Italy

In this work, we propose a long-term RGBD trackerthat achieves state-of-the-art performance on the PrincetonRGBD, STC and CDTB datasets and runs nearly real-time(20fps). The tracker is based on non-stationary formulation of the deep Discriminative Correlation Filter (DCF). The DCFfeature channels are modulated by the depth context in eachlocation which makes the tracker robust against occlusion andbackground clutter. Moreover, the non-stationary DCF also performs well in target re-detection enabling long-term tracking.

ICPR 2020

DAL: A Deep Depth-Aware Long-term Tracker

non-stationary dcf

long-term

rgbd tracking

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 present FourierNet, a single shot, anchor-free, fully convolutional instance segmentation method that predicts a shape vector. Consequently, this shape vector is converted into the masks’ contour points using a fast numerical transform. Compared to previous methods, we introduce a new training technique, where we utilize a differentiable shape decoder, which manages the automatic weight balancing of the shape vector’s coefficients. We used the Fourier series as a shape encoder because of its coefficient interpretability and fast implementation.
FourierNet shows promising results compared to polygon representation methods, achieving 30.6 mAP on the MS COCO 2017 benchmark. At lower image resolutions, it runs at 26.6 FPS with 24.3 mAP. It reaches 23.3 mAP using just eight parameters to represent the mask (note that at least four parameters are needed
for bounding box prediction only). Qualitative analysis shows that suppressing a reasonable proportion of higher frequencies of Fourier series, still generates meaningful masks. These results validate our understanding that lower frequency components hold higher information for the segmentation task, and therefore, we can achieve a compressed representation. Code is available at github.com/cogsys-tuebingen/FourierNet.

FourierNet: Compact Mask Representation for Instance Segmentation Using Differentiable Shape Decoders

Getting deep convolutional neural networks to per- form well requires a large amount of training data. When the available labelled data is small, it is often beneficial to use transfer learning to leverage a related larger dataset (source) in order to improve the performance on the small dataset (target). Among the transfer learning approaches, domain adaptation methods assume that distributions between the two domains are shifted and attempt to realign them. In this paper, we consider the domain adaptation problem from the perspective of multi-view graph embedding and dimensionality reduction. Instead of solving the generalised eigenvalue problem to perform the embedding, we formulate the graph-preserving criterion as a loss in the neural network and learn a domain-invariant feature transformation in an end-to-end fashion. We show that the proposed approach leads to a powerful Domain Adaptation framework which generalises the prior methods CCSA and d- SNE, and enables simple and effective loss designs; an LDA- inspired instantiation of the framework leads to performance on par with the state-of-the-art on the most widely used Domain Adaptation benchmarks, Office31 and MNIST to USPS datasets.

Supervised Domain Adaptation using Graph Embedding

Most state of the art object detectors output multiple detections per object. The duplicates are removed in a post-processing step called Non-Maximum Suppression. Classical Non-Maximum Suppression has shortcomings in scenes that contain objects with high overlap: This heuristic assumes that a high overlap between two bounding boxes corresponds to a high probability of one being a duplicate.
We propose FeatureNMS to solve this problem. FeatureNMS recognizes duplicates not only based on the intersection over union between the bounding boxes, but also based on the difference of feature vectors. These feature vectors can encode more information like visual appearance. Our approach outperforms classical NMS and derived approaches and achieves state of the art performance.

FeatureNMS: Non-Maximum Suppression by Learning Feature Embeddings

Unsupervised image-to-image translation is an inherently ill-posed problem. Recent methods based on deep encoder-decoder architectures have shown impressive results, but we show that they only succeed due to a strong locality bias, and they fail to learn very simple nonlocal transformations (e.g. mapping upside down faces to upright faces). When the locality bias is removed, the methods are too powerful and may fail to learn simple local transformations. In this paper we introduce linear encoder-decoder architectures for unsupervised image to image translation. We show that learning is much easier and faster with these architectures and yet the results are surprisingly effective. In particular, we show a number of local problems for which the results of the linear methods are comparable to those of state-of-the-art architectures but with a fraction of the training time, and a number of nonlocal problems for which the state-of-the-art fails while linear methods succeed.

The Surprising Effectiveness of Linear Unsupervised Image-to-Image Translation

Extracting features containing both high-resolution and high-level-semantic information is important for human pose estimation, while most existing methods of extracting high-resolution high-level-semantic features suffer from spatial information loss or semantic information mismatch. To efficiently address these issues, we propose a novel Dilation Pyramid Module (DPM), which can enlarge the receptive field multiplicatively to achieve high-level-semantic information as subsampling without reducing spatial resolution. DPM is composed of several consecutive dilated convolution layers of which dilation radius is specially designed to enlarge the receptive field multiplicatively and avoid the gridding issue of dilated convolution. Based on DPM, the Dilation Pyramid Net (DPN) is proposed to efficiently extract high-resolution high-level-semantic features. We experimentally demonstrate the effectiveness and efficiency of the proposed DPN
with comparable performance to the state-of-the-art methods over two challenging benchmark datasets: the COCO keypoint detection dataset and the MPII Human Pose dataset.

Efficient High-Resolution High-Level-Semantic Representation Learning for Human Pose Estimation


Sound event recognition systems are rapidly becoming part of our life, since they can be profitably used in several vertical markets, ranging from audio security applications to scene classification and multi-modal analysis in social robotics. In the last years, a not negligible part of the scientific community started to apply Convolutional Neural Networks (CNNs) to image-based representations of the audio stream, due to their successful adoption in almost all the computer vision tasks.
In this paper, we carry out a detailed benchmark of various widely used CNN architectures and visual representations on a popular dataset, namely the MIVIA Audio Events database. Our analysis is aimed at understanding how these factors affect the sound event recognition performance with a particular focus on the false positive rate, very relevant in audio surveillance solutions. In fact, although most of the proposed solutions achieve a high recognition rate, the capability of distinguishing the events-of-interest from the background is often not yet sufficient for real systems, and prevent its usage in real applications. Our comprehensive experimental analysis investigates this aspect and allows to identify useful design guidelines for increasing the specificity of sound event recognition systems.

Which are the factors affecting the performance of audio surveillance systems?

This paper proposes an attentional network for the task of Continuous Sign Language Recognition. The proposed approach exploits co-independent streams of data to model the sign language modalities. These different channels of information
can share a complex temporal structure between each other. For that reason, we apply attention to synchronize and help capture entangled dependencies between the different sign language components. Even though Sign Language is multi-channel, handshapes represent the central entities in sign interpretation. Seeing handshapes in their correct context defines the meaning of a sign. Taking that into account, we utilize the attention mechanism to efficiently aggregate the hand features with their appropriate spatio-temporal context for better sign recognition.
We found that by doing so the model is able to identify the essential Sign Language components that revolve around the dominant hand and the face areas. We test our model on the benchmark dataset RWTH-PHOENIX-Weather 2014, yielding
competitive results.

Context Matters: Self-Attention for Sign Language Recognition

We introduce TAS500, a novel semantic segmentation dataset for autonomous
driving in unstructured outdoor environments. Using TAS500 as our training
dataset, we study how a more fine-grained labeling policy affects the overall
performance of the semantic segmentation.

A Fine-Grained Dataset and its Efficient Semantic Segmentation for Unstructured Driving Scenarios

In regression tasks, the data distribution is often too complex to be fitted by a single model. In contrast, partition-based models are developed where data is divided and fitted by local models. These models partition the input space and do not leverage the input-output dependency of multimodal- distributed data, and strong local models are needed to make good predictions. Addressing these problems, we propose a binary tree-structured hierarchical routing mixture of experts (HRME) model that has classifiers as non-leaf node experts and simple regression models as leaf node experts. The classifier nodes jointly soft-partition the input-output space based on the natural separateness of multimodal data. This enables simple leaf experts to be effective for prediction. Further, we develop a probabilistic framework for the HRME model and propose a recursive Expectation-Maximization (EM) based algorithm to learn both the tree structure and the expert models. Experiments on a collection of regression tasks validate our method’s effectiveness compared to various other regression models. 


Hierarchical Routing Mixture of Experts

Graph convolutional networks (GCNs) have been very successful in modeling non-Euclidean data structures, like sequences of body skeletons forming actions modeled as spatio-temporal graphs. Most GCN-based action recognition methods use deep feed-forward networks with high computational complexity to process all skeletons in an action. This leads to a high number of floating point operations (ranging from 16G to 100G FLOPs) to process a single sample, making their adoption in restricted computation application scenarios infeasible. 
In this paper, we propose a temporal attention module (TAM) for increasing the efficiency in skeleton-based action recognition by selecting the most informative skeletons of an action at the early layers of the network. We incorporate the TAM in a light-weight GCN topology to further reduce the overall number of computations. 
Experimental results on two benchmark datasets show that the proposed method outperforms with a large margin the baseline GCN-based method while having 2.9 less number of computations. Moreover, it performs on par with the state-of-the-art with up to 9.6 less number of computations.

Downloads

Next from ICPR 2020

FourierNet: Compact Mask Representation for Instance Segmentation Using Differentiable Shape Decoders

Similar lecture

Facetwise Mesh Refinement for Multi-View Stereo