AI Paper Atlas

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

Iwin: Human-Object Interaction Detection via Transformer with Irregular Windows

Danyang Tu, Xiongkuo Min, Huiyu Duan, Guodong Guo, Guangtao Zhai, Wei Shen

ECCV 2022 · Detection and segmentation › Open-set and few-shot detection · approach: Human-object interaction detection · 28 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 FPN high-resolution features (ablation)Iwin-B · HICO-DET (Default) FullmAP: 31.24 -> 32.03Improved
add irregular window partition (ablation)Iwin-B · HICO-DET (Default) FullmAP: 29.12 -> 32.03Improved
add multi-scale windows (ablation)Iwin-B · HICO-DET (Default) FullmAP: 31.42 -> 32.03Improved
add both irregular window partition and multi-scale windows (ablation)Iwin-B · HICO-DET (Default) FullmAP: 26.33 -> 32.03Improved
add token agglomeration (ablation)Iwin-B · HICO-DET (Default) FullmAP: 30.16 -> 32.03Improved
add global contextual modeling (ablation)Iwin-B · HICO-DET (Default) FullmAP: 23.05 -> 32.03Improved
use irregular-window agglomeration instead of regular 2x2 windows (ablation)Iwin-B · HICO-DET (Default) FullmAP: 27.50 -> 32.03Improved
use irregular-window agglomeration instead of k-means clustering (ablation)Iwin-B · HICO-DET (Default) FullmAP: 28.19 -> 32.03Improved
use sinusoidal position encoding at attention instead of none (ablation)Iwin-B · HICO-DET (Default) FullmAP: 20.80 -> 32.03Improved
use sine rather than learned position encoding at attention (ablation)Iwin-B · HICO-DET (Default) FullmAP: 31.64 -> 32.03Improved
apply position encoding at attention only rather than for all (including convolution) (ablation)Iwin-B · HICO-DET (Default) FullmAP: 28.59 -> 32.03Improved
use 6 Transformer decoder layers instead of 2 (ablation)Iwin-B · HICO-DET (Default) FullmAP: 27.31 -> 32.03Improved

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