Browse > Computer Vision > Weakly Supervised Action Localization

Weakly Supervised Action Localization

8 papers with code · Computer Vision

In this task, the training data consists of videos with a list of activities in them without any temporal boundary annotations. However, while testing, given a video, the algorithm should recognize the activities in the video and also provide the start and end time.

Leaderboards

Greatest papers with code

UntrimmedNets for Weakly Supervised Action Recognition and Detection

CVPR 2017 wanglimin/UntrimmedNet

We exploit the learned models for action recognition (WSR) and detection (WSD) on the untrimmed video datasets of THUMOS14 and ActivityNet.

TEMPORAL ACTION LOCALIZATION WEAKLY SUPERVISED ACTION LOCALIZATION

Completeness Modeling and Context Separation for Weakly Supervised Temporal Action Localization

CVPR 2019 Finspire13/CMCS-Temporal-Action-Localization

In this work, we first identify two underexplored problems posed by the weak supervision for temporal action localization, namely action completeness modeling and action-context separation.

WEAKLY SUPERVISED ACTION LOCALIZATION WEAKLY-SUPERVISED TEMPORAL ACTION LOCALIZATION

Background Suppression Network for Weakly-supervised Temporal Action Localization

22 Nov 2019Pilhyeon/BaSNet-pytorch

This formulation does not fully model the problem in that background frames are forced to be misclassified as action classes to predict video-level labels accurately.

WEAKLY SUPERVISED ACTION LOCALIZATION WEAKLY-SUPERVISED TEMPORAL ACTION LOCALIZATION

Guess Where? Actor-Supervision for Spatiotemporal Action Localization

5 Apr 2018escorciav/roi_pooling

Second, we propose an actor-based attention mechanism that enables the localization of the actions from action class labels and actor proposals and is end-to-end trainable.

ACTION LOCALIZATION WEAKLY SUPERVISED ACTION LOCALIZATION

3C-Net: Category Count and Center Loss for Weakly-Supervised Action Localization

ICCV 2019 naraysa/3c-net

Our joint formulation has three terms: a classification term to ensure the separability of learned action features, an adapted multi-label center loss term to enhance the action feature discriminability and a counting loss term to delineate adjacent action sequences, leading to improved localization.

WEAKLY SUPERVISED ACTION LOCALIZATION WEAKLY-SUPERVISED TEMPORAL ACTION LOCALIZATION