AI Paper Atlas

Research map / Detection and segmentation / CNN features

End-to-End 3D Dense Captioning With Vote2Cap-DETR

Sijin Chen, Hongyuan Zhu, Xin Chen, Yinjie Lei, Gang Yu, Tao Chen

CVPR 2023 · Detection and segmentation › CNN features · approach: Efficient DETR query design · 52 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
Use one-stage Vote2Cap-DETR instead of the strongest listed two-stage baseline3D dense captioning · ScanRefer val, IoU=0.50, SCST, w/ additional 2DCIDEr: 62.64 -> 70.63Improved
Use one-stage Vote2Cap-DETR instead of the strongest listed baseline3D dense captioning · Nr3D, IoU=0.50, SCSTCIDEr: 38.42 -> 45.53Improved
Add vote query positions instead of using seed positions (ablation)3DETR object detection · ScanNet detection, IoU=0.50mAP: 48.18 -> 49.15Improved
Add gathered content features to the vote query (ablation)Vote-position 3DETR query · ScanNet detection, IoU=0.50mAP: 49.15 -> 52.13Improved
Add gathered content features to the vote query (ablation)Vote-position 3DETR query · ScanNet detection, first decoder layer, IoU=0.50mAP: 30.23 -> 46.53Improved
Add local contextual features to the caption decoder (ablation)Object-centric caption decoder · ScanRefer, IoU=0.50, MLECIDEr: 60.15 -> 61.39Improved
Use local rather than global scene context tokens (ablation)Caption decoder with contextual features · ScanRefer, IoU=0.50, MLECIDEr: 61.20 -> 61.39Improved
Use set-to-set training instead of sentence training (ablation)Vote2Cap-DETR · ScanRefer, IoU=0.50, SCSTCIDEr: 71.39 -> 73.77Improved
Use set-to-set training instead of sentence training (ablation)Vote2Cap-DETR · ScanRefer, IoU=0.50, MLECIDEr: 61.21 -> 61.81Improved
Remove NMS (ablation)Vote2Cap-DETR · IoU=0.50CIDEr: 70.63 -> 71.57Improved
Remove NMS (ablation)Vote2Cap-DETR · IoU=0.50mAP50: 52.79 -> 52.82No clear effect
Replace the scene encoder, vote query, and transformer decoder with VoteNet (ablation)Vote2Cap-DETR · ScanRefer, IoU=0.50, MLECIDEr: 59.32 -> 52.96Hurt

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