iccv-experiments
Use when designing the experimental program for an ICCV paper against the early-March deadline, covering benchmark-drift audits across the two-year gap, baseline fairness in the foundation-model era, ablations that isolate mechanisms, qualitative and failure evidence, and sequencing runs so the decisive result lands before the deadline, not after.
Profile →npx skills add brycewang-stanford/Awesome-Journal-Skills --skill iccv-experiments --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.
# ICCV Experiments An ICCV experimental program is built under a fixed, unrepeatable date: the early-March deadline of an odd year (March 7 in 2025, with supplement due the same day). The program design problem is therefore *sequencing under a deadline*, on top of the usual question of what evidence convinces a vision reviewer. Both are handled here. ## Start with the benchmark-drift audit Because the venue is biennial, a project conceived after one ICCV and submitted to the next spans two years of field motion. Before designing experiments, audit what moved: ```text drift audit (fill once, in the autumn before the deadline) benchmarks: which datasets did the last two years of CVPR/ECCV/ICCV papers in this area actually evaluate on? any new canonical benchmark? baselines: leaderboard top-3 today vs when the project started → any baseline in your draft older than ~18 months is a red flag backbones: what does current SOTA initialize from? (matching this defines "fair" for your comparisons) metrics: any metric revision or new evaluation server since last cycle? protocols: resolution/prompt/eval-harness conventions that changed ``` Papers rejected for "outdated comparisons" are usually
- Start with the benchmark-drift audit
- The fairness ledger
- Ablations that isolate, not decorate
- Qualitative evidence with stated rules
- Sequencing runs toward March
- The four questions any ICCV review silently asks
- Reverify each cycle
- Output format
What does the iccv-experiments skill do?
Use when designing the experimental program for an ICCV paper against the early-March deadline, covering benchmark-drift audits across the two-year gap, baseline fairness in the foundation-model era, ablations that isolate mechanisms, qualitative and failure evidence, and sequencing runs so the decisive result lands before the deadline, not after.
How do I install it?
Run `npx skills add brycewang-stanford/Awesome-Journal-Skills --skill iccv-experiments --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 909 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.