ChaLearn Looking at People 2014 - Track 3: Gesture Recognition

Organized by xbaro - Current server time: Nov. 14, 2018, 11:09 a.m. UTC

First phase

Development
Feb. 9, 2014, 8 a.m. UTC

End

Competition Ends
May 28, 2014, 11 p.m. UTC

ChaLearn Looking at People Challenge and Workshop 2014

 

Track 3: Gesture Recognition

Challenge overview

ChaLearn organizes in 2014 three parallel challenge tracks on Human Pose Recovery on RGB data, action/interaction spotting on RGB data, and gesture spotting on RGB-Depth data.

Top three ranked participants on each track will be awarded and invited to follow the workshop submission guide for ECCV workshop for inclusion of a description of their system at the ECCV workshop proceedings and submit an extended paper in a special issue on gesture recognition at a high-impact factor journal.

 

 

Track information

More than 14,000 gestures are drawn from a vocabulary of 20 Italian sign gesture categories. The emphasis of this third track is on multi-modal automatic learning of a set of 20 gestures performed by several different users, with the aim of performing user independent continuous gesture spotting.

For each sample, RGB, depth, user segmentation and skeleton information are provided:

Chalearn LAP 2014. Track 3 data modalities

A more detailed information is provided on the data section of the competition.

 

Provided Resources

  • Scripts: With the data, the organizers provides a set of scripts to facilitate the access to the data and use the evaluation metrics. More information is provided on the data page.
  • Contact: In order to clarify any doubt or to ask general assistance, you can contact the organizers at gesturechallenge@googlegroups.com or use the forum on data description page.

ChaLearn Looking at People Challenge and Workshop 2014

 

Track 3: Gesture Recognition

Evaluation Criteria

Recognition performance will be evaluated using the Jaccard Index (overlap). In this sense, for each one of the 20 gesture categories labeled for each RGBD sequences, the Jaccard Index is defined as follows:

Where As,n is the ground truth of action/gesture n at sequence s, and Bs,n is the prediction for such action/gesture at sequence s. For both Tracks 2 and 3, As,n and Bs,n are binary vectors where 1-value entries denote frames in which the n-th action/gesture is being performed.

In the case of false positives (e.g predicting a action that is not on the ground truth), the Jaccard Index will be automatically 0 for that action prediction and that action class will count in the mean Jaccard Index computation. In other words n equals the intersection of action categories appearing in the ground truth and in the predictions.

Participants will be evaluated upon mean Jaccard Index among all actions/gestures categories for all sequences, where all action/gesture categories are independent but not mutually exclusive (in a certain frame more than one action/gesture class can be active). In addition, when computing the mean Jaccard Index all gesture categories will have the same importance. Finally, the participant with the highest mean Jaccard Index will be the winner. An example of the calculation for a single sequence and two action/gesture categories is show in Figure 2.

Figure 2: Example of mean Jaccard Index calculation for different instances of gestures/actions categories in a sequence (single red lines denote ground truth annotations and double red lines denote predictions). In the top part of the image we see the ground truth annotations for actions/gestures walk and fight at a sequence s. In the center part of the image a prediction is evaluated obtaining a Jaccard Index of 0.72. In the bottom part of the image the same procedure is performed with the action fight and the obtained Jaccard Index is 0.46. Finally, the mean Jaccard Index is computed obtaining a value of 0.59.

Submission format

Participants must submit their predictions in the following format. For each sequence SequenceXXXX.zip in the data folder, participants should create a SequenceXXXX_prediction.csv file with a line for each predicted gesture [GestureID, StartFrame, EndFrame] (the same format as SequenceXXXX_labels.csv). The predictions for all the samples will be put in a single ZIP file and submitted to Codalab.

CHALEARN Contest Rules for ChaLearn Looking at People 2014

Official rules

Common terms used in these rules:

These are the official rules that govern how the ChaLearn Looking at People 2014 contest promotion will operate. This promotion will be simply referred to as the “contest” or the “challenge” throughout the rest of these rules and may be abbreviated on our website, in our documentation, and other publications as ChaLearn LAP.

In these rules, “organizers”, “we,” “our,” and “us” refer to CHALEARN; "participant”, “you,” and “yourself” refer to an eligible contest participant.

