- General Chairs:
- Anastasios Doulamis,
- Jordi Gonzàlez,
- Program Chairs:
- Marco Bertini,
- Luc van Gool,
- Nikolaos Matsatsinis,
- Thomas B. Moeslund,
- Mark Nixon,
- Liang Wang
This section acknowledges all the people involved in the first ACM International Workshop on Analysis and Retrieval of Tracked Events and Motion in Imagery Streams (ARTEMIS2010) held at Firenze (Italy) on October 29, 2010. ARTEMIS2010 was hosted by the International Conference on Multimedia 2010 which is sponsored by ACM.
The ARTEMIS workshop outlined the state of the research on the evaluation of events and human motion in image sequences. This video hermeneutics process implies the assessment of the achievements of four decades of visual tracking research into the development of high-level, cognitive functionalities. So, a workshop was suitable to provide cross-disciplinary approaches to addressing the aforementioned challenges on the topic of computational models of human behaviour understanding using cognitive systems, with the purpose to advance understanding of the state-of-the-art on evaluation in the frame of cognitive processing. The goals of this workshop were set to provide a holistic view on the interpretation and description of human behaviours in image sequences, specially focusing on the interactions and collaborations between computer vision researchers and: (i) artificial intelligence techniques for the highlevel analysis of human behaviours in human-populated scenarios; (ii) multimedia semantics methods for content-based browsing, indexing and retrieval of human behaviours detected in image sequences; (iii) computer animation algorithms for graphical-models generation learned/controlled by semantic concepts extracted from image sequences; and (iv) computational linguistics theories for natural-language description and semantic mapping of human behaviours based on ontologies. The aim was then to encourage links between researchers in such different areas who address those semantic enhancements which can be applied based on the numeric data obtained from tracking processes.
In total, 27 papers from 17 different countries were submitted, of which 14 (about 50%) were accepted. Out of these 14 accepted papers, 9 were oral presentations (33%), 4 were posters and 1 was a demo paper. We would therefore like to thank all the authors for submitting their work and apologise that not all the papers could be accepted. We are also especially grateful to the 53 members of the Program Committee for their remarkable effort and the high quality as well as the time delivery of the reviews.
Proceeding Downloads
Emphatic human interaction analysis for cognitive environments
Understanding the dynamic evolution of complex scenes where multiple patterns interact according to a hidden semantic goal is an issue of current intelligent environments. This issue is made somehow more complex due to the more spread and intensive use ...
Human gesture recognition using 3.5-dimensional trajectory features for hands-free user interface
We present a new human motion recognition technique for a hands-free user interface. Although many motion recognition technologies for video sequences have been reported, no man-machine interface that recognizes enough variety of motions has been ...
Human pose estimation with implicit shape models
We address the problem of articulated 2D human pose estimation in natural images. A well-known person detector -- the Implicit Shape Model (ISM) approach introduced by Leibe et al. -- is shown not only to be well suited to detect persons, but can also ...
Joint multitarget object tracking and interaction analysis by a probabilistic bio-inspired model
In this paper a joint human tracking and human-to-human interaction recognition system is proposed. While usually these two functions are performed separately, it will be shown that it is possible to improve the tracking performances if these functions ...
Multi-object particle filter tracking with automatic event analysis
The automatic video content analysis is an important step to provide the content-based video coding, indexing and retrieval. It is also a key issue to the event analysis in video surveillance. In this paper, an automatic event analysis approach is ...
Dense spatio-temporal features for non-parametric anomaly detection and localization
In this paper we propose dense spatio-temporal features to capture scene dynamic statistics together with appearance, in video surveillance applications. These features are exploited in a real-time anomaly detection system. Anomaly detection is ...
Implicit visual concept modeling in image / video annotation
In this paper a novel approach for automatically annotating image databases is proposed. Despite most current approaches that are just based on spatial content analysis, the proposed method properly combines implicit feedback information and visual ...
Enhanced human behavior recognition using HMM and evaluative rectification
Human behavior recognition and real world environments monitoring constitute challenging research problems rapidly gaining momentum over the last years. Methods for time series classification like the Hidden Markov Models have been employed in the past ...
Automatic fish classification for underwater species behavior understanding
- Concetto Spampinato,
- Daniela Giordano,
- Roberto Di Salvo,
- Yun-Heh Jessica Chen-Burger,
- Robert Bob Fisher,
- Gayathri Nadarajan
The aim of this work is to propose an automatic fish classification system that operates in the natural underwater environment to assist marine biologists in understanding subehavior. Fish classification is performed by combining two types of features: ...
Combining inertial and visual sensing for human action recognition in tennis
In this paper, we present a framework for both the automatic extraction of the temporal location of tennis strokes within a match and the subsequent classification of these as being either a serve, forehand or backhand. We employ the use of low-cost ...
Event detection in video using motion analysis
Digital video is being used widely in a variety of applications such as entertainment, surveillance and security. Large amount of video in surveillance and security requires systems capable of processing video to automatically detect and recognize ...
Human action recognition with MPEG-7 descriptors and architectures
Modern video surveillance requires addressing high-level concepts such as humans' actions and activities. In addition, surveillance applications need to be portable over a variety of platforms, from servers to mobile devices. In this paper, we explore ...
Event-based unobtrusive authentication using multi-view image sequences
his paper presents a novel framework for dynamic activity-related user authentication utilizing dynamic and static anthropometric information. The recognition of the performed activity is based on Radon transforms that are applied on spatiotemporal ...
Real time illumination invariant motion change detection
An original approach for real time detection of changes in motion is presented, which can lead to the detection and recognition of events. Current video change detection focuses on shot changes which depend on appearance, not motion. Changes in motion ...
Tools for semi-automatic monitoring of industrial workflows
- Roland Mörzinger,
- Manolis Sardis,
- Igor Rosenberg,
- Helmut Grabner,
- Galina Veres,
- Imed Bouchrika,
- Marcus Thaler,
- Rene Schuster,
- Albert Hofmann,
- Georg Thallinger,
- Vassileios Anagnostopoulos,
- Dimitrios Kosmopoulos,
- Athanasios Voulodimos,
- Constantinos Lalos,
- Nikolaos Doulamis,
- Theodora Varvarigou,
- Rolando Palma Zelada,
- Ignacio Jubert Soler,
- Severin Stalder,
- Luc Van Gool,
- Lee Middleton,
- Zoheir Sabeur,
- Banafshe Arbab-Zavar,
- John Carter,
- Mark Nixon
This paper describes a tool chain for monitoring complex workflows. Statistics obtained from automatic workflow monitoring in a car assembly environment assist in improving industrial safety and process quality. To this end, we propose automatic ...
Multi-sensor registration for objects motion detection
The first step in order to achieve low-level multi-sensor fusion is the registration of images from multiple types of sensors. This is a very important task: it can be useful to improve the detection or the tracking of a moving object in an area. ...
- Proceedings of the first ACM international workshop on Analysis and retrieval of tracked events and motion in imagery streams