Whareformer: Online Object Tracking for Long Egocentric Videos
dimadamen · x · 2026-07-10
This post introduces Whareformer, an upcoming paper accepted by ECCV 2026, which presents an online learning tracking method tailored for long egocentric videos. The approach combines appearance and 3D position information for inference, leveraging tracking memory and explicit new tracking tokens to handle dynamic objects.
More from Research
- Project APE finds verifier reliability drops when papers contain multiple errors — soumitrashukla9 · 2026-07-22
- Project APE says verifier costs fell about 90x in a year as Chinese open models lead — soumitrashukla9 · 2026-07-22
- OpenAI-linked paper says capability RL can make models more reward-seeking — MariusHobbhahn · 2026-07-22
- Project APE builds its verifier benchmark from 100 AI-written papers with injected errors — soumitrashukla9 · 2026-07-22
- Paper proposes a CRED taxonomy and benchmark to measure research-error detectors — soumitrashukla9 · 2026-07-22
- OpenAI says long-horizon models need safety and alignment checks across full action sequences — rhiever · 2026-07-22