AI Paper Atlas

Research map / 3D vision / 3D generation

Scene-Centric Joint Parsing of Cross-View Videos

Hang Qi, Yuanlu Xu, Tao Yuan, Tianfu Wu, Song-Chun Zhu

AAAI 2018 · 3D vision › 3D generation · approach: Semantic scene completion · 14 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Jointly parse cross-view proposals into scene-centric predictionsView-centric action proposals · CAMPUSOverall action accuracy: 0.82 -> 0.90Improved
Jointly parse cross-view proposals into scene-centric predictionsView-centric action proposals · TUM KitchenOverall action accuracy: 0.59 -> 0.70Improved
Jointly parse cross-view proposals into scene-centric predictionsView-centric attribute proposals · CAMPUSmAP: 0.59 -> 0.63Improved
Jointly parse cross-view proposals into scene-centric predictionsView-centric attribute proposals · TUM KitchenmAP: 0.76 -> 0.84Improved
Use joint parsing rather than Xu et al.Multi-object detection · CAMPUS-S1DA (%): 49.30 -> 56.00Improved
Use joint parsing rather than Xu et al.Multi-object detection · CAMPUS-S2DA (%): 27.81 -> 28.24Improved
Use joint parsing rather than Xu et al.Multi-object detection · CAMPUS-S3DA (%): 49.71 -> 50.60Improved
Use joint parsing rather than Xu et al.Multi-object detection · CAMPUS-S4DA (%): 24.46 -> 24.81Improved
Use joint parsing rather than Xu et al.Multi-object detection · TUM KitchenDA (%): 86.53 -> 89.13Improved
Use joint parsing to aggregate observations across camerasMulti-object tracking · CAMPUS-S1TA (%): 56.15 -> 55.95No clear effect
Use joint parsing to aggregate observations across camerasMulti-object tracking · CAMPUS-S2TA (%): 28.74 -> 27.91Hurt
Use joint parsing to aggregate observations across camerasMulti-object tracking · CAMPUS-S3TA (%): 49.68 -> 50.55Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy