Hongliang Li

Latest

• A Survey of Vision and Language Related Multi-modal Task
• CrossDet++: Growing Crossline Representation for Object Detection
• Real-time panoptic segmentation with relationship between adjacent pixels and boundary prediction
• What Happens in Crowd Scenes: A New Dataset about Crowd Scenes for Image Captioning
• What Happens in Crowd Scenes: A New Dataset about Crowd Scenes for Image Captioning
• RefCrowd: Grounding the Target in Crowd with Referring Expressions
• RefCrowd: Grounding the Target in Crowd with Referring Expressions
• POS-trends Dynamic-Aware Model for Video Caption
• CrossDet: Crossline Representation for Object Detection
• Multi-stage Tag Guidance Network in Video Caption