conftrace_

i3d model

2 papers

Explore in graph

Also known as

I3D

Co-occurring keywords · papers mentioning both

action recognition (2) full-body transformer (1) optical flow feature (1) feature hallucination (1) bag of word (1) lip reading (1) fisher vector (1) video processing (1) data cleaning (1) pre-trained model (1)

Papers

Clean Text and Full-Body Transformer: Microsoft’s Submission to the WMT22 Shared Task on Sign Language Translation EMNLP 2022 Hallucinating IDT Descriptors and I3D Optical Flow Features for Action Recognition With CNNs ICCV 2019