Papers › Spatially Conditioned Graphs for Detecting Human-Object Interactions

Spatially Conditioned Graphs for Detecting Human-Object Interactions

11 Dec 2020ICCV 2021 10arXiv:2012.06060archive 2025-07-28

Frederic Z. Zhang, Dylan Campbell, Stephen Gould

We address the problem of detecting human-object interactions in images using graphical neural networks. Unlike conventional methods, where nodes send scaled but otherwise identical messages to each of their neighbours, we propose to condition messages between pairs of nodes on their spatial relationships, resulting in different messages going to neighbours of the same node. To this end, we explore various ways of applying spatial conditioning under a multi-branch structure. Through extensive experimentation we demonstrate the advantages of spatial conditioning for the computation of the adjacency structure, messages and the refined graph features. In particular, we empirically show that as the quality of the bounding boxes increases, their coarse appearance features contribute relatively less to the disambiguation of interactions compared to the spatial information. Our method achieves an mAP of 31.33% on HICO-DET and 54.2% on V-COCO, significantly outperforming state-of-the-art on fine-tuned detections.

PaperPDFConference PDFCode

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

fredzzhang/spatially-conditioned-graphs officialmentioned in papermentioned on GitHubpytorch report
fredzzhang/hicodet officialpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Human-Object Interaction DetectionObject

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Human-Object Interaction Detection HICO-DET SCG (DETR-R101) mAP 29.26 #29 of 55 Archive leaderboard report
Human-Object Interaction Detection V-COCO SCG AP(S1) 54.2 #18 of 34 Archive leaderboard report
Human-Object Interaction Detection V-COCO SCG AP(S2) 60.9 #18 of 34 Archive leaderboard report
Human-Object Interaction Detection V-COCO SCG Time Per Frame(ms) 500 #18 of 34 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections