Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →brycewang-stanford/acmmm-topic-selection
Use when deciding whether a project is a genuine ACM MM (ACM Multimedia) contribution rather than single-modality work, choosing a thematic area, and routing between ACM MM, CVPR/ICCV, ACL/EMNLP, ICMR, MMSys, NeurIPS/ICLR, and the ACM TOMM journal by finding the cross-modal or media-systems core of the contribution.
Passed 19 of 22 test cases with the skill, and 7 of 22 without it.
and 13 more in the full report
12 fixed7 passed either way3 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 12 test cases the skill fixed. Same model, same prompt, with and without the skill.
We built a C++ high-throughput real-time video streaming pipeline framework that handles multi-camera synchronization and packet loss concealment. The software is fully documented, open-source, and intended for community use. Evaluate where this project fits best in the standard output format with keys [Fit], [Best venue], [Thematic area], [Cross-modal or systems core], [Top rejection risk], and [Next action].
| Checked | Without skill | With skill |
|---|---|---|
| The response rates the overall alignment as strong ACM MM. | Missed | Passed |
| The response selects the Open Source Software Competition track within ACM MM. | Passed | Passed |
The instructions your model reads when the skill loads.
Use this before writing. ACM MM is strongest for work that treats more than one medium at once — vision, audio/speech, language, sensor, interaction — or that advances the systems that transport, index, and render media. The core test is whether the contribution lives at a seam between media.
| Signal in the project | ACM MM reading |
|---|---|
| Two or more modalities that must interact for the result to hold | Core fit — the house genre |
| A reusable media system, framework, or dataset the community adopts | Core fit (Open Source / Dataset tracks) |
| Subjective quality / emotion / engagement measured with a user study | Core fit (human-centric areas) |
| A single-modality benchmark win (vision-only, text-only) | Better at CVPR/ICCV or ACL |
| Retrieval accuracy with no systems or cross-modal novelty | ICMR or SIGIR |
| Media delivery / networking with little content modeling | MMSys |
The main track is split into thematic areas (Multimodal Fusion; Generative and Foundation Models; Search and Recommendation; Emotional and Social Signals; Art and Culture; Systems; Transport and Delivery; Responsible Multimedia; and more). The area is not cosmetic — it selects your reviewers. Name the primary area honestly; if the paper genuinely spans two, pick the one whose reviewers can best judge the contribution, not the application.
test cases passed, vs 7 / 22 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.