We use the SMG dataset for the online recognition track here. We deploy a cross-subject evaluation protocol by dividing the 40 subjects into a training group of long sequences from 35 subjects and a testing group of sequences from 5 subjects. MG online recognition track: We jointly evaluate the detection and classification performances of algorithms by using the **F1 score** measurement defined below: F1 =2*Precision*Recall/(Precision+Recall), given a long video sequence that needs to be evaluated, Precision is the fraction of correctly classified MGs among all gestures retrieved in the sequence by algorithms, while Recall (or sensitivity) is the fraction of MGs that have been correctly retrieved over the total amount of annotated MGs. Submission format for online recognition track. Participants must submit their predictions following **the sample format below**. The results will be evaluated on the server and displayed on the ranking list in real-time. The organization team has the right to examine the participants' source code to ensure the reproducibility of the algorithms. The final results and ranking will be confirmed and announced by organizers. ## Submission File Participants must submit their predictions in the a single .csv file. You can check the submission.csv sample file [here](https://drive.google.com/file/d/16BSNZNCdkQSEfrfsGjDXID2tNyI-3eKI/view?usp=sharing). The submission .csv file should consist of the following columns with headers: ID: incremental index class: prediction label start_frame: staring frame end_frame: ending frame sample_id: represents the subject. i.e, sample folder name is Sample0005, the sample_id is 5. ID, class, start_frame, end_frame, sample_id 0,5,35,45,65 1,2,52,65,65 2,4,70,80,55 etc. The old leader board from phase1 (validation) is displayed below. Please submit your final results on the testing data to get your ranking on the final phase2 leader board. [Phase 1 leaderboard](https://drive.google.com/file/d/1TWcDKqRitCdFU0k5Y4n--nNppfhb_a39/view?usp=sharing)