Italy


In this work, we address the problem of audio-based near-duplicate video retrieval. We propose the Audio Similarity Learning (AuSiL) approach that effectively captures temporal patterns of audio similarity between video pairs. For the robust similarity calculation between two videos, we first extract representative audio-based video descriptors by leveraging transfer learning based on a Convolutional Neural Network (CNN) trained on a large scale dataset of audio events, and then we calculate the similarity matrix derived from the pairwise similarity of these descriptors. The similarity matrix is subsequently fed to a CNN network that captures the temporal structures existing within its content. We train our network following a triplet generation process and optimizing the triplet loss function. To evaluate the effectiveness of the proposed approach, we have manually annotated two publicly available video datasets based on the audio duplicity between their videos. The proposed approach achieves very competitive results compared to three state-of-the-art methods. Also, unlike the competing methods, it is very robust to the retrieval of audio duplicates generated with speed transformations.

ICPR 2020

Audio-based Near-Duplicate Video Retrieval with Audio Similarity Learning

audio processing

video retrieval

convolutional neural networks

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


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.

Drift anticipation with forgetting to improve evolving fuzzy system


The performance of an audio-visual sound source separation system is determined by its ability to separate audio sources given the images of the sources and the audio mixture. The goal of this study is to investigate the ability to learn the map-ping between the sounds and the images of instruments in the self-supervisied mix-and-seperate training paradigm used by state-of-the-art audio-visual sound source separation methods. Theoretical and empirical analyses illustrate that the self-supervised mix-and-separate training does not automatically learn the 1-to-1 correspondence between visual and audio signals, leading to low audio-visual object classification accuracy. Based on this analysis, a weakly-supervised method called Object-Prior is proposed and evaluated on two audio-visual datasets. The experimental results show that the Object-Prior method outperforms state-of-the-art baselines in the audio-visual sound source separation task. It is also more robust against asynchronized data, where the frame and the audio do not come from the same video, and recognizes musical instruments based on their sound with higher accuracy. This indicates that learning the 1-to-1 correspondence between visual and audio features of an instrument improves the effectiveness of audio-visual sound source separation.

Improving Mix-and-Separate Training in Audio-Visual Sound Source Separation with an Object Prior

Hcore-Init: Neural Network Initialization based on Graph Degeneracy

Human activity recognition plays a central role in the development of intelligent systems for video surveillance, public security, health care and home monitoring, where detection and recognition of activities can improve the quality of life and security of humans. Typically, automated, intuitive and real-time systems are required to recognize human activities and identify accurately unusual behaviors in order to prevent dangerous situations. In this work, we explore the combination of three modalities (RGB, depth and skeleton data) to design a robust multi-modal framework for vision-based human activity recognition. Especially, spatial information, body shape/posture and temporal evolution of actions are highlighted using illustrative representations obtained from a combination of dynamic RGB images, dynamic depth images and skeleton data representations. Therefore, each video is represented with three images that summarize the ongoing action. Our framework takes advantage of transfer learning from pre-trained models to extract significant features from these newly created images. Next, we fuse extracted features using Canonical Correlation Analysis and train a Long Short-Term Memory network to classify actions from visual descriptive images. Experimental results demonstrated the reliability of our feature-fusion framework that allows us to capture highly significant features and enables us to achieve the state-of-the-art performance on the public UTD-MHAD and NTU RGB+D datasets.

Vision-Based Multi-Modal Framework for Action Recognition

Most existing works regarding facial demographic estimation are focused on still image datasets, although nowadays the need to analyze video content in real applications is increasing. We propose to tackle gender, age and ethnicity estimation in the context of video scenarios. Our main contribution is to use an attribute-specific quality assessment procedure to select most relevant frames from a video sequence for each of the three demographic modalities. Selected frames are classified with fine-tuned MobileNet models and a final video prediction is obtained with a majority voting strategy. Our validation on three different datasets and our comparison with state-of-the art models, show the effectiveness of the proposed demographic classifiers and the quality pipeline, which allows to reduce both: the number of frames to be classified and the processing time in practical applications; and improves the soft biometrics prediction accuracy.

Attribute-based quality assessment for demographic estimation in face videos

Convolutional neural networks are shown to be vulnerable to changes in the background. The proposed method is an end-to-end method that augments the training set by introducing new backgrounds during the training process. These backgrounds are created by a generative network that is trained as an adversary to the model. A case study is explored based on overhead power line insulators detection using a drone – a training set is prepared from photographs taken inside a
laboratory and then evaluated using photographs that are harder to collect from outside the laboratory. The proposed method improves performance by over 20% for this case study.

