Current state-of-the-art approaches for few-shot action recognition achieve promising performance by conducting frame-level matching on learned visual features. However, they …
A Ray, MH Kolekar - Expert Systems with Applications, 2023 - Elsevier
In this competitive world, the supervision and monitoring of human resources are primary and necessary tasks to drive context-aware applications. Advancement in sensor and …
J Xing, M Wang, Y Ruan, B Chen… - Proceedings of the …, 2023 - openaccess.thecvf.com
Class prototype construction and matching are core aspects of few-shot action recognition. Previous methods mainly focus on designing spatiotemporal relation modeling modules or …
H Tang, J Liu, S Yan, R Yan, Z Li, J Tang - Proceedings of the 31st ACM …, 2023 - dl.acm.org
Due to the scarcity of manually annotated data required for fine-grained video understanding, few-shot fine-grained (FS-FG) action recognition has gained significant …
Y Huang, L Yang, Y Sato - European Conference on Computer Vision, 2022 - Springer
Few-shot action recognition aims to recognize novel action classes using only a small number of labeled training samples. In this work, we propose a novel approach that first …
Learning from large-scale contrastive language-image pre-training like CLIP has shown remarkable success in a wide range of downstream tasks recently, but it is still under …
H Xia, K Li, MR Min, Z Ding - Proceedings of the IEEE/CVF …, 2023 - openaccess.thecvf.com
Recent few-shot video classification (FSVC) works achieve promising performance by capturing similarity across support and query samples with different temporal alignment …
We present a novel method for few-shot video classification, which performs appearance and temporal alignments. In particular, given a pair of query and support videos, we conduct …
Few-shot action recognition aims to recognize few-labeled novel action classes and attracts growing attentions due to practical significance. Human skeletons provide explainable and …