Italy

Action spotting has recently been proposed as an alternative to action detection and key frame extraction. However, the current state-of-the-art method of action spotting requires an expensive ground truth composed of the search sequences
employed by human annotators spotting actions - a critical limitation.
In this article, we propose to use a reinforcement learning algorithm to perform efficient action spotting using only the temporal segments from the action detection annotations, thus opening an interesting solution for video understanding.
Experiments performed on THUMOS14 and ActivityNet datasets show that the proposed method, named ActionSpotter, leads to good results and outperforms state-of-the-art detection outputs redrawn for this application. In particular, the spotting mean Average Precision on THUMOS14 is significantly improved from 59.7% to 65.6% while skipping 23% of video.

ICPR 2020

ActionSpotter: Deep Reinforcement Learning Framework for Temporal Action Spotting in Videos

action

reinforcement

video

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 work considers the problem of domain shift in person re-identification. Being trained on one dataset, a re-identification model usually performs much worse on unseen data. Partially this gap is caused by the relatively small scale of person re-identification datasets (compared to face recognition ones, for instance), but it is also related to training objectives. We propose to use the metric learning objective, and some additional training practices to build well-generalizing, yet, computationally efficient models.

Building Computationally Efficient and Well-Generalizing Person Re-Identification Models with Metric Learning

In this paper we propose solving localized multiple kernel learning (LMKL) using LMKL-Net, a feedforward deep neural network (DNN). In contrast to previous works, as a learning principle we propose parameterizing the gating function for learning kernel combination weights and the multiclass classifier using an attentional network (AN) and a multilayer perceptron (MLP), respectively. Such interpretability helps us better understand how the network solves the problem. Thanks to stochastic gradient descent (SGD), our approach has linear computational complexity in training. Empirically on benchmark datasets we demonstrate that with comparable or better accuracy than the state-of-the-art, our LMKL-Net can be trained about two orders of magnitude faster with about two orders of magnitude smaller memory footprint for large-scale learning.

An Efficient Empirical Solver for Localized Multiple Kernel Learning Via DNNs


In deep metric learning targeted at time series, the correlation between feature activations may be easily enlarged through highly nonlinear neural networks, leading to suboptimal embedding effectiveness. An effective solution to this problem is whitening. For example, in online signature verification, whitening can be derived for three individual Gaussian distributions, namely the distributions of local features at all temporal positions 1) for all signatures of all subjects, 2) for all signatures of each particular subject, and 3) for each particular signature of each particular subject. This study proposes a unified method called total whitening that integrates these individual Gaussians. Total whitening rectifies the layout of multiple individual Gaussians to resemble a standard normal distribution, improving the balance between intraclass invariance and interclass discriminative power. Experimental results demonstrate that total whitening achieves state-of-the-art accuracy when tested on online signature verification benchmarks.

Total Whitening for Online Signature Verification Based on Deep Representation

We propose a robust long-term object tracking method that resolves the fundamental cause of the drift and loss of a target in visual object tracking. The proposed method consists of “sampling area extension”, which prevents a tracking result from drifting to other objects by learning false positive samples in advance (before they enter the search region of the target), and “adaptive search based on motion models”, which prevents a tracking result from drifting to other objects and avoids the loss of the target by using not only appearance features but also motion models to adaptively search for the target. Experiments conducted on long-term tracking dataset showed that our first technique improved robustness by 16.6% while the second technique improved robustness by 15.3%. By combining both, our method achieved 21.7% and 9.1% improvement for the robustness and precision, and the processing speed became 3.3 times faster. Additional experiments showed that our method achieved the top robustness among state-of-the-art methods on three long-term tracking datasets. These findings demonstrate that our method is effective for long-term object tracking and that its performance and speed are promising for use in practical applications of various technologies underlying object tracking.

Reducing False Positives in Object Tracking With Siamese Network

In a generic object tracking, depth (D) information provides informative cues for foreground-background separation and target bounding box regression. However, so far, few trackers have used depth information to play the important role aforementioned due to the lack of a suitable model. In this paper, a RGB-D tracker named TSDM is proposed, which is composed of a Mask-generator (M-g), SiamRPN++ and a Depth-refiner (D-r). The M-g generates the background masks, and updates them as the target 3D position changes. The D-r optimizes the target bounding box estimated by SiamRPN++, based on the spatial depth distribution difference between the target and the surrounding background. Extensive evaluation on the Princeton Tracking Benchmark and the Visual Object Tracking challenge shows that our tracker outperforms the state-of-the-art by a large margin while achieving 23 FPS. In addition, a light-weight variant can run at 31 FPS and thus it is practical for real world applications. Code and models of TSDM are available at https://github.com/lql-team/TSDM.

