Italy


The cost-effective visual representation and fast query-by-example search are two challenging goals that should be maintained for web-scale visual retrieval tasks on moderate hardware. This paper introduces a fast and robust method that ensures both of these goals by obtaining state-of-the art performance for an image-to-video search scenario. Hence, we present critical enhancements to well-known indexing and visual representation techniques by promoting faster, better and moderate retrieval performance. We also boost the superiority of our method for some visual challenges by exploiting individual decisions of local and global descriptors at query time. For instance, local content descriptors represent copied/duplicated scenes with large geometric deformations such as scale, orientation and affine transformation. In contrast, the use of global content descriptors is more practical for near-duplicate and semantic searches. Experiments are conducted on a large-scale Stanford I2V dataset. The experimental results show that our method is useful in terms of complexity and query processing time for large-scale visual retrieval scenarios, even if local and global representations are used together. The proposed method is superior and achieves state-of-the-art performance based on the mean average precision (MAP) score of this dataset. Lastly, we report additional MAP scores after updating the ground annotations unveiled by retrieval results of the proposed method, and it shows that the actual performance.

ICPR 2020

Exploiting Local Indexing and Deep Feature Confidence Scores 
for Fast Image-to-Video Search

image-to-video search

visual content retrieval

feature indexing

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


Environmental Sound Classification (ESC) is an active research area in the audio domain and has seen a lot of progress in the past years. However, many of the existing approaches achieve high accuracy by relying on domain-specific features and architectures, making it harder to benefit from advances in other fields (e.g., the image domain). Additionally, some of the past successes have been attributed to a discrepancy of how results are evaluated (i.e., on unofficial splits of the UrbanSound8K (US8K) dataset), distorting the overall progression of the field.
The contribution of this paper is twofold. First, we present a model that is inherently compatible with mono and stereo sound inputs. Our model is based on simple log-power Short-Time Fourier Transform (STFT) spectrograms and combines them with several well-known approaches from the image domain (i.e., ResNet, Siamese-like networks and attention). We investigate the influence of cross-domain pre-training, architectural changes, and evaluate our model on standard datasets. We find that our model out-performs all previously known approaches in a fair comparison by achieving accuracies of 97.0 % (ESC-10), 91.5 % (ESC-50) and 84.2 % / 85.4 % (US8K mono / stereo).
Second, we provide a comprehensive overview of the actual state of the field, by differentiating several previously reported results on the US8K dataset between official or unofficial splits.

ESResNet: Environmental Sound Classification Based on Visual Domain Models




While deep learning approaches have shown remarkable performance in many imaging tasks, most of these methods rely on the availability of large quantities of data. Medical imaging data, however, are scarce and fragmented. Generative Adversarial Networks (GANs) have recently been very effective in handling such datasets by generating more data. If the datasets are very small, however, GANs cannot learn the data distribution properly, resulting in less diverse or low-quality results. One such limited dataset is that for the concurrent gain of 19/20 chromosomes (19/20 co-gain), a mutation with positive prognostic value in Glioblastomas (GBM). In this paper, imaging biomarkers are detected for the mutation to streamline the extensive and invasive prognosis pipeline. Since this mutation is relatively rare, i.e. small dataset, a novel generative framework – the Sequential Attribute GEnerator (SAGE), is proposed, that generates detailed tumor imaging features while learning from a limited dataset. Experiments show that not only does SAGE generate high quality tumors when compared to Progressively Growing GAN (PGGAN), Wasserstein GAN with Gradient Penalty (WGAN-GP) and Deep Convolutional-GAN (DC-GAN), but also captures the imaging biomarkers accurately.

SAGE: Sequential Attribute Generator for Analyzing Glioblastomas Using Limited Dataset

Person Re-Identification (re-ID) aims at retrieving images of the same person taken by different cameras. A challenge for re-ID is the performance preservation when a model is used on data of interest (target data) which belong to a different domain from the training data domain (source data). Unsupervised Domain Adaptation (UDA) is an interesting research direction for this challenge as it avoids a costly annotation of the target data. Pseudo-labeling methods achieve the best results in UDA-based re-ID. They incrementally learn with identity pseudo-labels which are initialized by clustering features in the source re-ID encoder space. Surprisingly, labeled source data are discarded after this initialization step. However, we believe that pseudo-labeling could further leverage the labeled source data in order to improve the post-initialization training steps.
In order to improve robustness against erroneous pseudo-labels, we advocate the exploitation of both labeled source data and pseudo-labeled target data during all training iterations. To support our guideline, we introduce a framework which relies on a two-branch architecture optimizing classification and triplet loss based metric learning in source and target domains, respectively, in order to allow adaptability to the target domain while ensuring robustness to noisy pseudo-labels. Indeed, shared low and mid-level parameters benefit from the source classification and triplet loss signal while high-level parameters of the target branch learn domain-specific features.
Our method is simple enough to be easily combined with existing pseudo-labeling UDA approaches. We show experimentally that it is efficient and improves performance when the base method has no mechanism to deal with pseudo-label noise.
Our approach reaches state-of-the-art performance when evaluated on commonly used datasets, Market-1501 and DukeMTMC-reID, and outperforms the state of the art when targeting the bigger and more challenging dataset MSMT.

Unsupervised Domain Adaptation for Person Re-Identification through Source-Guided Pseudo-Labeling


Precise segmentation of objects is an important problem in tasks like class-agnostic object proposal generation or instance segmentation. Deep learning-based systems usually generate segmentations of objects based on coarse feature maps, due to the inherent downsampling in CNNs. This leads to segmentation boundaries not adhering well to the object boundaries in the image. To tackle this problem, we introduce a new superpixel-based refinement approach on top of the state-of-the-art object proposal system AttentionMask. The refinement utilizes superpixel pooling for feature extraction and a novel superpixel classifier to determine if a high precision superpixel belongs to an object or not. Our experiments show an improvement of up to 26.0% in terms of average recall compared to original ttentionMask. Furthermore, qualitative and quantitative analyses of the segmentations reveal significant improvements in terms of boundary adherence for the proposed refinement compared to various deep learning-based state-of-the-art object proposal generation systems.

