Background-Aware Robust Context Learning for Weakly-Supervised Temporal Action Localization
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Access"
DOI: 10.1109/access.2022.3183789
Abstract: Weakly supervised temporal action localization (WTAL) aims to localize temporal intervals of actions in an untrimmed video using only video-level action labels. Although the learning of the background is an important issue in WTAL, most… read more here.
Keywords: supervised temporal; weakly supervised; action localization; background ... See more keywords
Breaking Winner-Takes-All: Iterative-Winners-Out Networks for Weakly Supervised Temporal Action Localization
Sign Up to like & getrecommendations! Published in 2019 at "IEEE Transactions on Image Processing"
DOI: 10.1109/tip.2019.2922108
Abstract: We address the challenging problem of weakly supervised temporal action localization from unconstrained web videos, where only the video-level action labels are available during training. Inspired by the adversarial erasing strategy in weakly supervised semantic… read more here.
Keywords: supervised temporal; temporal action; action localization; action ... See more keywords
StochasticFormer: Stochastic Modeling for Weakly Supervised Temporal Action Localization
Sign Up to like & getrecommendations! Published in 2023 at "IEEE Transactions on Image Processing"
DOI: 10.1109/tip.2023.3244411
Abstract: Weakly supervised temporal action localization (WS-TAL) aims to identify the time intervals corresponding to actions of interest in untrimmed videos with video-level weak supervision. For most existing WS-TAL methods, two commonly encountered challenges are under-localization… read more here.
Keywords: supervised temporal; localization; weakly supervised; action localization ... See more keywords
Adaptive Two-Stream Consensus Network for Weakly-Supervised Temporal Action Localization
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Transactions on Pattern Analysis and Machine Intelligence"
DOI: 10.1109/tpami.2022.3189662
Abstract: Weakly-supervised temporal action localization (W-TAL) aims to classify and localize all action instances in untrimmed videos under only video-level supervision. Without frame-level annotations, it is challenging for W-TAL methods to clearly distinguish actions and background,… read more here.
Keywords: supervised temporal; localization; weakly supervised; temporal action ... See more keywords