AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Hierarchy Parsing for Image Captioning

Ting Yao, Yingwei Pan, Yehao Li, Tao Mei

ICCV 2019 · Detection and segmentation › Open-set and few-shot detection · approach: Interactive and referring segmentation · 220 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 hierarchy parsing (HIP) featuresUp-Down · COCO Karpathy test (cross-entropy)CIDEr-D: 113.5 -> 116.6Improved
add hierarchy parsing (HIP) featuresGCN-LSTM · COCO Karpathy test (cross-entropy)CIDEr-D: 117.1 -> 120.3Improved
add HIP featuresUp-Down · COCO Karpathy test (CIDEr-D optimization)CIDEr-D: 120.1 -> 127.2Improved
add HIP featuresGCN-LSTM · COCO Karpathy test (CIDEr-D optimization)CIDEr-D: 128.7 -> 130.6Improved
add Tree-LSTM-enhanced features to region features (ablation)Up-Down · COCO Karpathy test (cross-entropy, Up-Down decoder)CIDEr-D: 113.5 -> 115.5Improved
add instance-level features to region features (ablation)Up-Down · COCO Karpathy test (cross-entropy, Up-Down decoder)CIDEr-D: 113.5 -> 114.9Improved
add region features to instance and Tree-LSTM features (full HIP) (ablation)Up-Down · COCO Karpathy test (cross-entropy, Up-Down decoder)CIDEr-D: 115.2 -> 116.6Improved
use instance-level features alone instead of region features (ablation)Up-Down · COCO Karpathy test (cross-entropy, Up-Down decoder)CIDEr-D: 113.5 -> 113.3Hurt
use HIP image-level features for recognitionUp-Down features · COCO multi-label recognitionC-F1: 63.74 -> 65.74Improved
use HIP image-level features for recognitionUp-Down features · COCO multi-label recognitionO-F1: 65.41 -> 68.61Improved
add HIP to GCN-LSTMGCN-LSTM · COCO online test server (c5)CIDEr-D: 125.3 -> 127.9Improved
add HIP to GCN-LSTMGCN-LSTM · Human evaluation (1K COCO test images)M1: 73.9% -> 76.5%Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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