Video-understanding Tag - Viblo https://viblo.asia/rss Sun* Inc. https://viblo.asia/logo_full.svg https://viblo.asia/logo_full.svg Video-understanding Tag - Viblo https://viblo.asia/rss vi-vn 2026-09-14T02:14:00+07:00 <![CDATA[Paper reading | VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking]]> https://viblo.asia/p/paper-reading-videomae-v2-scaling-video-masked-autoencoders-with-dual-masking-W13VMj1G4Y7 https://viblo.asia/p/paper-reading-videomae-v2-scaling-video-masked-autoencoders-with-dual-masking-W13VMj1G4Y7 Viblo AI 2025-07-19 16:21:40 <![CDATA[Paper reading | VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking]]> https://viblo.asia/p/paper-reading-videomae-v2-scaling-video-masked-autoencoders-with-dual-masking-qPoL72XlJvk https://viblo.asia/p/paper-reading-videomae-v2-scaling-video-masked-autoencoders-with-dual-masking-qPoL72XlJvk Viblo AI 2023-12-14 15:00:00 <![CDATA[Paper reading | VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training]]> https://viblo.asia/p/paper-reading-videomae-masked-autoencoders-are-data-efficient-learners-for-self-supervised-video-pre-training-zXRJ8bdqVGq https://viblo.asia/p/paper-reading-videomae-masked-autoencoders-are-data-efficient-learners-for-self-supervised-video-pre-training-zXRJ8bdqVGq Viblo AI 2023-11-08 16:00:11 <![CDATA[Paper reading | Rethinking Video ViTs: Sparse Video Tubes for Joint Image and Video Learning]]> https://viblo.asia/p/paper-reading-rethinking-video-vits-sparse-video-tubes-for-joint-image-and-video-learning-y37LdEPRVov https://viblo.asia/p/paper-reading-rethinking-video-vits-sparse-video-tubes-for-joint-image-and-video-learning-y37LdEPRVov Viblo AI 2023-11-06 15:00:00 <![CDATA[[Paper Explain][End-to-End Dense Video Captioning with Parallel Decoding] PDVC - Hướng tiếp cận end-to-end với giải mã song song cho bài toán Dense Video Captioning]]> https://viblo.asia/p/paper-explainend-to-end-dense-video-captioning-with-parallel-decoding-pdvc-huong-tiep-can-end-to-end-voi-giai-ma-song-song-cho-bai-toan-dense-video-captioning-gDVK2PaAlLj https://viblo.asia/p/paper-explainend-to-end-dense-video-captioning-with-parallel-decoding-pdvc-huong-tiep-can-end-to-end-voi-giai-ma-song-song-cho-bai-toan-dense-video-captioning-gDVK2PaAlLj Hữu Đạt 2022-06-16 18:03:35 <![CDATA[[Paper Explained] TimeSformer: Are Transformers the Game-changer for Action Recognition?]]> https://viblo.asia/p/paper-explained-timesformer-are-transformers-the-game-changer-for-action-recognition-oOVlYJoy58W https://viblo.asia/p/paper-explained-timesformer-are-transformers-the-game-changer-for-action-recognition-oOVlYJoy58W Quang Trần 2021-08-30 10:36:45 <![CDATA[Video Understanding: Tổng quan]]> https://viblo.asia/p/video-understanding-tong-quan-GrLZDRzJ5k0 https://viblo.asia/p/video-understanding-tong-quan-GrLZDRzJ5k0 Bui Tien Tung 2021-08-19 00:08:36