wacv-experiments
Use when designing or auditing WACV experiments, covering Applications-track systems evidence (latency, power, robustness under real constraints) versus Algorithms-track matched-baseline novelty, comparative assessment under the deployed condition, uncertainty over seeds and sessions, ablations, and evidence that survives the two-round review.
Profile →npx skills add brycewang-stanford/Awesome-Journal-Skills --skill wacv-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.
# WACV Experiments Use this to build evidence a WACV reviewer accepts in Round 1 instead of sending to Revise and Resubmit. The controlling idea: WACV reviews under **two tracks**, and each track has a different evidence bar. Facts are the WACV 2026/2027 cycles as read on 2026-07-09. ## Evidence by track | Question the reviewer asks | Applications track | Algorithms track | |---|---|---| | Does it work where it must? | Metric **under the deployment constraint** (power/latency/light/data budget) | Metric on the standard benchmark | | Is the comparison fair? | Baselines re-tuned to the **same constraint**, not their defaults | Baselines under **matched backbone/compute** | | What does it cost? | Measured latency, wattage, memory on the **named device** | FLOPs/params/throughput reported honestly | | When does it fail? | Failure cases under the real condition | Ablation isolating the mechanism | | Is the gain real? | Uncertainty over sessions **and** seeds | Uncertainty over seeds; significance where small | The single most common WACV revision request is "you compared against baselines at their defaults, not under your constraint." Pre-empt it: an Applications claim is only supported
- Evidence by track
- The four implicit questions
- Comparative assessment under the deployed condition
- Uncertainty and honesty
- Ablations that isolate the claim
- Reverify each cycle
- Output format
What does the wacv-experiments skill do?
Use when designing or auditing WACV experiments, covering Applications-track systems evidence (latency, power, robustness under real constraints) versus Algorithms-track matched-baseline novelty, comparative assessment under the deployed condition, uncertainty over seeds and sessions, ablations, and evidence that survives the two-round review.
How do I install it?
Run `npx skills add brycewang-stanford/Awesome-Journal-Skills --skill wacv-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.