AI Paper Atlas

Research map / Detection and segmentation / 3D detection and driving

Vote2Cap-DETR++: Decoupling Localization and Describing for End-to-End 3D Dense Captioning

Sijin Chen, Hongyuan Zhu, Mingsheng Li, Xin Chen, Peng Guo, Yinjie Lei, Gang Yu, Taihao Li, Tao Chen

TPAMI 2024 · Detection and segmentation › 3D detection and driving · approach: 3D objectness and scene segmentation · 37 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
add vote query position p_vq as query position (ablation)3DETR-m · ScanNet valmAP@0.5: +0.97% mAP@0.5Improved
add aggregated local feature f_vq as initial query feature (ablation)Vote2Cap-DETR · ScanNet valmAP@0.5: +2.98% mAP@0.5Improved
add local context tokens (DCC) in caption head (ablation)object-centric decoder · ScanRefer val (frozen backbone)C@0.5: 60.15 -> 61.39Improved
use set-to-set training instead of sentence training under SCST (ablation)Vote2Cap-DETR · ScanRefer valC@0.5: 71.39 -> 73.77Improved
use set-to-set training under MLE (ablation)Vote2Cap-DETR · ScanRefer valC@0.5: 61.21 -> 61.81No clear effect
add detection pretraining before end-to-end training (ablation)Vote2Cap-DETR · ScanRefer valC@0.5: 52.15 -> 62.03Improved
remove NMS at inference (ablation)Vote2Cap-DETR · ScanRefer valC@0.5: 70.63 -> 71.57No clear effect
remove NMS at inference (ablation)SpaCap3D · ScanRefer valmAP50: 37.77 -> 23.30Hurt
refine vote queries spatially in first three decoder layers (ablation)Vote2Cap-DETR · ScanNet valmAP@0.5: 52.13 -> 55.48Improved
refine vote queries in all decoder layers instead of first three (ablation)Vote2Cap-DETR++ · ScanNet valmAP@0.5: 55.48 -> 54.55Hurt
decouple loc and caption queries without correspondence (ablation)Vote2Cap-DETR · ScanRefer valC@0.5: 66.01 -> 65.38Hurt
link caption queries with loc queries through token-wise projection (ablation)decoupled queries · ScanRefer valC@0.5: 65.38 -> 67.58Improved

Later papers that compared with this method

1 later accepted paper reports Vote2Cap-DETR as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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