Citation for Published Version Escalera Guerrero, S., Fabian, J

Total Page:16

File Type:pdf, Size:1020Kb

Citation for Published Version Escalera Guerrero, S., Fabian, J Citation for published version Escalera Guerrero, S., Fabian, J., Pardo, P., Baró Solé, X., Gonzàlez Sabaté, J., Escalante, H.J., Misevic, D., Steiner, U. & Guyon, I. (2016). ChaLearn Looking at People 2015: Apparent Age and Cultural Event Recognition Datasets and Results. IEEE International Conference on Computer Vision. Proceedings, 2016(), 243-251. doi: 10.1109/ICCVW.2015.40 DOI https://doi.org/10.1109/ICCVW.2015.40 Document Version This is the Accepted Manuscript version. The version in the Universitat Oberta de Catalunya institutional repository, O2 may differ from the final published version. Copyright and Reuse This manuscript version is made available under the terms of the Creative Commons Attribution Non Commercial No Derivatives licence (CC-BY-NC-ND) http://creativecommons.org/licenses/by-nc-nd/3.0/es, which permits ​ others to download it and share it with others as long as they credit you, but they can’t change it in any way or use them commercially. Enquiries If you believe this document infringes copyright, please contact the Research Team at: [email protected] Universitat Oberta de Catalunya Research archive ChaLearn Looking at People 2015: Apparent Age and Cultural Event Recognition datasets and results Sergio Escalera Junior Fabian Pablo Pardo Universitat de Barcelona and CVC Computer Vision Center Universitat de Barcelona Xavier Baro´ Jordi Gonzalez` Hugo J. Escalante Universitat Oberta de Catalunya Universitat Autonoma` de Barcelona INAOE Mexico Computer Vision Center Computer Vision Center Dusan Misevic Ulrich Steiner Isabelle Guyon Center for Research and Interdisciplinarity Max-Planck Odense Center Clopinet, ChaLearn Abstract as well as technical limitations such as spatial and temporal resolution. Facial expressions analysis and age estimation Following previous series on Looking at People (LAP) are hot topics in Looking at People that serve as additional competitions [14, 13, 11, 12, 2], in 2015 ChaLearn ran two cues to determine human behavior and mood indicators. Fi- new competitions within the field of Looking at People: (1) nally, images of cultural events constitute a very challeng- age estimation, and (2) cultural event recognition, both in ing recognition problem due to a high variability of gar- still images. We developed a crowd-sourcing application to ments, objects, human poses and scene context. Therefore, collect and label data about the apparent age of people (as how to combine and exploit all this knowledge from pixels opposed to the real age). In terms of cultural event recog- constitutes an interesting problem. nition, one hundred categories had to be recognized. These These challenges motivated our choice to organize a new tasks involved scene understanding and human body anal- ICCV workshop and a competition on these topics to sus- ysis. This paper summarizes both challenges and data, as tain the effort of the computer vision community. These well as the results achieved by the participants of the com- new competitions come as a natural evolution from our pre- petition. Details of the ChaLearn LAP competitions can be vious workshops at CVPR2011, CVPR2012, ICPR2012, found at http://gesture.chalearn.org/. ICMI2013, ECCV2014 and CVPR2015. We continued us- ing our website http://gesture.chalearn.org for promotion and challenge entries in the quantitative competition were 1. Introduction scored on-line using the Codalab Microsoft-Stanford Uni- versity platforms (http://codalab.org/). The automatic analysis of the human body, also named In the rest of this paper, we describe in more detail both Looking at People, in still images and image sequences age estimation and cultural event recognition challenges, keeps making rapid progress with and the constant improve- their relevance in the context of the state of the art, and de- ment of new published methods that rapidly advance the scribe the results achieved by the participants in both chal- state-of-the-art. lenges. In 2015, ChaLearn organized new competitions and workshops on age estimation and cultural event recogni- 2. Age estimation challenge tion from still images. The recognition of continuous, nat- ural human signals and activities is very challenging due Age estimation is a difficult task which requires the au- to the multimodal nature of the visual cues (e.g., move- tomatic detection and interpretation of facial features. We ments of fingers and lips, facial expressions, body pose), have designed an application using the Facebook API for 17141 the collaborative harversting and labeling by the commu- nity in a gamified fashion (http://sunai.uoc.edu:8005/). Age estimation has historically been one of the most challenging problems within the field of facial analysis [32, 17, 21]. It can be very useful for several applications, such as advanced video surveillance, demographic statis- tics collection, business