.png){kind=icon}
Return
Query-guided feature mining for weakly supervised object detection
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neucom.2026.133698.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• QGFM proposes dynamic queries to actively mine object semantics for effective WSOD. • CQC module alleviates the semantic confusion, such that detections are semantically consistent with target labels. • Extensive evaluations on the PASCAL VOC and MS COCO benchmarks show the effectiveness of QGFM.
Keywords:
Query-guided feature mining
Weakly supervised object detection
Dynamic queries
Semantic consistency
Object semantics
Journal
IF:
6.5
Papers:
2.5W
Citations:
6.5W
Organization
Cited Papers
.png){kind=icon}
ShareSave
ShareSaveShareSave
View more