 

SECTION 1: Contest description

This is a skill-based contest and chance plays no part in the determination of the winner(s). The goal of the contest is split into three competition tracks (with a shared schedule):

Trak1: Human Pose Recovery:

Focus of the Contest: More than 8,000 frames of continuous RGB sequences are recorded and labeled with the objective of performing human pose recovery by means of recognizing more than 120,000 human limbs of different people.

Track 2: Action/Interaction Recognition:

Focus of the Contest: Focus of the Contest: Recognizing actions/interactions using 235 performances of 11 action/interaction categories recorded and manually labeled in continuous RGB sequences of different people performing natural isolated and collaborative behaviors.

Track 3: Gesture Recognition:

Focus of the Contest: Recognizing gestures drawn from a vocabulary of Italian sign gesture categories. The emphasis of this track is on multi-modal automatic learning of a set of 20 gestures performed by several different users, with the aim of performing user independent continuous gesture spotting.

This track follows a previous challenge organized on the same theme: ChaLearn Multi-modal Gesture Recognition 2013. In this new edition, more precise labels are provided, allowing a gesture spotting competition. The data contains more than 900 samples, containing near 14.000 gesture instances and more than 1.4 million of frames.

All eligible entries received for any of the three tracks will be judged using the criteria described in Section 7 to determine winners.

 

SECTION 2: Tentative Contest Schedule

The registered participants will be notified by email of any change in the schedule.

February 9, 2014: Beginning of the quantitative competition, release of development and validation data.

April 24, 2014: Publication of the group registration procedure. All groups must register to participate on the final evaluation stage.

May 1, 2014: Release of encrypted final evaluation data and validation labels. Participants can start training their methods with the whole data set. Deadline for group registration.

May 8, 2014: Deadline for code submission. Participants will be provided with code submission details together with the validation labels (see section 7).

May 9, 2014: Release of final evaluation data decryption key. Participants start predicting the results on the final evaluation data.

May 15, 2014: End of the quantitative competition. Deadline for submitting the predictions over the final evaluation data. Deadline for code submission. The organizers start the code verification by running it on the final evaluation data.

June 1, 2014: Deadline for submitting the fact sheets.

June 10, 2014: Release of the verification results to the participants for review. Top ranked participants are invited to follow the workshop submission guide for inclusion at ECCV 2014 proceedings (pending acceptance) or a ECCV 2014 Satellite Event and will be invited to submit an extension of their work to a high impact factor journal (pending acceptance).

 

SECTION 3: Eligibility

You are eligible to enter this contest if you meet the following requirements:

(a) You are an individual or a team of people desiring to contribute to the tasks of the challenge and accepting to follow its rules; and

(b) You are NOT a resident of any country constrained by US export regulations included in the OFAC sanction page. Therefore residents of these countries/regions are not eligible to participate; and

(c) You are not an employee of CHALEARN; and

(d) You are not involved in any part of the administration and execution of this contest; and

(e) You are not an immediate family (parent, sibling, spouse, or child) or household member of an employee of CHALEARN, or a person involved in any part of the administration and execution of this contest.

This contest is void within the geographic area identified above and wherever else prohibited by law.

If you choose to submit an entry, but are not qualified to enter the contest, this entry is voluntary, and any entry you submit is governed by the remainder of these contest rules; CHALEARN reserves the right to evaluate it for scientific purposes. If you are not qualified to submit a contest entry and still choose to submit one, under no circumstances will such entries qualify for sponsored prizes.

 

SECTION 4: Entry

To be eligible for judging, an entry must meet the following content/technical requirements:

(a) Entry contents:

The participants are required to submit prediction results and code (see section 7). To be eligible for prizes, the top ranking participants are required to publicly release their code under a license of their choice, taken among one of the those: (Apache License 2.0, BSD 3-Clause "New" or "Revised" license, or BSD 2-Clause "Simplified" or "FreeBSD" license) and make their code accessible on-line for a period no less than three year following the end of the challenge, and permit the organizers to upload the code the the Codalab experimental platform to make it available to Codalab users, where it will remain available as long as the organizers wish. To be part of the final ranking the participants will be asked to fill out a survey (fact sheet) briefly describing their method. The top ranking participants will be invited to submit a maximum 8-page paper for the proceedings of the ECCV ChaLearn LAP 2014 workshop (pending acceptance) or ECCV ChaLearn LAP 2014 satellite event, following the event publication guidelines.

(b) Pre-requisite:

There is no pre-requisite to participate, including no requirement to have participated in previous challenges.

(c) Use of data provided:

All data provided by CHALEARN is freely available to the participants from the website of the challenge (codalab.org) under license terms provided with the data.

(1) Test data (final evaluation data):

The organizers will use test data to perform the final evaluation, hence the participants’ final entry will be based on test data.

(2) Training and validation data:

The contest organizers will make available to the participants a training dataset with truth values, and a validation set with no truth values. The validation data will be used by the participants for practice purposes to validate their systems. It will be similar in composition to the test set.

(3) Post-challenge analyses:

The organizers may also perform additional post-challenge analyses using extra data, but the results will not affect the ranking of the challenge performed with the test data.

(d) Submission:

The entries of the participants will be submitted on-line via the Codalab web platform. During the development period, the participants will receive immediate feed-back on validation data released for practice purpose. For the final evaluation, the results will be computed automatically on test data submissions. The performances on test data will not be released until the challenge is over.

(e) Original work, permissions:

In addition, by submitting your entry into this contest you confirm that, to the best of your knowledge:

(1) Your entry is your own original work; and

(2) Your entry only includes material that you own, or that you have permission from the copyright/trademark owner to use.

 

SECTION 5: Potential use of entry

Other than what is set forth below, we are not claiming any ownership rights to your entry. However, by submitting your entry, you:

(a) Are granting us an irrevocable, worldwide right and license, in exchange for your opportunity to participate in the contest and potential prize awards, for the duration of the protection of the copyrights to:

(1) Use, review, assess, test and otherwise analyze results submitted or produced by your code and other material submitted by you in connection with this contest and any future research or contests sponsored by CHALEARN; and

(2) Feature your entry and all its content in connection with the promotion of this contest in all media (now known or later developed);

(b) Agree to sign any necessary documentation that may be required for us and our designees to make use of the rights you granted above;

(c) Understand and acknowledge that sponsors and other entrants may have developed or commissioned materials similar or identical to your submission and you waive any claims you may have resulting from any similarities to your entry;

(d) Understand that we cannot control the incoming information you will disclose to our representatives or our co-sponsor’s representatives in the course of entering, or what our representatives will remember about your entry. You also understand that we will not restrict work assignments of representatives or our co-sponsor’s representatives who have had access to your entry. By entering this contest, you agree that use of information in our representatives’ or our co-sponsor’s representatives unaided memories in the development or deployment of our products or services does not create liability for us under this agreement or copyright or trade secret law;

(e) Understand that you will not receive any compensation or credit for use of your entry, other than what is described in these official rules.

If you do not want to grant us these rights to your entry, please do not enter this contest.

 

SECTION 6: Submission of entries

(a) Follow the instructions on the Codalab website (codalab.org) to submit entries. You must register to the track or tracks you want to participate in.

(b) The participants will be registered as mutually exclusive teams. For final entries, the team leader will be responsible to make the submission. Each team may submit only one single final entry. We are not responsible for entries that we do not receive for any reason, or for entries that we receive but are not functioning properly.

(c) The participants must follow the instructions. We will automatically disqualify incomplete or invalid entries.

 

SECTION 7: Submission of code

(a) During the challenge, participants are encouraged to submit to Codalab their predictions in a ZIP file containing the predictions in the requested format. A submission example for each track will be provided in the track submission section.

(b) For the final evaluation, participants are required to submit a ZIP file following the instructions published with the validation labels, containing:

(1) Executable or source code of their code, which allows to generate the predictions from the data. Although the use of Python is encouraged, any programming language can be used. The entry point must follow the provided format for each track.

(2) All necessary libraries and dependencies to run their code.

(3) Instructions on how to execute their code.

(4) A form disclosing the list of team members.

 

SECTION 8: Judging the entries

The board of CHALEARN will select a panel of judges to judge the entries; all judges will be forbidden to enter the contest and will be experts in causality, statistics, machine learning, or a related field, or experts in challenge organization. A list of the judges will be made available upon request. The judges will review all eligible entries received and select three winners for each of the three competition tracks based upon the prediction score on test data. The judges will verify that the winners complied with the rules, including that they documented their method by filling out a fact sheet that will be provided to the participants.

Evaluation will be performed by submitting prediction results to the challenge track using the Codalab platform. The considered evaluation metric is the overlap (Jaccard index) for all three tracks. Please read Annex I of this document for a detailed explanation and examples of the estimation of the metric.