intelligence and customer profiling, and search optimization in large databases. Different ap- plication scenarios can benefit from learning systems that (a) Game Panel predict the apparent age, such as medical diagnosis (prema- ture aging due to environment, sickness, depression, stress, fatigue, etc.), effect of anti-aging treatment (hormone re- placement therapy, topical treatments), or effect of cosmet- ics, haircuts, accessories and plastic surgery, just to mention a few. Some of the reasons age estimation is still a chal- lenging problem are the uncontrollable nature of the aging process, the strong specificity to the personal traits of each individual, high variance of observations within the same (b) Gallery Panel age range, and the fact that it is very hard to gather com- plete and sufficient data to train accurate models. 2.1. Dataset Due to the nature of the age estimation problem, there is a restricted number of publicly available databases pro- viding a substantial number of face images labeled with ac- curate age information. Table 1 shows the summary of the existing databases with main reference, number of samples, (c) Ranking Panel number of subjects, age range, type of age and additional information. This field has experienced a renewed inter- Figure 1. Age Recognition Application. (a) User can see the im- est from 2006 on, since the availability of large databases ages of the rest of participants and vote for the apparent age. (b) User can upload images and see their uploads and the opinion of like MORPH-Album 2 [34], which increased by 55× the the users regarding the apparent age of people in their photos. (c) amount of real age-annotated data with respect to traditional User can see the points he/she achieves by uploading and voting age databases. Therefore, this database has extensively been photos and the ranking among his/her friends and all the partici- used in recent works by applying to it different descriptors pants of the application. and classification schemes. However, all existing datasets are based on real age estimation. In the present challenge, we propose the first dataset to recognize the apparent age of a global and friends leaderboard where the users could see people based on the opinion of many subjects using a new their position in the ranking. We asked the users to upload crowd-sourcing data collection and labeling application and images of a single person and we gave them tools to crop the 1 the data from AgeGuess platform . image if necessary, we also asked them to provide the real We developed a web application in order to collect and age for images they uploaded themselves (or a good approx- label an age estimation dataset online by the community. imation), allowing more analysis and comparisons between The application uses the Facebook API to facilitate the ac- real age and apparent age. cess hence reach more people with a broader background. In order to increase the number of images in the It also allows us to easily collect data from the participants, database, an exhaustive research was done to find similar such as gender, nationality and age. We show some panels applications which were collecting the same, or very close, of the application in the Figure 1(a), 1(b) and 1(c). type of data. The result of this search was AgeGuess, which The web application was developed in a gamified way, collects nearly the same information as we do. The line of i.e. the users or players get points for uploading and label- research of the AgeGuess team is focused on aging and age ing images, the closer the age guess was to the apparent age perception from a biologically demographical point of view. (average labeled age) the more points the player obtained. The AgeGuess team agreed to partner with the HuPBA re- In order to increase the engagement of the players, we added search group and the ChaLeran platform to joint effort in the 1AgeGuess: http://www.ageguess.org/ data collection. The Table 2 shows the main characteristics 17152 Table 1. Age-based Databases and its characteristics. Database #Faces #Subj. Range Type of age Controlled Balanced age Other annotation Enviroment Distrivution FG-NET [25, 24] 1,002 82 0 - 69 Real Age No No 68 Facial Landmarks GROUPS [19] 28,231 28,231 0 - 66+ Age group No No - PAL [27] 580 580 19 - 93 Age group No No - FRGC [31] 44,278 568 18 - 70 Real Age Partially No - MORPH2 [35] 55,134 13,618 16 - 77 Real Age Yes No - YGA [18] 8,000 1,600 0 - 93 Real Age No No - FERET[30] 14,126 1,199 - Real Age Partially No - Iranian face [3] 3,600 616 2 - 85 Real Age No No Kind of skin and cosmetic points PIE [37] 41,638 68 - Real Age Yes No - WIT-BD [42] 26,222 5,500 3 - 85 Age group No No - Caucasian Face 147 - 20 - 62 Real Age Yes No 208 Shape Landmarks Database [5] LHI [1] 8,000 8,000 9 - 89 Real Age Yes Yes - HOIP [16] 306,600 300 15 - 64 Age Group Yes No - Ni’s Web- 219,892 - 1 - 80 Real Age No No - Collected Database [28] OUI-Adience [9] 26.580 2.284 0 - 60+ Age Group No No Gender of the final database.
