8 Result(s)
-
Chapter and Conference Paper
Image Inpainting with Cascaded Modulation GAN and Object-Aware Training
Recent image inpainting methods have made great progress but often struggle to generate plausible image structures when dealing with large holes in complex images. This is partially due to the lack of effectiv...
-
Chapter and Conference Paper
Improving Closed and Open-Vocabulary Attribute Prediction Using Transformers
We study recognizing attributes for objects in visual scenes. We consider attributes to be any phrases that describe an object’s physical and semantic properties, and its relationships with other objects. Exis...
-
Chapter and Conference Paper
GALA: Toward Geometry-and-Lighting-Aware Object Search for Compositing
Compositing-aware object search aims to find the most compatible objects for compositing given a background image and a query bounding box. Previous works focus on learning compatibility between the foreground...
-
Chapter and Conference Paper
PhraseClick: Toward Achieving Flexible Interactive Segmentation by Phrase and Click
Existing interactive object segmentation methods mainly take spatial interactions such as bounding boxes or clicks as input. However, these interactions do not contain information about explicit attributes of ...
-
Chapter and Conference Paper
YouTube-VOS: Sequence-to-Sequence Video Object Segmentation
Learning long-term spatial-temporal features are critical for many video analysis tasks. However, existing video segmentation methods predominantly rely on static image segmentation techniques, and methods cap...
-
Chapter and Conference Paper
Interactive Boundary Prediction for Object Selection
Interactive image segmentation is critical for many image editing tasks. While recent advanced methods on interactive segmentation focus on the region-based paradigm, more traditional boundary-based methods su...
-
Chapter and Conference Paper
Start, Follow, Read: End-to-End Full-Page Handwriting Recognition
Despite decades of research, offline handwriting recognition (HWR) of degraded historical documents remains a challenging problem, which if solved could greatly improve the searchability of online cultural her...
-
Chapter and Conference Paper
Concept Mask: Large-Scale Segmentation from Semantic Concepts
Existing works on semantic segmentation typically consider a small number of labels, ranging from tens to a few hundreds. With a large number of labels, training and evaluation of such task become extremely ch...
