eccv-topic-selection
Use when deciding whether a computer-vision project should target ECCV — weighing the two-year even-year cadence against CVPR, ICCV, WACV, BMVC, ACCV, NeurIPS, and journal routes, testing whether the work matches ECCV's breadth from geometry to vision-language, and reading the Koenderink Prize lineage as a durability signal.
Profile →npx skills add brycewang-stanford/Awesome-Journal-Skills --skill eccv-topic-selection --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# ECCV Topic Selection Use this before committing a project to ECCV. The fit question has two layers: *is this an ECCV-shaped paper* (scope, evidence, durability), and *is the even-year calendar the right bet* — because choosing ECCV means the next chance at this venue is two years away, and the same March deadline usually competes with an ICCV or CVPR alternative for the identical result. ## Scope: what ECCV-shaped means ECCV is a general vision flagship with a strong geometric and European heritage: 3D reconstruction, SLAM/SfM, optical flow, recognition, segmentation, video, generative models, vision-language, embodied and applied vision all live in its LNCS volumes. The historical taste signal: ECCV's proceedings carried COCO (2014), SSD and Perceptual Losses (2016), and NeRF and RAFT (2020) — datasets, practical detectors, and representation shifts, not just incremental leaderboard entries. ECVA's **Koenderink Prize** honors a ten-year-old ECCV paper each edition; asking "could this matter in ten years?" is a good severity filter for whether the contribution is a mechanism or a configuration. ## The calendar layer | Situation | Reading | |---|---| | Result ready by February of
- Scope: what ECCV-shaped means
- The calendar layer
- Five questions before committing
- Anti-fit signals
- Decision procedure
- Output format
What does the eccv-topic-selection skill do?
Use when deciding whether a computer-vision project should target ECCV — weighing the two-year even-year cadence against CVPR, ICCV, WACV, BMVC, ACCV, NeurIPS, and journal routes, testing whether the work matches ECCV's breadth from geometry to vision-language, and reading the Koenderink Prize lineage as a durability signal.
How do I install it?
Run `npx skills add brycewang-stanford/Awesome-Journal-Skills --skill eccv-topic-selection --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From brycewang-stanford/Awesome-Journal-Skills, a repository with 984 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.