Recommended publications
  • 2016 Venice Carnival Special Projects Case History
    Carnival of Venice 2016 23 January – 9 February From January, 23 To February, 9 Venice historical Centre, islands, Mestre, Marghera Number of visitors: more than 1.000.000 attendants, with daily peaks of 150.000 persons Programm of Carnival 2015 18 days of events and celebrations: from the prologue to the Mardi Gras (Shrove Tuesday) that marks the grand finale of the gala. Crowds are expected to peak during the three weekends of the event (January 23-24 and 30-31, February 6-7), the Thursday before Lent (February 4) and Mardi Gras (February 9). Program: the highlights Prologue (January 23-24): the official opening of the Carnival with the “Festa Veneziana” in Cannaregio, made of a water parade of rowers in costume and food tasting. First weekend (January 30-31): the Volo dell’Angelo, the Festa delle Marie (that recalls a historical event elaborating it in the form of a beauty contest in Renaissance costumes), the historical re-enactments. Second weekend (6-7 February): final of the best masked costume contest, the “commedia dell’arte” shows, music concerts, the “volo dell’Asino” in Mestre. For the whole period of the carnival: daily shows for the best masked costume contest, cultural events (itineraries and nighttime visits to museums and cultural seats in the city, exhibitions, readings, ecc.), dj-set. Let’s all spend marvellous Carnival nights at the Arsenal! The Arsenal dresses up in magic, poetry, music and sensational special effects on water and turns into Carnival at the Arsenal. Music and traveling entertainment will be introduced by a magic show.
    [Show full text]
  • INTERNASJONALT MAGASIN (1).Pdf
    CI ComANen SiuEsE, I CAN HEAR, I CAANp SriPl 2E0A1K3 CONTENT 3 Editorial 4-5 Windsurfing 6 What you thought you knew 7 Our language 8-9 Tourism in the Ardennes and music festivals 10-11 Welcome to Trondheim 12-13 The luxury industry in France 14-15 Unsolved mysteries 16-17 The carnival 18 Importance of economy 19 World politics 20-21 Trolls of Norway 22-25 Science and technology 26 Kids with guns 27 Fast changes 28 Festivals in Trondheim 29 Worlds most interesting festivals 30-31 The canary islands music festival 32 Champagne 32 Fast changes 33 Economy in the Ardennes 34 Relocation of electrolux factory 2 I can see, hear, speak EDITORIAL EDITORIAL Editor The Desk EDITOR’S Inger Lise Stensheim Sara Rye Martinsen NOTE As a part of the Comenius pro- Kristian Arne Iversen ject, the media class of the Ca- Emilie Davidsen Malene Andersen thedral School of Trondheim has made a magazine featuring many things about our town, and Norway’s culture. We have Julie Røkke Osen been working on this magazine together with students from Slovakia, Turkey, France and Spain, and together with their Photography content we have produced a magazine full of information about all of our countries and their culture, that you will sure- Christina Rygvik Malin Albertsen Gjørv ly enjoy reading through. Some of our students will meet them in the Comenius exchange pro- gram in a couple of weeks, and they will present the magazine and its content there. We hope Lise Nielsen Torun Edvardsen that you enjoy what we have to present, and we’ll see you! Kristian Arne Iversen Lena Pedersen I can see, hear, speak 3 WINDSURFING Water sports in the Canary Islands windsurfing and kitesurfing Like every year in the Canary Is- music, shows, food stands (typi- boarding.
    [Show full text]
  • Chalearn Looking at People 2015 Challenges: Action Spotting and Cultural Event Recognition
    ChaLearn Looking at People 2015 challenges: action spotting and cultural event recognition Xavier Baro´ Jordi Gonzalez` Universitat Oberta de Catalunya - CVC Computer Vision Center (UAB) [email protected] [email protected] Junior Fabian Miguel A. Bautista Computer Vision Center (UAB) Universitat de Barcelona [email protected] [email protected] Marc Oliu Hugo Jair Escalante Isabelle Guyon Universitat de Barcelona INAOE Chalearn [email protected] [email protected] [email protected] Sergio Escalera Universitat de Barcelona - CVC [email protected] Abstract CVPR workshop on action/interaction spotting and cultural event recognition. The recognition of continuous, natural Following previous series on Looking at People (LAP) human signals and activities is very challenging due to the challenges [6, 5, 4], ChaLearn ran two competitions to multimodal nature of the visual cues (e.g., movements of be presented at CVPR 2015: action/interaction spotting fingers and lips, facial expression, body pose), as well as and cultural event recognition in RGB data. We ran a technical limitations such as spatial and temporal resolu- second round on human activity recognition on RGB data tion. In addition, images of cultural events constitute a very sequences. In terms of cultural event recognition, tens challenging recognition problem due to a high variability of categories have to be recognized. This involves scene of garments, objects, human poses and context. Therefore, understanding and human analysis. This paper summa- how to combine and exploit all this knowledge from pixels rizes the two challenges and the obtained results. De- constitutes a challenging problem. tails of the ChaLearn LAP competitions can be found at http://gesture.chalearn.org/.
    [Show full text]
  • Carnival Scratch-Art® Mask
    Carnival Scratch-Art® Mask (art + social studies) Explore the history of carnival masks from various cultures, such as Mardi Gras in New Materials Orleans, the Carnival of Venice and “Commedia Scratch Art® Clear-Scratch™ Film Dell'arte” in Italy. Ornate and colorful masks are (13524-1030), package of 30 sheets, ® easy to create with Scratch -Art Clear-Scratch™ need 1/2 sheet per demi-mask, full sheet for film and permanent Sharpie® markers. full-face mask Grade Levels K-8 Sharpie Chisel-Tip Markers, set of 8 colors Note: instructions and materials based on a (21383-0089), share one set between 4-5 class of 25 students. Adjust as needed. students Preparation Scratch Sticks (14907-1045), package of 100, need one per student 1. Cut sheets of Scratch Art® Clear- Scratch™ film in half to make 8" x 4.75" Wood Dowel, 1/4" dia x 12" (60448-1412) pieces. Will need one piece per mask package of 12, need one per mask ® 2. Draw a mask shape on paper and cut out Blick E-Z Grip Knife (57419-2980), one or to use as a template. For demi-mask, use two per class the pattern on page 2. Optional Process Krylon® Low-Odor Spray Finish (23710-1001), 1. Trace the mask shape onto the matte gloss, 11-oz can, need one side of the film lightly with a pencil. Extra features, such as ears, hair, antennae, etc. can be added to the basic clear plastic surface. Place a plain white mask shape if desired. Cut mask out of sheet of paper beneath the mask while film (do not cut out eye areas).
    [Show full text]
  • Progressive English III
    1 PREPARATORIA 22 Portfolio of Evidences 2nd Opportunity Progressive English III Student’s name: __________________________________________________ Student´s number: ________________ Date: _____/ ______ / 2020 Teacher: _________________________________________ Group: _________ This portfolio is part of 60% of your qualification. This value will be obtained as long as it meets the following requirements: 1. Transcribed by hand, in its entirety and with the correct answers. 2. Complete identification data. 3. This portfolio must be uploaded in PDF extension, only on the day and at the time of the exam in the Tasks section of your team corresponding to the subject in MS Teams, where your teacher will review it. 4. PLEASE ANSWER ONLY WITH BLUE INK AND ADD YOUR NAME ON EACH SHEET. Elaborated by M.C.C. Patricia Karina Perez Burgos. 2 UNIVERSIDAD AUTÓNOMA DE NUEVO LEÓN PREPARATORIA NO. 22 PORTFOLIO OF EVIDENCE PROGRESSIVE ENGLISH III SECOND OPORTUNITY NAME: _______________________________________________________________ GROUP:_______________________________________________________________ DATE:________________________________________________________________ Elaborated by M.C.C. Patricia Karina Perez Burgos. 3 Conditional sentences are often divided into different types. 1. Zero conditional. We use the zero conditional to talk about things that are generally true, especially for laws and rules. ... 2. First conditional. We use the first conditional when we talk about future situations we believe are real or possible. ... The first conditional describes a particular situation, whereas the zero conditional describes what happens in general. I.- Read the following pairs of sentences in zero and first conditionals, and choose the ones that are written correctly. 1.- (a) The table will break if you sit on it. (b) The table will break, if you sit on it.
