**！！！[New]！！！ Update: The final ranking is announced and the leader of the top 3 teams please send a confirmation email to [zenghaoqi@huawei.com]. Please also indicate your team name in the email.**


| #Rank|Team Name | Total 1-Place Number | Total 2-Place Number | The highest ranking except for first and second place |
|:---:|:---:|:---:|:---:|:---:|
| #1|DragonBooOOM | 4 | - | - |
| #2|USTC_IAT_United|  1| 1 | - |
| #3|damNull|  1| 0 | 5 |


Congratulations to all the winners! For ranking details, please refer to the following Public Per-Metric Leaderboard Results.

------------------------------------------

**Public Per-Metric Leaderboard Results**

![](https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F7542929%2Fbaf4731e9a496885fae29a5d1b40f0c5%2Fresult.png?generation=1704960241973483&alt=media)

**Note**: Only valid submissions that meet the correct format were evaluated, we recruited over 30 participants to do subjective evaluations. Moreover,  we also observe that objective metrics are not consistent with human subjective evaluations, which is the same as the findings of Kucherenko et al. [1].

**Reference**
[1] Kucherenko, Taras, et al. "Evaluating gesture-generation in a large-scale open challenge: The GENEA Challenge 2022." arXiv preprint arXiv:2303.08737 (2023).

------------------------------------------


**Happy New Year! The competition is now closed for submission and we will evaluate the results and announce the final results once we finish all the evaluations.**

**Please verify that your submission meets the correct format (a zip file containing videos with a resolution of 288x512 and a CSV file). Submissions with videos of other resolutions or in illegal formats will be rejected.**

Nonverbal behaviors, especially co-speech gestures, are vital for face-to-face communication. Studies have shown that gestures can help express intentions, convey emotions, and complement the information conveyed by speech. Recent research has demonstrated that machine learning-based approaches play an increasingly critical role in motion synthesis, which has become the primary method for co-speech gesture synthesis.

In this task, participants are required to synthesize co-speech gesture videos of a target person based on any given audio. The final output should be a rendered video, instead of motion sequences. Generally, the synthesized gesture motions in this task are expected to be natural, difficult to distinguish from captured videos, and consistent with audio in terms of rhythm, semantics, and style. We encourage participants to propose novel ideas for synthesizing high-fidelity co-speech gestures.

Specifically, we will provide two video clips for each target person, one (about 5 minutes) for training, and one (about 1 minute) for validation. We will also provide a testing audio for the participants to generate the final result video for the target person.

### Prizes
$1,800 will be awarded to the Top 3 teams with the highest scores at the conclusion of the competition:
- 1st Place - $ 1,000
- 2nd Place - $ 500
- 3rd Place - $ 300

**Note that teams that win the prize should submit their code and technical reports at the end of the competition.**