DeepAI AI Chat
Log In Sign Up

PcmNet: Position-Sensitive Context Modeling Network for Temporal Action Localization

by   Xin Qin, et al.

Temporal action localization is an important and challenging task that aims to locate temporal regions in real-world untrimmed videos where actions occur and recognize their classes. It is widely acknowledged that video context is a critical cue for video understanding, and exploiting the context has become an important strategy to boost localization performance. However, previous state-of-the-art methods focus more on exploring semantic context which captures the feature similarity among frames or proposals, and neglect positional context which is vital for temporal localization. In this paper, we propose a temporal-position-sensitive context modeling approach to incorporate both positional and semantic information for more precise action localization. Specifically, we first augment feature representations with directed temporal positional encoding, and then conduct attention-based information propagation, in both frame-level and proposal-level. Consequently, the generated feature representations are significantly empowered with the discriminative capability of encoding the position-aware context information, and thus benefit boundary detection and proposal evaluation. We achieve state-of-the-art performance on both two challenging datasets, THUMOS-14 and ActivityNet-1.3, demonstrating the effectiveness and generalization ability of our method.


page 1

page 7

page 8


Decoupling Localization and Classification in Single Shot Temporal Action Detection

Video temporal action detection aims to temporally localize and recogniz...

Temporal Action Localization using Long Short-Term Dependency

Temporal action localization in untrimmed videos is an important but dif...

G-TAD: Sub-Graph Localization for Temporal Action Detection

Temporal action detection is a fundamental yet challenging task in video...

Action Sensitivity Learning for Temporal Action Localization

Temporal action localization (TAL), which involves recognizing and locat...

Adaptive Proposal Generation Network for Temporal Sentence Localization in Videos

We address the problem of temporal sentence localization in videos (TSLV...

Modeling Multi-Label Action Dependencies for Temporal Action Localization

Real-world videos contain many complex actions with inherent relationshi...