    [Show full text]
  • Department of Music Programs 1972 - 1973 Department of Music Olivet Nazarene University
    Olivet Nazarene University Digital Commons @ Olivet School of Music: Performance Programs Music 1973 Department of Music Programs 1972 - 1973 Department of Music Olivet Nazarene University Follow this and additional works at: https://digitalcommons.olivet.edu/musi_prog Part of the Fine Arts Commons, and the Music Performance Commons Recommended Citation Department of Music, "Department of Music Programs 1972 - 1973" (1973). School of Music: Performance Programs. 6. https://digitalcommons.olivet.edu/musi_prog/6 This Book is brought to you for free and open access by the Music at Digital Commons @ Olivet. It has been accepted for inclusion in School of Music: Performance Programs by an authorized administrator of Digital Commons @ Olivet. For more information, please contact [email protected]. 7 8 0 .7 3 9 0£4p 1 9 7 2 -7 3 PROGRAMS 1972 1973 DEPARTMENT OF MUSIC yuvet Nazarene College Kankakee. VL OLIVET NAZARENE COLLEGE. DEPARTMENT OF MUSIC p r e s e n ts a STUDENT RECITAL Six E cossaises ........................ .... .......................................... B eeth oven Terry Morsch, piano T raum erei ........................ ........................................ Robert Schumann Important Event Robert Schumann Brad Morsch, piano Caro Mio B e n .......................................... Guiseppe Giordani Cheryl Spargur, soprano Linda Jarnagin, accompanist Art Thou The Christ? ..................... ..... Jeoffrey O'Hara Marla Kensey, soprano Still Wie Die Nacht .............................................................. C
    [Show full text]
  • Untitled (Human Mask), Mostra O Poder Transforma- O Saber Raso Da Indexação
    2 3 4 5 Ministério da Cidadania e GetNet apresentam CURADORIA DE MARCELLO DANTAS FAROL SANTANDER 8 DE OUTUBRO DE 2019 A 5 DE JANEIRO DE 2020 Convidamos a todos para um passeio pela cultura de cinco continentes por meio da exposição ETNOS – Faces da Diversidade. A mostra apresenta 150 máscaras que expressam a multiplicidade da representação facial como instrumento de reconhecimento da identidade humana. Ao considerar que as máscaras nos dão a possibilidade de falar uma linguagem universal que não depende de idiomas, a exposição nos convida a refletir sobre a existência de uma comunicação não verbal que se estabelece, primordial- mente, por meio de símbolos. A sensação de mistério e encantamento propor- cionados pela evidência de uma linguagem capaz de prescindir do discurso, desconstrói convicções e concepções prévias e nos estimula à formulação de perguntas para as quais podem existir várias e distintas respostas. Um olhar atento e curioso para a multiplicidade de expressões que o ser humano se habilitou a produzir desde tempos ancestrais até a contempora- neidade foi o que nos conduziu para a construção desse projeto tão singular que agora trouxemos ao Farol Santander em São Paulo. PATRICIA AUDI Vice-Presidente de Comunicação, Marketing, Relações Institucionais e Sustentabilidade Santander 8 ETNOS FACES DA DIVERSIDADE MARCELLO DANTAS 12 MÁSCARAS – ANCESTRALIDADES EM CONSTRUÇÃO MARIA CATARINA DUNCAN 24 EXPOSIÇÃO EXHIBITION 99 TEXTOS EM INGLÊS ENGLISH TEXTS 10 ETNOS FACES DA DIVERSIDADE MARCELLO DANTAS CURADOR “Os mitos são sonhos públicos; os sonhos são mitos privados”. Joseph Campbell O que diferencia uma etnia de outra não são os cor- de mil faces,2 sobre o papel que tais instrumentos pos, não são os anseios de felicidade e nem o ins- desempenham na vivência dos mitos (algo próximo tinto de vida e de amor.