Superpixel-based Refinement for Object Proposal Generation

Despite great progress, previous stereo matching algorithms still lack the ability to match textureless regions and slender structure areas. To tackle this problem, we propose ASMNet, an attention stereo matching network. Attention module and disparity refinement module are constructed in the ASMNet. The attention module can improve correlation information between two images by channels and spatial attention.The feature-guided disparity refinement module learns more geometry information in different feature levels to refine the coarse prediction resolution constantly. The proposed approach was evaluated on several benchmark datasets. Experiments show that the proposed method achieves competitive results on KITTI and Scene-Flow datasets while running in real-time at 14ms.

Attention Stereo Matching Network

The notion of anchor plays a major role in modern detection algorithms such as the Faster-RCNN or the SSD detector. Anchors relate the features of the last layers of the detector with bounding boxes containing objects in images. Despite their importance, the literature on object detection has not paid real attention to them. The motivation of this paper comes from the observations that (i) each anchor learns to classify and regress candidate objects independently (ii) insufficient examples are available for each anchor in case of small-scale datasets. This paper addresses these questions by proposing a novel hierarchical head for the SSD detector. The new design has the added advantage of no extra weights, as compared to the original design at inference time, while improving detectors performance for small size training sets. Improved performance on PASCAL-VOC and state-of-the-art performance on FlickrLogos-47 validate the method. We also show when the proposed design does not give additional performance gain over the original design.

Hierarchical Head Design for Object Detectors

Objects from correlated classes usually share highly similar appearance while objects from uncorrelated classes are very different. Most of current image recognition works treat each class independently, which ignores these class correlations and inevitably leads to sub-optimal performance in many cases. Fortunately, object classes inherently form a hierarchy with different levels of abstraction and this hierarchy encodes rich correlations among different classes. In this work, we utilize a soft label vector that encodes the prior knowledge of class correlations as extra regularization to train the image classifiers. Specifically, for each class, instead of simply using a one-hot vector, we assign a high value to its correlated classes and assign small values to those uncorrelated ones, thus generating knowledge embedded soft labels. We conduct experiments on both general and fine-grained image recognition benchmarks and demonstrate its superiority compared with existing methods.

Exploiting Knowledge Embedded Soft Labels for Image Recognition

The detection of logos in images, for instance, logos of airlines on airplane tails, is a difficult task in real-world weather conditions. Most systems used for logo detection are very good at detecting logos in clean images. However, they exhibit problems when images are degraded by effects of adverse weather conditions as they frequently occur in real-world scenarios. For investigating this problem on airline logo detection as a sub-problem of logo detection, we first present a new dataset for
airline logo detection on airplane tails containing a test split with images degraded by adverse weather effects. Second, to handle the detection of airline logos effectively, a new two-stage airline logo detection system based on a state-of-the-art object proposal generation system and a specifically tailored classifier is proposed. Finally, improving the results on images degraded by adverse weather effects, we introduce a learning-free application-agnostic data augmentation strategy simulating effects like rain and fog. The results show the superior performance of our airline logo detection system compared to state-of-the-art. Furthermore, applying our data augmentation approach to a variety of systems, reduces the significant drop in performance on degraded images.

Which Airline is This? Airline Logo Detection in Real-World Weather Conditions

Camera pose estimation in large-scale environments is still an open question and, despite recent promising results, it may still fail in some situations. The research so far has focused on improving subcomponents of estimation pipelines, to achieve more accurate poses. However, there is no guarantee for the result to be correct, even though the correctness of pose estimation is critically important in several visual localization applications, such as in autonomous navigation.
In this paper we bring to attention a novel research question, pose confidence estimation, where we aim at quantifying how reliable the visually estimated pose is.
We develop a novel confidence measure to fulfill this task and show that it can be flexibly applied to different datasets, indoor or outdoor, and for various visual localization pipelines.
We also show that the proposed techniques can be used to accomplish a secondary goal: improving the accuracy of existing pose estimation pipelines.
Finally, the proposed approach is computationally light-weight and adds only a negligible increase to the computational effort of pose estimation.

Can You Trust Your Pose? Confidence Estimation in Visual Localization


In the last few years, several techniques for facial
manipulation in videos have been successfully developed and
made available to the masses (i.e., FaceSwap, deepfake, etc.).
These methods enable anyone to easily edit faces in video
sequences with incredibly realistic results and a very little effort.
Despite the usefulness of these tools in many fields, if used
maliciously, they can have a significantly bad impact on society
(e.g., fake news spreading, cyber bullying through fake revenge
porn). The ability of objectively detecting whether a face has
been manipulated in a video sequence is then a task of utmost
importance.
In this paper, we tackle the problem of face manipulation detection in video sequences targeting modern facial manipulation
techniques. In particular, we study the ensembling of different
trained Convolutional Neural Network (CNN) models. In the
proposed solution, different models are obtained starting from a
base network (i.e., EfficientNetB4) making use of two different
concepts: (i) attention layers; (ii) siamese training. We show that
combining these networks leads to promising face manipulation
detection results on two publicly available datasets with more
than 119000 videos.

Premium content

Exploiting Local Indexing and Deep Feature Confidence Scores for Fast Image-to-Video Search

Downloads

Next from ICPR 2020

ESResNet: Environmental Sound Classification Based on Visual Domain Models

Similar lecture

Webly Supervised Image-Text Embedding with Noisy Tag Refinement