Corpus ID: 236447522

Enriching Local and Global Contexts for Temporal Action Localization

  title={Enriching Local and Global Contexts for Temporal Action Localization},
  author={Zixin Zhu and Wei Tang and Le Wang and Nanning Zheng and Gang Hua},
Effectively tackling the problem of temporal action localization (TAL) necessitates a visual representation that jointly pursues two confounding goals, i.e., fine-grained discrimination for temporal localization and sufficient visual invariance for action classification. We address this challenge by enriching both the local and global contexts in the popular two-stage temporal localization framework, where action proposals are first generated followed by action classification and temporal… Expand

Figures and Tables from this paper


Gaussian Temporal Awareness Networks for Action Localization
Gaussian Temporal Awareness Networks (GTAN) is presented --- a new architecture that novelly integrates the exploitation of temporal structure into an one-stage action localization framework and achieves superior results when comparing to state-of-the-art approaches. Expand
G-TAD: Sub-Graph Localization for Temporal Action Detection
This work proposes a graph convolutional network (GCN) model to adaptively incorporate multi-level semantic context into video features and cast temporal action detection as a sub-graph localization problem. Expand
Refinement of Boundary Regression Using Uncertainty in Temporal Action Localization
A Gaussian model is constructed for predicting the uncertainty variance of the boundary and improved state-of-the-art mAP@0.5 value and gains significant improvements on both THUMOS14 and ActivityNet v1.3 datasets. Expand
Progressive Boundary Refinement Network for Temporal Action Detection
The proposed end-to-end progressive boundary refinement network (PBRNet) belongs to the family of one-stage detectors and is equipped with three cascaded detection modules for localizing action boundary more and more precisely. Expand
Decoupling Localization and Classification in Single Shot Temporal Action Detection
A novel Decoupled Single Shot temporal Action Detection (Decouple-SSAD) method to mitigate such problem by decoupling the localization and classification in a one-stage scheme and demonstrates superior performance over state-of-the-art methods. Expand
CDC: Convolutional-De-Convolutional Networks for Precise Temporal Action Localization in Untrimmed Videos
A novel Convolutional-De-Convolutional (CDC) network that places CDC filters on top of 3D ConvNets, which have been shown to be effective for abstracting action semantics but reduce the temporal length of the input data. Expand
Multi-Granularity Generator for Temporal Action Proposal
Through temporally adjusting the segment proposals with fine-grained information based on frame actionness, MGG achieves the superior performance over state-of-the-art methods on the public THUMOS-14 and ActivityNet-1.3 datasets. Expand
Graph Convolutional Networks for Temporal Action Localization
This paper builds an action proposal graph, where each proposal is represented as a node and their relations between two proposals as an edge and applies the GCNs over the graph to model the relations among different proposals and learn powerful representations for the action classification and localization. Expand
Temporal Action Detection with Structured Segment Networks
The structured segment network (SSN) is presented, a novel framework which models the temporal structure of each action instance via a structured temporal pyramid and introduces a decomposed discriminative model comprising two classifiers, respectively for classifying actions and determining completeness. Expand
BSN: Boundary Sensitive Network for Temporal Action Proposal Generation
An effective proposal generation method, named Boundary-Sensitive Network (BSN), which adopts "local to global" fashion and significantly improves the state-of-the-art temporal action detection performance. Expand