    [Show full text]
  • February 2021
    FEBRUARY 2021 Division Director’s Message Celebrating Black History Month The Origins of Black History Month In 1920, the Universal Negro Improvement Association sponsored the First International Convention of the Negro Peoples of the World, it convened in New York for a month- U. Desmond Alufohai long event and, included 20,000 delegates, from 25 nations. Director On August 31st, the Declaration of the Rights of the Negro Protocol & International Affairs Division People of the World was adopted. Paragraph 39 of the document established “That Miami-Dade Aviation Department the colors, Red, Black and Green, be the colors of the Negro race”. Each color has a symbolic meaning: red, the shared blood of the people as well as the blood shed Black History Month, a.k.a. National African American History Month had while fighting for liberation; black, the people; and green, growth and the lush its origins in 1915 when historian and vegetation of Africa. Over the years, the flag has been known by several names, author Dr. Carter G. Woodson including the Black Liberation Flag, Pan-African Flag, Universal African Flag, and founded the Association for the Study Afro-American Unity Flag. To this day, the flag and its colors remain symbols of of African American Life and History. pride and culture. The organization initiated the first Negro History Week in February 1926. In 1926, Dr. Carter G. Woodson, an American historian, author, journalist, and founder of the Association for the Study of African Kent State University (KSU), Kent, American Life and History, announced that the second week of Ohio is located along the Cuyahoga River in Northeast Ohio on the western February would be “Negro History Week”.
    [Show full text]
  • Age Estimation and Cultural Event Recognition
    ChaLearn Looking at People 2015 new competitions: Age Estimation and Cultural Event Recognition Sergio Escalera Jordi Gonzalez` Xavier Baro´ Pablo Pardo University of Barcelona Univ. Autonoma` de Barcelona Universitat Oberta de Catalunya University of Barcelona Computer Vision Center, UAB Computer Vision Center, UAB Computer Vision Center, UAB Email: [email protected] Email: [email protected] Email: [email protected] Email: [email protected] Junior Fabian Marc Oliu Hugo Jair Escalante Ivan Huerta Univ. Autonoma` de Barcelona University of Barcelona INAOE University of Venezia Computer Vision Center, UAB Computer Vision Center, UAB Email: [email protected] Email: [email protected] Email: [email protected] Email: [email protected] Isabelle Guyon Clopinet, Berkeley Email: [email protected] Abstract—Following previous series on Looking at People and context. Therefore, how to combine and exploit all this (LAP) challenges [1], [2], [3], in 2015 ChaLearn runs two new knowledge from pixels constitutes an interesting problem. competitions within the field of Looking at People: age and cul- tural event recognition in still images. We propose the first crowd- This motivates our choice to organize a new workshop and sourcing application to collect and label data about apparent a competition on this topic to sustain the effort of the computer age of people instead of the real age. In terms of cultural event vision community. These new competitions come as a natural recognition, tens of categories have to be recognized. This involves evolution from our previous workshops at CVPR 2011, CVPR scene understanding and human analysis. This paper summarizes 2012, ICPR 2012, ICMI 2013, and ECCV 2014.
