AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

SeqTR: A Simple Yet Universal Network for Visual Grounding

Chaoyang Zhu, Yiyi Zhou, Yunhang Shen, Gen Luo, Xingjia Pan, Mingbao Lin, Chao Chen, Liujuan Cao, Xiaoshuai Sun, Rongrong Ji

ECCV 2022 · Vision-language and multimodal › Human and embodied modeling · approach: Visual grounding transformers · 178 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 max pooling of word features instead of mean pooling (ablation)SeqTR · RefCOCO valPrec@0.5 (%): 79.73 -> 80.07Improved
use max pooling instead of final bi-GRU hidden state (ablation)SeqTR · RefCOCO+ valPrec@0.5 (%): 67.46 -> 68.31Improved
raise 1st token weight to 1.5 (ablation)SeqTR · RefCOCO+ valPrec@0.5 (%): 68.31 -> 68.63Improved
raise first token weight to 3 (ablation)SeqTR · RefCOCO+ valPrec@0.5 (%): 68.31 -> 67.81Hurt
raise 2nd and 3rd token weights to 2 (ablation)SeqTR · RefCOCOg val-uPrec@0.5 (%): 69.95 -> 69.51Hurt
add multi-task REC+RES supervision (ablation)SeqTR · RefCOCO valRES mIoU (%): 64.20 -> 62.93Hurt
add multi-task REC+RES supervision (ablation)SeqTR · RefCOCO+ valRES mIoU (%): 52.22 -> 53.65Improved
add multi-task REC+RES supervision (ablation)SeqTR · RefCOCOg val-uRES mIoU (%): 53.25 -> 53.25No clear effect
use uniform instead of center-based mask contour sampling (ablation)SeqTR · RES upper boundmIoU upper bound: 91.58 -> 95.57Improved
add large-scale pre-trainingSeqTR · RefCOCO val (RES)mIoU (%): 67.26 -> 71.70Improved
add large-scale pre-trainingSeqTR · RefCOCO+ val (RES)mIoU (%): 54.14 -> 63.04Improved
sample with nucleus top-p 0.6 instead of argmax (ablation)SeqTR · RefCOCO val (RES)mIoU (%): 67.26 -> 66.15Hurt

Later papers that compared with this method

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

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

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