Weakly Supervised Action Localization by Sparse Temporal Pooling Network

Code

• github.com/demianzhang/weakly-action-localization
  none★ 0
• github.com/Lin716/STPN-lin
  none★ 0
• github.com/HoganZhang/weakly-action-localization
  none★ 0

Abstract

We propose a weakly supervised temporal action localization algorithm on untrimmed videos using convolutional neural networks. Our algorithm learns from video-level class labels and predicts temporal intervals of human actions with no requirement of temporal localization annotations. We design our network to identify a sparse subset of key segments associated with target actions in a video using an attention module and fuse the key segments through adaptive temporal pooling. Our loss function is comprised of two terms that minimize the video-level action classification error and enforce the sparsity of the segment selection. At inference time, we extract and score temporal proposals using temporal class activations and class-agnostic attentions to estimate the time intervals that correspond to target actions. The proposed algorithm attains state-of-the-art results on the THUMOS14 dataset and outstanding performance on ActivityNet1.3 even with its weak supervision.

Tasks

Benchmark Results

Reproductions