The decisions of these judges are final and binding. The distribution of prizes according to the decisions made by the judges will be made within three (3) months after completion of the last round of the contest. If we do not receive a sufficient number of entries meeting the entry requirements, we may, at our discretion based on the above criteria, not award any or all of the contest prizes below. In the event of a tie between any eligible entries, the tie will be broken by giving preference to the earliest submission, using the time stamp of the submission platform.

 

SECTION 9: Prizes and Awards

(a) ChaLearn and University of Barcelona are the financial sponsors of this contest. There will be 3000 dollars in prizes awarded as incentive prizes to boost contest participation; these prizes will not require participants to enter into an IP agreement with ChaLearn and University of Barcelona, but it requires to deliver source code to ChaLearn and University of Barcelona for verification.

(b) Incentive Prizes for each of the three track competitions
First place: 500 USD and travel award (*) + Award certificate
Second place: 300 USD and travel award (*) + Award certificate
Third place: 200 USD and travel award (*) + Award certificate

In addition all three top ranked participants for each track will be invited to submit a paper of their winner method following the submission guidelines for ECCV ChaLearn 2014 LAP workshop (pending acceptance) or ECCV ChaLearn LAP 2014 Satellite event, and will be invited to submit an extension of their work to a high impact factor journal (pending acceptance).

(*) The amount will be based on need and availability. The travel award may be used for one of the workshops organized in conjunction with the challenge. The award money will be granted in reimbursement of expenses including airfare, ground transportation, hotel, or workshop registration. Reimbursement is conditioned on (i) attending the workshop, (ii) making an oral presentation of the methods used in the challenge, and (iii) presenting original receipts and boarding passes.

(c) Best paper awards:

CHALEARN will also give a best paper award and a best student paper award for papers submitted to the proceedings of the workshop.

(d) Travel awards:

Other travel awards may be distributed to deserving participants based upon need and availability.

(e) If for any reason the advertised prize is unavailable, unless to do so would be prohibited by law, we reserve the right to substitute a prize(s) of equal or greater value, as permitted. We will only award one prize per team on each track. However different tracks can be awarded to the same team. If you are selected as a potential winner of this contest:

(1) If your prize is not in cash, you may not exchange your prize for cash; you may not exchange any prize for other merchandise or services.

(2) You may not designate someone else as the winner. If you are unable or unwilling to accept your prize, we will award it to an alternate potential winner.

(3) If you accept a prize, you will be solely responsible for all applicable taxes related to accepting the prize.

(4) If you are a minor in your place of residence, we may award the prize to your parent/legal guardian on your behalf and your parent/legal guardian will be designated as the winner.

 

SECTION 11: Notifications

If there is any change to data, schedule, instructions of participation, or these rules, the registered participants will be notified at the email they provided with the registration.

If you are a potential winner, we will notify you by sending a message to the e-mail address listed on your final entry within seven days following the determination of winners. If the notification that we send is returned as undeliverable, or you are otherwise unreachable for any reason, we may award the prize to an alternate winner, unless forbidden by applicable law.

Winners who have entered the contest as a team will be responsible to share any prize among their members. The prize will be delivered to the registered team leader. If this person becomes unavailable for any reason, the prize will be delivered to be the authorized account holder of the e-mail address used to make the winning entry.

If you are a potential winner, we may require you to sign a declaration of eligibility, use, indemnity and liability/publicity release and applicable tax forms. If you are a potential winner and are a minor in your place of residence, and we require that your parent or legal guardian will be designated as the winner, and we may require that they sign a declaration of eligibility, use, indemnity and liability/publicity release on your behalf. If you, (or your parent/legal guardian if applicable), do not sign and return these required forms within the time period listed on the winner notification message, we may disqualify you (or the designated parent/legal guardian) and select an alternate selected winner.

 

SECTION 12: On-line notification

We will post changes in the rules or changes in the data as well as the names of confirmed winners (after contest decisions are made by the judges) online on http://gesture.chalearn.org/. Additionally, a forum has been included to each track in order to provide specific information. This list will remain posted for one year or will be made available upon request by sending email to mmgesture@chalearn.org.

 

SECTION 13: Conditions

By entering this contest you agree:

(a) To abide by these official rules;

(b) To the extent allowable under applicable law, to release and hold harmless CHALEARN and University of Barcelona, their respective parents, subsidiaries, affiliates, employees and agents from any and all liability or any injury, loss, damage, right, claim or action of any kind arising from or in connection with this contest or any prize won save for residents of the United Kingdom, Chile, Korea, Greece, Brazil, Turkey, Hong Kong, France and Germany with respect to claims resulting from death or personal injury arising from CHALEARN’s and University of Barcelona’s negligence, for residents of the United Kingdom with respect to claims resulting from the tort of deceit or any other liabilities that may not be excluded by law, and for residents of Australia in respect of any implied condition or warranty the exclusion of which from these official rules would contravene any statute or cause any part of these official rules to be void;

(c) That CHALEARN’s decisions will be final and binding on all matters related to this contest; and

(d) That by accepting a prize, CHALEARN and University of Barcelona may use your team name, your name, and your place of residence on-line and in print, or in any other media, in connection with this contest, without payment or compensation to you. The declaration of eligibility, use, indemnity and liability/publicity release provided to the potential winner will make reference to obtaining his/her free consent to use his/her name and place of residence. In any case, the lack of such consent does not prevent the winner from receiving the prize.

(e) This contest will be governed by the laws of the state of California, and you consent to the exclusive jurisdiction and venue of the courts of the state of California for any disputes arising out of this contest. For residents of Austria only: you may withdraw your submission from this contest within seven days of your entry. If you withdraw within seven days of entry, your submission will be returned to you, and we will not make any use of your submission in the future. However, you will not be eligible to win a prize. If you do not withdraw within seven days of entry, you will be bound by the provisions of these official rules. For residents of the United Kingdom only: the provisions of the contracts (rights of third parties) act 1999 will not apply to this agreement. For residents of New Zealand only: the provisions of the contracts (privity) act of 1982 will not apply to this agreement. For Quebec residents: any litigation respecting the conduct or organization of a publicity contest may be submitted to the Régie des Alcools, des Courses et des Jeux for ruling. Any litigation respecting the awarding of a prize may be submitted to the Régie only for the purpose of helping the parties reach a settlement. For residents of Israel only: this agreement does not entitle third parties to benefits under this agreement as defined in Chapter “D” of the Contracts Act (General Part) – 1973.

 

SECTION 14: Unforeseen event

If an unforeseen or unexpected event (including, but not limited to: someone cheating; a virus, bug, or catastrophic event corrupting data or the submission platform; someone discovering a flaw in the data or modalities of the challenge) that cannot be reasonably anticipated or controlled, (also referred to as force majeure) affects the fairness and / or integrity of this contest, we reserve the right to cancel, change or suspend this contest. This right is reserved whether the event is due to human or technical error. If a solution cannot be found to restore the integrity of the contest, we reserve the right to select winners based on the criteria specified above from among all eligible entries received before we had to cancel, change or suspend the contest subject to obtaining the approval from the Régie des Alcools, des Courses et des Jeux with respect to the province of Quebec.

Computer “hacking” is unlawful. If you attempt to compromise the integrity or the legitimate operation of this contest by hacking or by cheating or committing fraud in any way, we may seek damages from you to the fullest extent permitted by law. Further, we may ban you from participating in any of our future contests, so please play fairly.

 

SECTION 15: Sponsor

ChaLearn is a sponsor of this contest.
955 Creston Road,
Berkeley, CA 94708, USA
events@chalearn.org

and

Faculty of Mathematics, University of Barcelona (UB) is the co-sponsor of this contest
Gran Via de les Corts Catalanes 585,
08007 Barcelona, Spain
UB member from ChaLearn: sergio@maia.ub.es

 

SECTION 16: Privacy

During the development phase of the contest and when they submit their final entries, contest participants do not need to disclose their real identity, but must provide a valid email address where we can be deliver notifications to them regarding the contest. To be eligible for prizes, however, contest participants will need to disclose their real identity to contest organizers, informing them by email of their name, professional affiliation, and address. To enter the contest, the participants will need to become users of the Codalab platform. Any profile information stored on this platform can be viewed and edited by the users. After the contest, the participants may cancel their account with the Codalab and cease to be users of that platform. All personal information will then be destroyed. The Codalab privacy policy will apply to contest information submitted by participants on the Codalab. Otherwise, CHALEARN’s privacy policy will apply to this contest and to all information that we receive from your entry that we receive directly from you or which you have submitted as part of your contest entry on the Codalab. Please read the privacy policy on the contest entry page before accepting the official rules and submitting your entry. Please note that by accepting the official rules you are also accepting the terms of the CHALEARN privacy policy: http://www.chalearn.org/privacy.html.

