Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

No-Frills Human-Object Interaction Detection: Factorization, Layout Encodings, and Training Techniques

About

We show that for human-object interaction detection a relatively simple factorized model with appearance and layout encodings constructed from pre-trained object detectors outperforms more sophisticated approaches. Our model includes factors for detection scores, human and object appearance, and coarse (box-pair configuration) and optionally fine-grained layout (human pose). We also develop training techniques that improve learning efficiency by: (1) eliminating a train-inference mismatch; (2) rejecting easy negatives during mini-batch training; and (3) using a ratio of negatives to positives that is two orders of magnitude larger than existing approaches. We conduct a thorough ablation study to understand the importance of different factors and training techniques using the challenging HICO-Det dataset.

Tanmay Gupta, Alexander Schwing, Derek Hoiem• 2018

Related benchmarks

TaskDatasetResultRank
Human-Object Interaction DetectionHICO-DET (test)
mAP (full)20.41
493
Human-Object Interaction DetectionV-COCO (test)
AP (Role, Scenario 1)53.1
270
Human-Object Interaction DetectionHICO-DET
mAP (Full)17.18
233
HOI DetectionHICO-DET (test)
Box mAP (Full)17.18
32
Human-Object Interaction DetectionV-COCO
AP (Role)31.8
23
Human-Object Interaction DetectionHICO-DET 9 (test)
mAP (Full)17.18
21
Human-Object Interaction DetectionHOI-VP
mAP61.05
11
Showing 7 of 7 rows

Other info

Follow for update