DeepAI AI Chat
Log In Sign Up

Weakly Supervised Temporal Action Localization with Segment-Level Labels

by   Xinpeng Ding, et al.

Temporal action localization presents a trade-off between test performance and annotation-time cost. Fully supervised methods achieve good performance with time-consuming boundary annotations. Weakly supervised methods with cheaper video-level category label annotations result in worse performance. In this paper, we introduce a new segment-level supervision setting: segments are labeled when annotators observe actions happening here. We incorporate this segment-level supervision along with a novel localization module in the training. Specifically, we devise a partial segment loss regarded as a loss sampling to learn integral action parts from labeled segments. Since the labeled segments are only parts of actions, the model tends to overfit along with the training process. To tackle this problem, we first obtain a similarity matrix from discriminative features guided by a sphere loss. Then, a propagation loss is devised based on the matrix to act as a regularization term, allowing implicit unlabeled segments propagation during training. Experiments validate that our method can outperform the video-level supervision methods with almost same the annotation time.


page 3

page 4

page 7

page 14


AutoLoc: Weakly-supervised Temporal Action Localization

Temporal Action Localization (TAL) in untrimmed video is important for m...

ASM-Loc: Action-aware Segment Modeling for Weakly-Supervised Temporal Action Localization

Weakly-supervised temporal action localization aims to recognize and loc...

TransVCL: Attention-enhanced Video Copy Localization Network with Flexible Supervision

Video copy localization aims to precisely localize all the copied segmen...

Action Graphs: Weakly-supervised Action Localization with Graph Convolution Networks

We present a method for weakly-supervised action localization based on g...

LPAT: Learning to Predict Adaptive Threshold for Weakly-supervised Temporal Action Localization

Recently, Weakly-supervised Temporal Action Localization (WTAL) has been...

Spatio-Temporal Action Localization in a Weakly Supervised Setting

Enabling computational systems with the ability to localize actions in v...

Point-Level Temporal Action Localization: Bridging Fully-supervised Proposals to Weakly-supervised Losses

Point-Level temporal action localization (PTAL) aims to localize actions...