TSDM: Tracking by SiamRPN++ with a Depthrefiner and a Mask-generator

In this paper, we address a problem of atmospheric blocking pattern recognition in global climate model simulation data. Understanding blocking events is a crucial problem to society and natural infrastructure, as they often lead to weather extremes, such as heat waves, heavy precipitation, and the unusually poor air condition. Moreover, it is very challenging to detect these events as there is no physics-based model of blocking dynamic development that could account for their spatiotemporal characteristics. Here, we propose a new two-stage hierarchical pattern recognition method for detection and localisation of atmospheric blocking events in different regions over the globe. For both the detection stage and localisation stage, we train five different architectures of a convolutional neural network (CNN) based classifier and regressor. The results show the general pattern of the atmospheric blocking detection performance increasing significantly for the deep CNN architectures. In contrast, we see the estimation error of event location decreasing significantly in the localisation problem for the shallow CNN architectures. We demonstrate that CNN architectures tend to achieve the highest accuracy for blocking event detection and the lowest estimation error of event localisation in regions of the Northern Hemisphere than in regions of the Southern Hemisphere.

Atmospheric Blocking Pattern Recognition in Global Climate Model Simulation Data

Estimating the 6D pose of objects is an important process for intelligent systems to achieve interaction with the real-world. 
As the RGB-D sensors become more accessible, the fusion-based methods have prevailed, since the point clouds provide complementary geometric information with RGB values. However, due to the difference in feature space between color image and depth image, the network structures that directly perform point-to-point matching fusion do not effectively fuse the features of the two. 
In this paper, we propose a simple but effective approach, named MixedFusion. Different from the prior works, we argue that the spatial correspondence of color and point clouds could be decoupled and reconnected, thus enabling a more flexible fusion scheme. By performing the proposed method, more informative points can be mixed and fused with rich color features.
Extensive experiments are conducted on the challenging LineMod and YCB-Video datasets, which shows that our method significantly boosts the performance without introducing extra overheads. Furthermore, when the minimum tolerance of metric narrows, the proposed approach performs better for the high-precision demands.

MixedFusion: 6D Object Pose Estimation from Decoupled RGB-Depth Features




Ranking is a ubiquitous problem setting that appears in many real-world applications. The superior players or objects in the ranking list are oftentimes estimated from matchups and pairwise comparisons. In order to predict the result of unobserved events, various models have been developed to integrate the matchup and pairwise comparison results into a single ranking list of players. Amongst these models, the Bradley-Terry model is the mainstream which achieves the goal by authorizing enriched probabilistic interpretation of players. However, the model suffers from its strong assumption of transitive relationships and becomes vulnerable in practice when intransitive relationships exist. In this paper, we propose a low-rank matrix approach to characterize all players and unify the related works on representation learning of players by rearranging the constructively. Our experimental results on synthetic datasets and real-world datasets show that the proposed model is competitive with the standard models in terms of out-of-sample predictive performance and consistency of model interpretation.

An Intransitivity Model for Matchup and Pairwise Comparison

Autonomous driving is challenging in adverse road and weather conditions in which there might not be lane lines, the road might be covered in snow and the visibility might be poor. We extend the previous work on end-to-end learning for autonomous steering to operate in these adverse real-life conditions with multimodal data. We collected 28 hours of driving data in several road and weather conditions and trained convolutional neural networks to predict the car steering wheel angle from front-facing color camera images and lidar range and reflectance data. We compared the CNN model performances based on the different modalities and our results show that the lidar modality improves the performances of different multimodal sensor-fusion models. We also performed on-road tests with different models and they support this observation.

Multimodal End-to-End Learning for Autonomous Steering in Adverse Road and Weather Conditions

Visual object tracking is of great interest in many applications, as it preserves the identity of an object throughout a video. However, while real applications demand systems capable of real-time-tracking multiple objects, multi-object tracking solutions usually follow the tracking-by-detection paradigm, thus they depend on running a costly detector in each frame, and they do not allow the tracking of arbitrary objects, i.e., they require training for specific classes. In response to this need, this work presents the architecture of SiamMT, a system capable of efficiently applying individual visual tracking techniques to multiple objects in real-time. This makes it the first deep-learning-based arbitrary multi-object tracker. To achieve this, we propose global frame features extraction by using a fully-convolutional neural network, followed by the cropping and resizing of the different object search areas. The final similarity operation between these search areas and the target exemplars is carried out with an optimized pairwise cross-correlation. These novelties allow the system to track multiple targets in a scalable manner, achieving 25 fps with 60 simultaneous objects for VGA videos and 40 objects for HD720 videos, all with a tracking quality similar to SiamFC.

Premium content

ActionSpotter: Deep Reinforcement Learning Framework for Temporal Action Spotting in Videos

Downloads

Next from ICPR 2020

Building Computationally Efficient and Well-Generalizing Person Re-Identification Models with Metric Learning

Similar lecture

AG-GAN: An Attentive Group-Aware GAN for pedestrian trajectory prediction