https://hackerpaper.kaipfister.de/p/1711.11248/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMThttps://news.ycombinator.com/item?id=21096478urn:hackerpapers:submission:1711.11248:21096478Fri, 27 Sep 2019 21:33:10 GMT<p>IG65M-PyTorch: video models pre-trained on over 65M Instagram videos</p><p>Think: resnet+imagenet but for videos: https://github.com/moabitcoin/ig65m-pytorch We ported the r(2+1)d model (from CVPR 2018, see https://arxiv.org/abs/1711.11248) and the weights pre-trained by Facebook Research on over 65 million Instagram videos (from CVPR 2019, https://arxiv.org/abs/1905.00561) to PyTorch and released architecture, weights, tools for conversion, and feature extraction example. The official Facebook Research codebase can be found at https://github.com/facebookresearch/vmz These models and pre-trained weights are immensly powerful e.g. for fine-tuning on action…</p><p>10 points; 0 discussion replies on HN. <a href="https://hackerpaper.kaipfister.de/p/1711.11248/">Paper and source history</a>. A submission is not an endorsement.</p>cs.CV