Background Suppression Network for Weakly-supervised Temporal Action Localization
Weakly-supervised temporal action localization is a very challenging problem because frame-wise labels are not given in the training stage while the only hint is video-level labels: whether each video contains action frames of interest. Previous methods aggregate frame-level class scores to produce video-level prediction and learn from video-level action labels. 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. In this paper, we design Background Suppression Network (BaS-Net) which introduces an auxiliary class for background and has a two-branch weight-sharing architecture with an asymmetrical training strategy. This enables BaS-Net to suppress activations from background frames to improve localization performance. Extensive experiments demonstrate the effectiveness of BaS-Net and its superiority over the state-of-the-art methods on the most popular benchmarks - THUMOS'14 and ActivityNet. Our code and the trained model are available at https://github.com/Pilhyeon/BaSNet-pytorch.
Code (2)
Tasks
Action LocalizationTemporal Action LocalizationWeakly Supervised Action LocalizationWeakly-supervised Temporal Action LocalizationSimilar Papers 제목 키워드 기반
Weakly supervised temporal action localization with actionness-guided false positive suppression
Weakly supervised temporal action localization aims to locate the temporal boundaries of action instances in untrimmed videos using video-level labels and assign them the corresponding action category. Generally, it is s…
Action LocalizationTemporal Action LocalizationWeakly Supervised Action LocalizationWeakly-supervised Temporal Action LocalizationCross-Modal Background Suppression for Audio-Visual Event Localization
Audiovisual Event (AVE) localization requires the model to jointly localize an event by observing audio and visual information. However, in unconstrained videos, both information types may be inconsistent or suffer f…
audio-visual event localizationWeakly-Supervised Temporal Action Localization Through Local-Global Background Modeling
Weakly-Supervised Temporal Action Localization (WS-TAL) task aims to recognize and localize temporal starts and ends of action instances in an untrimmed video with only video-level label supervision. Due to lack of negat…
Action LocalizationTemporal Action LocalizationWeakly-supervised LearningWeakly-supervised Temporal Action LocalizationWeakly-supervised Temporal Action Localization by Uncertainty Modeling
Weakly-supervised temporal action localization aims to learn detecting temporal intervals of action classes with only video-level labels. To this end, it is crucial to separate frames of action classes from the backgroun…
Action ClassificationAction LocalizationMultiple Instance LearningOut-of-Distribution Detection+3Weakly-supervised Action Localization with Background Modeling
We describe a latent approach that learns to detect actions in long sequences given training videos with only whole-video class labels. Our approach makes use of two innovations to attention-modeling in weakly-supervised…
Action LocalizationWeakly Supervised Action LocalizationWeakly-supervised Learning