we find that with our proposed training mechanism as an initialization, the performance of the existing state-of-the-art classification deep architectures can be preferably improved.

Image Representation Learning by Transformation Regression

We present a module that extends the temporal graph of a graph convolutional network (GCN) for action recognition with a sequence of skeletons. Existing methods attempt to represent a more appropriate spatial graph on an intra-frame, but disregard optimization of the temporal graph on the inter-frame. Concretely, these methods connect between vertices corresponding only to the same joint on the inter-frame. In this work, we focus on adding connections to neighboring multiple vertices on the inter-frame and extracting additional features based on the ex-tended temporal graph. Our module is a simple yet effective method to extract correlated features of multiple joints in human movement. Moreover, our module aids in further performance improvements, along with other GCN methods that optimize only the spatial graph. We conduct extensive experiments on two large datasets, NTU RGB+D and Kinetics-Skeleton, and demonstrate that our module is effective for several existing models and our final model achieves state-of-the-art performance.

Temporal Extension Module for Skeleton-Based Action Recognition

Recent research has revealed that deep neural networks are highly vulnerable to adversarial examples. In this paper, different from most adversarial attacks which directly modify pixels in spatial domain, we propose a novel black-box attack in frequency domain, named as \textit{f-mixup}, based on the property of natural images and perception disparity between human-visual system (HVS) and convolutional neural networks (CNNs): First, natural images tend to have the bulk of their Fourier spectrums concentrated on the low frequency domain; Second, HVS is much less sensitive to high frequencies while CNNs can utilize both low and high frequency information to make predictions. Extensive experiments are conducted and show that deeper CNNs tend to concentrate more on the higher frequency domain, which may explain the contradiction between robustness and accuracy. In addition, we compared \textit{f-mixup} with existing attack methods and observed that our approach possesses great advantages. Finally, we show that \textit{f-mixup} can be also incorporated in training to make deep CNNs defensible against a kind of perturbations effectively.

F-mixup: Attack CNNs From Fourier Perspective

Visual tracking serves as a significant module in many applications. However, the heavy computation and low speed of many recent trackers restrict their applications in some computing power restricted scenarios. On the other hand, the simple update scheme of most correlation filter based trackers limits their robustness during target deformation and occlusion. In this paper, we explore the update scheme of correlation filter based trackers and propose an efficient and adaptive training sample update scheme. Training sample extracted in each frame is updated to the training set according to its distance between existing samples measured with difference hashing algorithm(DHA) or discarded according to tracking result reliability. Experiments on OTB-2015, Temple Color 128 and UAV123 demonstrate our tracker performs favourably against state-of-the-art trackers with light computation and runs over 100 fps on desktop computer with Intel i7-8700 CPU(3.2GHz).

Efficient correlation filter tracking with adaptive training sample update scheme


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.

Enhanced User Interest and Expertise Modeling for Expert Recommendation

Predicting which part of a scene elderly people would pay attention to could be useful in assisting their daily activities, such as driving, walking, and searching. Many computational models for predicting focus of attention (FoA) have
been developed. However, most of them focus on mimicking adult FoA and do not work well for predicting elderly’s, due to age-related changes in human vision. Is it possible to leverage the prediction results made by an FoA model of general adults to accurately predict elderly’s FoA, rather than training a new network from scratch? In this paper, we consider a novel problem of translating adult’s FoA to elderly’s and propose an approach based on deep image-to-image translation. Our model is trained by minimizing both Kullback-Leibler divergence and adversarial loss to approximate the joint probability distribution of adult and elderly FoA. Experiments on two datasets demonstrate that our model gives remarkable prediction accuracy.

Translating Adult’s Focus of Attention to Elderly’s

In supervised classiﬁcation, the learning process typically trains a classiﬁer to optimize the accuracy of classifying data into the classes that appear in the learning set, and only them. While this framework ﬁts many use cases, there are situations where the learning process is knowingly performed using a learning set that only represents the data that have been observed so far among a virtually unconstrained variety of possible samples. It is then crucial to deﬁne a classiﬁer which has the ability to reject a sample, i.e., to classify it into a rejection class that has not been yet deﬁned. Although obvious solutions can add this ability a posteriori to a classiﬁer that has been learned classically, a better approach seems to directly account for this requirement in the classiﬁer design. In this presentation, we propose an innovative learning strategy for supervised classiﬁcation that is able, by design, to reject a sample as not belonging to any of the known classes. For that, we rely on modeling each class as the combination of a probability density function (PDF) and a threshold that is computed with respect to the other classes. Several alternatives are compared and the best result is presented in this framework.

How to deﬁne a rejection class based on model learning?

Existing deep siamese trackers are typically built on off-the-shelf CNN models for feature learning, with the demand for huge power consumption and memory storage. This limits current deep siamese trackers to be carried on resource-constrained devices like mobile phones. In this work, we address this issue by presenting a novel Distilled Learning Framework(DLF) for siamese tracking, which aims at learning tracking models with efficiency and high accuracy. Specifically, we propose two simple yet effective knowledge distillation strategies, denote as point-wise distillation and pairwise distillation, which are designed for transferring knowledge from a more discriminative teacher tracker into a compact student tracker. In this way, cost-effective and high performance tracking could be achieved. Extensive experiments on several tracking benchmarks demonstrate the effectiveness of our proposed method.

Exploiting Distilled Learning for Deep Siamese Tracking


Group retrieval has attracted plenty of attention in artificial intelligence, traditional group retrieval researches assume that members in a group are unique and do
not change under different cameras. However, the assumption may not be met for practical situations such as open-world and group-ambiguity scenarios. This paper tackles an important yet non-studied problem: re-identifying changing groups of people under the open-world and group-ambiguity scenarios in different camera fields. The open-world scenario considers that there are probably non-target
people for the probe set appear in the searching gallery, while the group-ambiguity scenario means the group members may change. The open-world and group-ambiguity issue is very challenging for the existing methods because the changing of group members results in dramatic visual variations. Nevertheless, as far as we know, the existing literature lacks benchmarks which target on coping with this issue. In this paper, we propose a new group retrieval dataset named OWGA-Campus to consider these challenges. Moreover, we propose a person-to-group similarity matching based ambiguity removal (P2GSM-AR) method to solve these
problems and realize the intention of group retrieval. Experimental results on OWGA-Campus dataset demonstrate the effectiveness and robustness of the proposed P2GSM-AR approach in improving the performance of the state-of-the-art feature extraction methods of person re-id towards the open-world and ambiguous group retrieval task.

Premium content

Simple Multi-Resolution Representation Learning for Human Pose Estimation

Downloads

Next from ICPR 2020

Multi-Direction Convolution for Semantic Segmentation

Similar lecture

RefiNet: 3D Human Pose Refinement with Depth Maps