Multi-Granularity Fusion Network for Proposal and Activity Localization: Submission to ActivityNet Challenge 2019 Task 1 and Task 2

07/29/2019
by   Haisheng Su, et al.
0

This technical report presents an overview of our solution used in the submission to ActivityNet Challenge 2019 Task 1 (temporal action proposal generation) and Task 2 (temporal action localization/detection). Temporal action proposal indicates the temporal intervals containing the actions and plays an important role in temporal action localization. Top-down and bottom-up methods are the two main categories used for proposal generation in the existing literature. In this paper, we devise a novel Multi-Granularity Fusion Network (MGFN) to combine the proposals generated from different frameworks for complementary filtering and confidence re-ranking. Specifically, we consider the diversity comprehensively from multiple perspectives, e.g. the characteristic aspect, the data aspect, the model aspect and the result aspect. Our MGFN achieves the state-of-the-art performance on the temporal action proposal task with 69.85 AUC score and the temporal action localization task with 38.90 mAP on the challenge testing set.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset