Understanding video transformers for segmentation: A survey of application and interpretability

R Karim, RP Wildes - arxiv preprint arxiv:2310.12296, 2023 - arxiv.org
Video segmentation encompasses a wide range of categories of problem formulation, eg,
object, scene, actor-action and multimodal video segmentation, for delineating task-specific …

Interpretable deep feature propagation for early action recognition

H Zhao, RP Wildes - arxiv preprint arxiv:2107.05122, 2021 - arxiv.org
Early action recognition (action prediction) from limited preliminary observations plays a
critical role for streaming vision systems that demand real-time inference, as video actions …

[PDF][PDF] NEURAL NETWORKS TRAINING ACCELERATION THROUGH WEIGHT PREDICTION

QM Nguyen - 2023 - trepo.tuni.fi
Researchers have successfully improved the inference speed of deep learning models
through various algorithmic or hardware acceleration methods. However, the process of …

MMC Transformer: Multiscale Multigrid Comparator Transformer for Few-Shot Video Segmentation

M Siam, KG Derpanis, R Wildes - openreview.net
Learning to compare support and query feature sets for few-shot image and video
understanding has been shown to be a powerful approach. Typically, methods limit feature …