-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Thatipelli_2022_CVPR, author = {Thatipelli, Anirudh and Narayan, Sanath and Khan, Salman and Anwer, Rao Muhammad and Khan, Fahad Shahbaz and Ghanem, Bernard}, title = {Spatio-Temporal Relation Modeling for Few-Shot Action Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2022}, pages = {19958-19967} }
Spatio-Temporal Relation Modeling for Few-Shot Action Recognition
Abstract
We propose a novel few-shot action recognition framework, STRM, which enhances class-specific feature discriminability while simultaneously learning higher-order temporal representations. The focus of our approach is a novel spatio-temporal enrichment module that aggregates spatial and temporal contexts with dedicated local patch-level and global frame-level feature enrichment sub-modules. Local patch-level enrichment captures the appearance-based characteristics of actions. On the other hand, global frame-level enrichment explicitly encodes the broad temporal context, thereby capturing the relevant object features over time. The resulting spatio-temporally enriched representations are then utilized to learn the relational matching between query and support action sub-sequences. We further introduce a query-class similarity classifier on the patch-level enriched features to enhance class-specific feature discriminability by reinforcing the feature learning at different stages in the proposed framework. Experiments are performed on four few-shot action recognition benchmarks: Kinetics, SSv2, HMDB51 and UCF101. Our extensive ablation study reveals the benefits of the proposed contributions. Furthermore, our approach sets a new state-of-the-art on all four benchmarks. On the challenging SSv2 benchmark, our approach achieves an absolute gain of 3.5% in classification accuracy, as compared to the best existing method in the literature. Our code and models are available at https://github.com/Anirudh257/strm.
Related Material