    [Show full text]
  • Chalearn Multi-Modal Gesture Recognition
    Human Pose Recovery and Behavior Analysis Group ChaLearn Looking at People 2015 new competitions: Age Estimation and Cultural Event Recognition Sergio Escalera, UB & CVC & ChaLearn Jordi Gonzàlez, UAB & CVC Xavier Baró, UOC & CVC Pablo Pardo, UB Junior Fabian, UAB & CVC Marc Oliu, UB & CVC Hugo J. Escalante, INAOE & ChaLearn Ivan Huerta, University of Venezia Isabelle Guyon, ChaLearn http://gesture.chalearn.org/ All rights reserved HuBPA© Human Pose Recovery and Behavior Analysis Group http://gesture.chalearn.org/ Index • ChaLearn Looking at People events • ChaLearn Looking at People Cultural Event Recognition • ChaLearn Looging at People Age Recognition • Ongoing and upcoming events 2 Human Pose Recovery and Behavior Analysis Group ChaLearn events http://gesture.chalearn.org/ ChaLearn Gesture Recognition Challenges and Workshops •Quantitative competition: CVPR 2011 - Workshop and Challenge •One-shot learning on Gesture Recognition •New depth-rgb data set CVPR 2012 - Workshop and Challenge •Dictionaries among 5-8 on Gesture Recognition gesture categories •Leveinstein: recognizing list ICPR 2012 - Workshop and Challenge of sequences within each on Gesture Recognition sequence •Quantitative competition: ICMI 2013 - Workshop and •User independent multiple instance Challenge on Gesture learning Recognition •New depth-rgb-mask-skeleton- ECCV 2014 – Workshop and audio data set Challenge on Human Pose, •Dictionary of 20 gesture categories Action and Gesture •Leveinstein: recognizing list of Recognition gestures within each sequence 3 Human Pose
    [Show full text]
  • Most Important Carnivals in Italy 2017
    MOST IMPORTANT CARNIVALS IN ITALY 2017 CARNIVAL OF VENICE Venice – 11– 28 February 2017 www.carnevale.venezia.it During the world’s most famous masked “open city “ party, every corner of Venice flourishes with chances to have fun and becomes a multicoloured series of shows, parades, masks and much more. St Mark’s Square, the true centre of the party, is transformed into a continuous workshop of colours, masks, music and shows hosting Carnival’s traditional events such as “Flight of the Angel” , “Festa delle Marie” and “La Colombina”. Palaces throughout the city host grand masked balls for those who want to immerse themselves in the Serenissima’s festive history. CARNIVAL OF VIAREGGIO Viareggio – 5,12,18,26,28 February 2017 http://viareggio.ilcarnevale.com/ The most flamboyant of all the Italian Carnivals, famous for its political satire will hosts the traditional shows of gigantic paper-mache figures on colourful floats. See above dates. Other events include: big parties, sports events, slang theatre show, food stalls etc. HISTORIC CARNIVAL OF IVREA Ivrea - Piedmont 11 Feb – 1 Mar 2017 http://www.storicocarnevaleivrea.it/ Traditional sounds of pipe and drum bands open the festival that sees the most spectacular event of the famous Battle of the Oranges (28 February). Undoubtedly, this is the most spectacular event of the festivities representing the fight for liberty, the symbol of the Ivrea Carnival. The orange battle is an incredible cultural and goliardic heritage putting the festival on a national and international level. CARNIVALE DEI FIGLI DI BOCCO Castiglion Fibocchi - Arezzo – 12 & 19 February 2017 www.carnevaledeifiglidibocco.it This Carnival takes place in Castiglion Fibocchi, a town near Arezzo.
    [Show full text]
  • Chalearn Looking at People 2015: Apparent Age and Cultural Event Recognition Datasets and Results
    ChaLearn Looking at People 2015: Apparent Age and Cultural Event Recognition datasets and results Sergio Escalera Junior Fabian Pablo Pardo Universitat de Barcelona and CVC Computer Vision Center Universitat de Barcelona Xavier Baro´ Jordi Gonzalez` Hugo J. Escalante Universitat Oberta de Catalunya Universitat Autonoma` de Barcelona INAOE Mexico Computer Vision Center Computer Vision Center Dusan Misevic Ulrich Steiner Isabelle Guyon Center for Research and Interdisciplinarity Max-Planck Odense Center Clopinet, ChaLearn Abstract as well as technical limitations such as spatial and temporal resolution. Facial expressions analysis and age estimation Following previous series on Looking at People (LAP) are hot topics in Looking at People that serve as additional competitions [14, 13, 11, 12, 2], in 2015 ChaLearn ran two cues to determine human behavior and mood indicators. Fi- new competitions within the field of Looking at People: (1) nally, images of cultural events constitute a very challeng- age estimation, and (2) cultural event recognition, both in ing recognition problem due to a high variability of gar- still images. We developed a crowd-sourcing application to ments, objects, human poses and scene context. Therefore, collect and label data about the apparent age of people (as how to combine and exploit all this knowledge from pixels opposed to the real age). In terms of cultural event recog- constitutes an interesting problem. nition, one hundred categories had to be recognized. These These challenges motivated our choice to organize a new tasks involved scene understanding and human body anal- ICCV workshop and a competition on these topics to sus- ysis. This paper summarizes both challenges and data, as tain the effort of the computer vision community.
    [Show full text]