Video action understanding

MS Hutchinson, VN Gadepally - IEEE Access, 2021 - ieeexplore.ieee.org
Many believe that the successes of deep learning on image understanding problems can be
replicated in the realm of video understanding. However, due to the scale and temporal …

Why can't i dance in the mall? learning to mitigate scene bias in action recognition

J Choi, C Gao, JCE Messou… - Advances in Neural …, 2019 - proceedings.neurips.cc
Human activities often occur in specific scene contexts, eg, playing basketball on a
basketball court. Training a model using existing video datasets thus inevitably captures and …

[PDF][PDF] Video action understanding: A tutorial

M Hutchinson, V Gadepally - ar** of Drosophila with a 2D–3D hybrid CNN framework
Z Jiang, PL Chazot, ME Celebi, D Crookes… - IEEE Access, 2019 - ieeexplore.ieee.org
Behavioural phenoty** of drosophila is an important means in biological and medical
research to identify the genetic, pathologic, or psychological impact on animal behavior …

Poseg: Pose-aware refinement network for human instance segmentation

D Zhou, Q He - IEEE Access, 2020 - ieeexplore.ieee.org
Human instance segmentation is a core problem for human-centric scene understanding
and segmenting human instances poses a unique challenge to vision systems due to large …

[書籍][B] Spatio-Temporal Action Instance Segmentation and Localisation

S Saha, G Singh, M Sapienza, PHS Torr, F Cuzzolin - 2020 - Springer
Current state-of-the-art human action recognition is focused on the classification of
temporally trimmed videos in which only one action occurs per frame. In this work we …

Action Recognition with Knowledge Transfer

JW Choi - 2021 - vtechworks.lib.vt.edu
Recent progress on deep neural networks has shown remarkable action recognition
performance from videos. The remarkable performance is often achieved by transfer …