View publication

Research in action detection has grown in the recent years, as it plays a key role in video understanding. Modelling the interactions (either spatial or temporal) between actors and their context has proven to be essential for this task. While recent works use spatial features with aggregated temporal information, this work proposes to use non-aggregated temporal information. This is done by adding an attention based method that leverages spatio-temporal interactions between elements in the scene along the clip. The main contribution of this work is the introduction of two cross attention blocks to effectively model the spatial relations and capture short range temporal interactions. Experiments on the AVA dataset show the advantages of the proposed approach that models spatio-temporal relations between relevant elements in the scene, outperforming other methods that model actor interactions with their context by +0.31 mAP.

Related readings and updates.

Self-Supervised Temporal Analysis of Spatiotemporal Data

*=Equal Contributors There exists a correlation between geospatial activity temporal patterns and type of land use. A novel self-supervised approach is proposed to stratify landscape based on mobility activity time series. First, the time series signal is transformed to the frequency domain and then compressed into task-agnostic temporal embeddings by a contractive autoencoder, which preserves cyclic temporal patterns observed in time series. The…
See paper details

CVPR 2021

Apple sponsored the annual conference of Computer Vision and Pattern Recognition (CVPR). The conference focuses on computer vision and its applications and took place virtually from June 19 to 25.

See event details