Spatio-temporal Relation Modeling for Few-shot Action Recognition

Anirudh Thatipelli, Sanath Narayan, Salman Khan, Rao Muhammad Anwer, Fahad Shahbaz Khan, Bernard Ghanem

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussaConference contributionScientificvertaisarvioitu

2 Sitaatiot (Scopus)


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.

OtsikkoProceedings - 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022
ISBN (elektroninen)978-1-6654-6946-3
DOI - pysyväislinkit
TilaJulkaistu - 2022
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisuussa
TapahtumaIEEE Conference on Computer Vision and Pattern Recognition - New Orleans, Yhdysvallat
Kesto: 18 kesäk. 202224 kesäk. 2022


NimiIEEE Computer Society Conference on Computer Vision and Pattern Recognition
ISSN (painettu)1063-6919
ISSN (elektroninen)2575-7075


ConferenceIEEE Conference on Computer Vision and Pattern Recognition
KaupunkiNew Orleans


Sukella tutkimusaiheisiin 'Spatio-temporal Relation Modeling for Few-shot Action Recognition'. Ne muodostavat yhdessä ainutlaatuisen sormenjäljen.

Siteeraa tätä