English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Generating human action proposals in untrimmed videos is an important yetchallenging task with wide applications. Current methods often suffer from thenoisy boundary locations and the inferior quality of confidence scores used forproposal retrieving. In this paper, we present BSN++, a new framework whichexploits complementary boundary regressor and relation modeling for temporalproposal generation. First, we propose a novel boundary regressor based on thecomplementary characteristics of both starting and ending boundary classifiers.Specifically, we utilize the U-shaped architecture with nested skip connectionsto capture rich contexts and introduce bi-directional boundary matchingmechanism to improve boundary precision. Second, to account for theproposal-proposal relations ignored in previous methods, we devise a proposalrelation block to which includes two self-attention modules from the aspects ofposition and channel. Furthermore, we find that there inevitably exists dataimbalanced problems in the positive/negative proposals and temporal durations,which harm the model performance on tail distributions. To relieve this issue,we introduce the scale-balanced re-sampling strategy. Extensive experiments areconducted on two popular benchmarks: ActivityNet-1.3 and THUMOS14, whichdemonstrate that BSN++ achieves the state-of-the-art performance. Notsurprisingly, the proposed BSN++ ranked 1st place in the CVPR19 - ActivityNetchallenge leaderboard on temporal action localization task.

BSN++: Complementary Boundary Regressor with Scale-Balanced Relation Modeling for Temporal Action Proposal Generation