 

Annex I

Evaluation measurements for the Chalearn LAP challenge 2014: Human Pose Recovery (Track 1)

It will be used the Jaccard Index (overlapping). Thus, for each one of the n≤14 limbs labeled for each subject on each frame i, the Jaccard Index is defined as follows:

where Ai,n is the ground truth of limb n, and Bi,n is the prediction for the same limb (at image i). For the dataset in this challenge both Ai,n and Bi,n are binary images where ‘1’ pixels denote the region in which the n-th limb is predicted. Particularly, since Ai,n (ground truth) is a binary image and 1-value pixels indicate the region of the n-th limb, this positive region does not necessarily need to be square. However, in all cases the positive region is a polyhedron defined by four points. Thus, numerator is the number ‘1’ pixels that intersects in both images Ai,n and Bi,n, and denominator is the number of union ‘1’ pixels after applying local or operator.

In the case of false positives (e.g predicting a limb that is not on the ground truth because of being occluded), the prediction will not affect the mean Hit Rate calculation. In other words n is computed as the intersection of the limb categories in the ground truth and the predictions.

Participant methods will be evaluated upon hit rate (HR) detection of limbs. That is, for each limb n at each image i a hit will be computed if Ji,n≥0.5. Then, the mean hit rate among all limbs for all images will be computed (where all limb detections will have the same weight) and the participant with the highest mean hit rate will be the winner.

In some images a limb may not labeled in the ground truth because of occlusions. In that case where n<14, participants must not provide with any prediction of that particular limb. An example of the mean hit rate calculation for an example of n=3 limbs and i=1 image is show in Figure 1.

Figure 1: Mean hit rate and Jaccard Index calculation for a sample with n=3 limbs and i=1 image. In the top part of the image the Jaccard Index for the head limb is computed, as it is greater than 0.5 then it computes as a hit for the image i and the head limb. Similarly, for the torso limb the Jaccard Index obtained is 0.72 (center part of the image) which also computes as a hit for torso limb. In addition, in the bottom of the image the Jaccard Index obtained for the left thigh limb is shown, which does not compute as a hit since 0.04

 

 

Evaluation measurements for the Chalearn LAP challenge 2014: Action Recognition on RGB (Track 2) and Multimodal Gesture Recognition (Track 3).

The metrics for the Chalearn LAP 2014 Track 2: Action Recognition on RGB challenge and Track 3: Multimodal Gesture Recognition will follow the trend in Track 1, evaluating the recognition performance using the Jaccard Index (for action/interaction and gesture spotting evaluation). In this sense, for each one of the n≤11 actions categories labeled for each RGB sequence s (Track 2) or the n≤20 gesture categories labeled for each RGBD sequence s (Track 3), the Jaccard Index is defined as follows:

Where As,n is the ground truth of action/gesture n at sequence s, and Bs,n is the prediction for such action/gesture at sequence s. For both Tracks 2 and 3, As,n and Bs,n are binary vectors where 1-value entries denote frames in which the n-th action/gesture is being performed.

In the case of false positives (e.g predicting a action that is not on the ground truth), the Jaccard Index will be automatically 0 for that action prediction and that action class will count in the mean Jaccard Index computation. In other words n equals the intersection of action categories appearing in the ground truth and in the predictions.

Participants will be evaluated upon mean Jaccard Index among all actions/gestures categories for all sequences, where all action/gesture categories are independent but not mutually exclusive (in a certain frame more than one action/gesture class can be active). In addition, when computing the mean Jaccard Index all gesture categories will have the same importance. Finally, the participant with the highest mean Jaccard Index will be the winner. An example of the calculation for a single sequence and two action/gesture categories is show in Figure 2.

Figure 2: Example of mean Jaccard Index calculation for different instances of gestures/actions categories in a sequence (single red lines denote ground truth annotations and double red lines denote predictions). In the top part of the image we see the ground truth annotations for actions/gestures walk and fight at a sequence s. In the center part of the image a prediction is evaluated obtaining a Jaccard Index of 0.72. In the bottom part of the image the same procedure is performed with the action fight and the obtained Jaccard Index is 0.46. Finally, the mean Jaccard Index is computed obtaining a value of 0.59.

Development

Start: Feb. 9, 2014, 8 a.m.

Final Evaluation

Start: May 16, 2014, 7 a.m.

Competition Ends

May 28, 2014, 11 p.m.

You must be logged in to participate in competitions.

Sign In