Name
Abstract | ||
|---|---|---|
Human-Object Interaction (HOI) detection plays a crucial role in activity understanding. Though significant progress has been made, interactiveness learning remains a challenging problem in HOI detection: existing methods usually generate redundant negative H-O pair proposals and fail to effectively extract interactive pairs. Though interactiveness has been studied in both whole body- and part- level and facilitates the H-O pairing, previous works only focus on the target person once (i.e., in a local perspective) and overlook the information of the other persons. In this paper, we argue that comparing body-parts of multi-person simultaneously can afford us more useful and supplementary interactiveness cues. That said, to learn body-part interactiveness from a global perspective: when classifying a target person’s body-part interactiveness, visual cues are explored not only from herself/himself but also from other persons in the image. We construct body-part saliency maps based on self-attention to mine cross-person informative cues and learn the holistic relationships between all the body-parts. We evaluate the proposed method on widely-used benchmarks HICO-DET and V-COCO. With our new perspective, the holistic global-local body-part interactiveness learning achieves significant improvements over state-of-the-art. Our code is available at https://github.com/enlighten0707/Body-Part-Map-for-Interactiveness. |
Year | DOI | Venue |
|---|---|---|
2022 | 10.1007/978-3-031-19772-7_8 | European Conference on Computer Vision |
Keywords | DocType | Citations |
Human-object interaction,Interactiveness learning,Body-part correlations | Conference | 0 |
PageRank | References | Authors |
0.34 | 0 | 6 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Xiaoqian Wu | 1 | 1 | 3.15 |
| Yonglu Li | 2 | 22 | 7.05 |
| Xinpeng Liu | 3 | 0 | 1.35 |
| Junyi Zhang | 4 | 0 | 0.34 |
| Yuzhe Wu | 5 | 0 | 0.34 |
| Cewu Lu | 6 | 993 | 62.08 |