Unsupervised Pre-training for Temporal Action Localization Tasks

by   Can Zhang, et al.

Unsupervised video representation learning has made remarkable achievements in recent years. However, most existing methods are designed and optimized for video classification. These pre-trained models can be sub-optimal for temporal localization tasks due to the inherent discrepancy between video-level classification and clip-level localization. To bridge this gap, we make the first attempt to propose a self-supervised pretext task, coined as Pseudo Action Localization (PAL) to Unsupervisedly Pre-train feature encoders for Temporal Action Localization tasks (UP-TAL). Specifically, we first randomly select temporal regions, each of which contains multiple clips, from one video as pseudo actions and then paste them onto different temporal positions of the other two videos. The pretext task is to align the features of pasted pseudo action regions from two synthetic videos and maximize the agreement between them. Compared to the existing unsupervised video representation learning approaches, our PAL adapts better to downstream TAL tasks by introducing a temporal equivariant contrastive learning paradigm in a temporally dense and scale-aware manner. Extensive experiments show that PAL can utilize large-scale unlabeled video data to significantly boost the performance of existing TAL methods. Our codes and models will be made publicly available at https://github.com/zhang-can/UP-TAL.


page 3

page 8


Boundary-sensitive Pre-training for Temporal Localization in Videos

Many video analysis tasks require temporal localization thus detection o...

TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks

Understanding videos is challenging in computer vision. In particular, t...

A Large-Scale Study on Unsupervised Spatiotemporal Representation Learning

We present a large-scale study on unsupervised spatiotemporal representa...

OpenTAL: Towards Open Set Temporal Action Localization

Temporal Action Localization (TAL) has experienced remarkable success un...

Unsupervised Open-Vocabulary Object Localization in Videos

In this paper, we show that recent advances in video representation lear...

Procedure-Aware Pretraining for Instructional Video Understanding

Our goal is to learn a video representation that is useful for downstrea...

Learning to Localize Actions from Moments

With the knowledge of action moments (i.e., trimmed video clips that eac...

Please sign up or login with your details

Forgot password? Click here to reset