Background Invariance by Adversarial Learning




Recognizing human activities from multi-channel time series data collected from wearable sensors has become an important practical application of machine learning. A serious challenge comes from the presence of coherent activities or body movements, such as movements of the head while walking or sitting, since signals representing these movements are mixed and interfere with each other. Basic multi-label classification typically assumes independence within the multiple activities. This is over-simplified and reduces modeling power even when using state-of-the-art deep learning methods. In this paper, we investigate this new problem, which we name ``Coherent Human Activity Recognition (Co-HAR)'', that keeps complete conditional dependency between the multiple labels. Additionally, we treat Co-HAR as a dense labeling problem that classifies each sample on a time step with multiple coherent labels to provide high-fidelity and duration-sensitive support to high-precision applications. To explicitly model conditional dependency, a novel condition-aware deep architecture ``Conditional-UNet'' is developed to allow for multiple dense labeling for Co-HAR. We also contribute a first-of-its-kind Co-HAR dataset for head gesture recognition associated with a user's activity, walking or sitting, to the research community. Extensive experiments on this dataset show that our model outperforms state-of-the-art deep learning methods and achieves up to 92% accuracy on context-based head gesture classification.

Conditional-UNet: A Condition-aware Deep Model for Coherent Human Activity Recognition From Wearables

This article proposes a novel attention-based body-pose encoding for human activity recognition. Most of the existing human activity recognition approaches based on 3D pose data often enrich the input data using additional handcrafted representations such as velocity, super-normal vectors, pairwise relations, and so on. The enriched data complements the 3Dbody joint position data and improves model performance. In this paper, we propose a novel approach that learns enhanced feature representations from a given sequence of 3D body joints.To achieve this encoding, the approach exploits two body pose streams: 1) a spatial stream which encodes the spatial relationship between various body joints at each time point to learn spatial structure involving the spatial distribution of different body joints 2) a temporal stream that learns the temporal variation of individual body joints over the entire sequence duration to present a temporally enhanced representation. Afterwards,these two pose streams are fused with a multi-head attention mechanism. We also capture the contextual information from the RGB video stream using a deep Convolutional NeuralNetwork (CNN) model combined with a multi-head attention and a bidirectional Long Short-Term Memory (LSTM) network.Finally, the RGB video stream is combined with the fused body-pose stream to give a novel end-to-end deep model for effective human activity recognition.

Attention-Driven Body Pose Encoding for Human Activity Recognition


Accurate and robust detection of objects from
monocular images is a fundamental vision task. This paper
describes a novel approach of holistic scene understanding that
can simultaneously achieve multiple tasks of scene reconstruction
and object detection from a single monocular image. Rather than
pursuing an independent solution for each individual task as
most existing work does, we seek a globally optimal solution that
holistically resolves the multiple perception and reasoning tasks
in an effective manner. The approach explores the complementary
properties of multimodal RGB images and depth data to improve
scene perception tasks. It uniquely combines the techniques
of canonical correlation analysis and deep learning to learn
the most correlated features to maximize the modal crosscorrelation
for improving performance and robustness of object
detection in complex environments. Extensive experiments have
been conducted to evaluate and demonstrate the performances
of the proposed approach.

Object Detection on Monocular Images with Two-Dimensional Canonical Correlation Analysis


Representing brain activities by networks is very crucial to understand various cognitive states. This study proposes a novel method to estimate static and dynamic brain networks using Kulback-Leibler divergence. The suggested brain networks are based on the probability distributions of voxel intensity values measured by functional Magnetic Resonance Images (fMRI) recorded while the subjects perform a predefined cognitive task, called complex problem solving. We investigate the validity of the estimated brain networks by modeling and analyzing the different phases of complex problem solving process of human brain, namely planning and execution phases. The suggested computational network model is tested by a classification schema using Support Vector Machines. We observe that the network models can successfully discriminate the planning and execution phases of complex problem solving process with more than 90% accuracy, when the estimated dynamic networks, extracted from the fMRI data, are classified by Support Vector Machines.

Premium content

Audio-based Near-Duplicate Video Retrieval with Audio Similarity Learning

Downloads

Next from ICPR 2020

Drift anticipation with forgetting to improve evolving fuzzy system

Similar lecture

Estimation of Abundance and Distribution of Salt Marsh Plants from Images Using Deep Learning