Temporal-attentive Covariance Pooling Networks for Video Recognition

Zilin Gao, Qilong Wang, Bingbing Zhang, Qinghua Hu, Peihua Li

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 7 functions out of this paper's own repositories and ran 3 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

Repositories linked to this paper

• ZilinGao/Temporal-attentive-Covariance-Pooling-Networks-for-Video-Recognition — marked official in Papers with Code; named in the paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

For video recognition task, a global representation summarizing the whole contents of the video snippets plays an important role for the final performance. However, existing video architectures usually generate it by using a simple, global average pooling (GAP) method, which has limited ability to capture complex dynamics of videos. For image recognition task, there exist evidences showing that covariance pooling has stronger representation ability than GAP. Unfortunately, such plain covariance pooling used in image recognition is an orderless representative, which cannot model spatio-temporal structure inherent in videos. Therefore, this paper proposes a Temporal-attentive Covariance Pooling (TCP), inserted at the end of deep architectures, to produce powerful video representations. Specifically, our TCP first develops a temporal attention module to adaptively calibrate spatio-temporal features for the succeeding covariance pooling, approximatively producing attentive covariance representations. Then, a temporal covariance pooling performs temporal pooling of the attentive covariance representations to characterize both intra-frame correlations and inter-frame cross-correlations of the calibrated features. As such, the proposed TCP can capture complex temporal dynamics. Finally, a fast matrix power normalization is introduced to exploit geometry of covariance representations. Note that our TCP is model-agnostic and can be flexibly integrated into any video architectures, resulting in TCPNet for effective video recognition. The extensive experiments on six benchmarks (e.g., Kinetics, Something-Something V1 and Charades) using various video architectures show our TCPNet is clearly superior to its counterparts, while having strong generalization ability. The source code is publicly available.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2110.14381")
get_code_for_paper("2110.14381")
have("2110.14381")

Connect an agent — have() is free.