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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Dynamics prediction, which is the problem of predicting future states ofscene objects based on current and prior states, is drawing increasingattention as an instance of learning physics. To solve this problem, RegionProposal Convolutional Interaction Network (RPCIN), a vision-based model, wasproposed and achieved state-of-the-art performance in long-term prediction.RPCIN only takes raw images and simple object descriptions, such as thebounding box and segmentation mask of each object, as input. However, despiteits success, the model's capability can be compromised under conditions ofenvironment misalignment. In this paper, we investigate two challengingconditions for environment misalignment: Cross-Domain and Cross-Context byproposing four datasets that are designed for these challenges: SimB-Border,SimB-Split, BlenB-Border, and BlenB-Split. The datasets cover two domains andtwo contexts. Using RPCIN as a probe, experiments conducted on the combinationsof the proposed datasets reveal potential weaknesses of the vision-basedlong-term dynamics prediction model. Furthermore, we propose a promisingdirection to mitigate the Cross-Domain challenge and provide concrete evidencesupporting such a direction, which provides dramatic alleviation of thechallenge on the proposed datasets.

A Critical View of Vision-Based Long-Term Dynamics Prediction Under Environment Misalignment