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

Object pose estimation is a long-standing problem in computer vision.Recently, attention-based vision transformer models have achievedstate-of-the-art results in many computer vision applications. Exploiting thepermutation-invariant nature of the attention mechanism, a family of visiontransformer models formulate multi-object pose estimation as a set predictionproblem. However, existing vision transformer models for multi-object poseestimation rely exclusively on the attention mechanism. Convolutional neuralnetworks, on the other hand, hard-wire various inductive biases into theirarchitecture. In this paper, we investigate incorporating inductive biases invision transformer models for multi-object pose estimation, which facilitateslearning long-range dependencies while circumventing the costly globalattention. In particular, we use multi-resolution deformable attention, wherethe attention operation is performed only between a few deformed referencepoints. Furthermore, we propose a query aggregation mechanism that enablesincreasing the number of object queries without increasing the computationalcomplexity. We evaluate the proposed model on the challenging YCB-Video datasetand report state-of-the-art results.

Efficient Multi-Object Pose Estimation using Multi-Resolution Deformable Attention and Query Aggregation