Fact: Frame-action cross-attention temporal modeling for efficient action segmentation
Z Lu, E Elhamifar - … of the IEEE/CVF Conference on …, 2024 - openaccess.thecvf.com
We study supervised action segmentation whose goal is to predict framewise action labels
of a video. To capture temporal dependencies over long horizons prior works either improve …
of a video. To capture temporal dependencies over long horizons prior works either improve …
DiffAct++: Diffusion Action Segmentation
Understanding long-form videos requires precise temporal action segmentation. While
existing studies typically employ multi-stage models that follow an iterative refinement …
existing studies typically employ multi-stage models that follow an iterative refinement …
Learning Solution-Aware Transformers for Efficiently Solving Quadratic Assignment Problem
Recently various optimization problems, such as Mixed Integer Linear Programming
Problems (MILPs), have undergone comprehensive investigation, leveraging the …
Problems (MILPs), have undergone comprehensive investigation, leveraging the …
Efficient Temporal Action Segmentation via Boundary-aware Query Voting
Although the performance of Temporal Action Segmentation (TAS) has improved in recent
years, achieving promising results often comes with a high computational cost due to dense …
years, achieving promising results often comes with a high computational cost due to dense …