The MOSS module learns and combines multi-order space-time self-similarity features to enhance temporal dynamics modeling in videos across action recognition, VQA, and robotic tasks.
arXiv:2208.01897 (2022)
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
TAG-Head adds a lightweight transformer-plus-time-aligned-graph head to existing 3D backbones to reach new RGB-only state-of-the-art on FineGym and HAA500 while surpassing some multimodal baselines.
citing papers explorer
-
Exploring High-Order Self-Similarity for Video Understanding
The MOSS module learns and combines multi-order space-time self-similarity features to enhance temporal dynamics modeling in videos across action recognition, VQA, and robotic tasks.
-
TAG-Head: Time-Aligned Graph Head for Plug-and-Play Fine-grained Action Recognition
TAG-Head adds a lightweight transformer-plus-time-aligned-graph head to existing 3D backbones to reach new RGB-only state-of-the-art on FineGym and HAA500 while surpassing some multimodal baselines.