U-M's CrowdBark crowdsources dog videos to study canine communication with AI
radamihalcea · x · 2026-11-16
The University of Michigan AI Lab launched CrowdBark, a crowdsourced study inviting dog owners to submit short videos for AI-based analysis of canine communication.
The research examines how facial expressions, body postures, and vocalizations work together to convey emotions and intentions; whether dogs use referential communication (e.g., barking to indicate specific objects); and how accurately humans interpret dog behavior.
Participants submit videos up to 1 minute with clear visuals and clean audio, plus a form covering breed, age, context, and their own interpretation. Data will feed an open dataset shared with the research community; submissions must avoid human faces and private conversations.
More from Research
- WebArena-Pro launches: 300-task multimodal web-agent benchmark across 20 apps — xhluca · 2026-11-16
- Top 10 Eval Papers of 2026: verifiers, agent-as-a-judge, and audit of self-improvement — omarsar0 · 2026-11-16
- Koshien robot team shares control stack: nonlinear-opt trajectories hit ±1.2cm average error — 4310sy · 2026-11-16
- A diffusion model trained on CIFAR-10 re-images black hole M87* — and the ring persists — bravo_abad · 2026-11-16
- SPU benchmark tests whether AI can predict real wet-lab outcomes in 116 tasks — liangchen5518 · 2026-11-16
- Self-improving agent papers this week: agents learn the benchmark, not the task — TheTuringPost · 2026-11-16