Upcoming challenge · Dataset being assembled

Kitchen video QA$300 bounty · upcoming: answer operational questions from fixed-camera restaurant and kitchen clips. Dataset being prepared · How scoring works. Two useful views: the draft page (objective, prize, candidate clips) or the build guide (first implementation shape). See live challenges →

The challengeBuild guide

Upcoming challenge - fixed-camera video QA

Build an agent that answers questions from messy kitchen video.

The target is practical: a small restaurant or cloud kitchen already has camera footage and wants plain answers, not a demo. Who did what? Did a required step happen? Was something visible, missing, late, or not possible to tell?

Prize
$300
top valid score, if it clears the benchmark
Data
7-8 clips
public samples plus hidden final clips
Budget
fixed
runtime, frames, and model/API cost capped

What you build

You submit one reproducible program. It receives short fixed-camera clips and a JSON file of questions, then writes a JSON file of answers. No manual review during evaluation.

python answer.py --videos ./clips --questions questions.json --out answers.json

The clips should feel like ordinary operations footage: prep counter, packing station, fryer line, handoff shelf, dish area, storage corner. Public examples may use fixed production cameras; final hidden scoring should use rights-cleared or sponsor-owned footage.

Question types

Objective answers

Yes/no, multiple choice, counts, timestamps, durations, and not-visible answers. Freeform scene descriptions do not decide the winner.

Operational facts

Cap or hairnet visible? Container sealed before handoff? Tray unattended too long? Which station was active? When did a bottleneck start?

No guessing credit

If the order number, face, label, or action is not visible, the right answer is not visible. Guessing should lose points.

Temporal reasoning

Many questions need the order of events, not just a single frame: first sealed bag, last item added, duration unattended, or step before serving.

Scoring draft

Total score is 100 points. The benchmark should be a simple frame-sampling VLM/OCR baseline; the prize should require beating that baseline on the hidden clips.

  • 65 points - answer correctness: structured answers across yes/no, counts, visible states, event order, timestamps, and not-visible cases.
  • 15 points - budget efficiency: valid runs stay under the hard runtime, frame, and model/API budget; cheaper valid runs get credit only if accuracy holds.
  • 15 points - hidden generalization: stable performance across layouts, lighting, cuisines, camera angles, and video quality.
  • 5 points - reproducibility: one-command run, logged frame sampling/model calls, deterministic or near-deterministic outputs.

Candidate video plan

Public raw kitchen CCTV that is both long and usable is scarce. The honest plan is: use public fixed-camera footage for examples, then score final entries on hidden rights-cleared clips. These are the current leads.

Research leadRail Drishti - Railway Kitchen Live CCTV video10:25 operational kitchen CCTV/dashboard-style footage. Strongest public kitchen-CCTV lead, but it is a screen recording.
Research leadJane at the Marketplace restaurant surveillance video - full raw9:54 raw restaurant surveillance. Good duration and camera feel; may be front-of-house or incident-focused, so it needs visual QA.
Fallback leadCommercial Kitchen Breakfast / Opening / Prep9:51 real commercial kitchen prep. More routine operations, but likely creator-shot rather than CCTV.
Fallback leadKitchenGuard - AI for Compliance Monitoring in Restaurants6:42 compliance-monitoring demo with real kitchen views. Relevant to hygiene questions, but not raw eval footage.
Fallback leadBon Appetit - 11 cameras in NYC's busiest brunch restaurant15:12 busy restaurant-service footage. Useful for public workflow questions, but produced and too long unless clipped.
Fallback leadBon Appetit - 12 cameras in a tiny restaurant kitchen11:36 fixed multi-camera kitchen service. Good for workflow and station questions, but produced footage.
Fallback leadBon Appetit - 13 cameras in New York's busiest ramen restaurant9:06 active kitchen line and service. Useful for event ordering and who-did-what public examples.
Anomaly sampleElevated kitchen fire: CCTV footage18:38 fixed CCTV-style incident footage. Useful for anomaly questions after clipping; not routine operations.
Long sample leadLIVEFEED Fauna - 3 hours of real kitchen serviceLong, real working-kitchen footage from Gusto TV. Not CCTV; useful for sample clips if rights are cleared.
Fallback leadBon Appetit - 19 cameras in a Michelin-starred restaurant12-minute fixed-angle restaurant operations. Useful for public examples, not final hidden scoring.
Fallback leadSecurity Camera B&W Restaurant5:51 fixed-camera restaurant footage. Good camera feel, but it is more front-of-house than kitchen.
Dataset leadKaggle - Kitchen Video in RestaurantsClaims restaurant-kitchen video for HACCP analysis. Needs access and license check before use.
Reference onlyCOM Kitchens177 unedited fixed-view cooking videos, but restricted to academic research. Good reference, not a public challenge asset.
Reference onlyEPFL Smart KitchenLong multi-view kitchen action dataset. Lab setting, not a restaurant, but useful for benchmark design.

Why this maps to a real business

A restaurant owner does not need a general video captioner. They need cheap, repeatable checks from footage they already collect: food sitting at handoff, missed sealing steps, cap/hairnet compliance, bottlenecks, spills, or staff activity at a station.

The cost cap matters. A system that spends heavily on every frame is less useful to a small kitchen than one that samples intelligently, asks the right visual questions, and admits when the video does not show enough.

Current status

  • Challenge mechanics are drafted.
  • Public sample candidates are identified, but rights and clip cuts still need a final pass.
  • Final hidden clips should be rights-cleared, anonymized, and not discoverable online.
  • The full machine-readable spec will be published once the clip set and baseline are locked.
Register interestRead scoring draftDownload draft spec