SegFix: Model-Agnostic Boundary Refinement for Segmentation

Computer Vision – ECCV 2020 - Lecture Notes in Computer Science ◽

10.1007/978-3-030-58610-2_29 ◽

2020 ◽

pp. 489-506 ◽

Cited By ~ 2

Author(s):

Yuhui Yuan ◽

Jingyi Xie ◽

Xilin Chen ◽

Jingdong Wang

Keyword(s):

Boundary Refinement

Download Full-text

Robust interactive image segmentation with automatic boundary refinement

2010 IEEE International Conference on Image Processing ◽

10.1109/icip.2010.5652012 ◽

2010 ◽

Cited By ~ 5

Author(s):

Dingding Liu ◽

Yingen Xiong ◽

Linda Shapiro ◽

Kari Pulli

Keyword(s):

Image Segmentation ◽

Interactive Image Segmentation ◽

Boundary Refinement

Download Full-text

Critical Boundary Refinement in a Group Sequential Trial When the Primary Endpoint Data Accumulate Faster Than the Secondary Endpoint

Contemporary Biostatistics with Biopharmaceutical Applications - ICSA Book Series in Statistics ◽

10.1007/978-3-030-15310-6_11 ◽

2019 ◽

pp. 205-224

Author(s):

Jiangtao Gou ◽

Oliver Y. Chén

Keyword(s):

Primary Endpoint ◽

Secondary Endpoint ◽

Group Sequential ◽

Sequential Trial ◽

Critical Boundary ◽

Endpoint Data ◽

Boundary Refinement

Download Full-text

Progressive Boundary Refinement Network for Temporal Action Detection

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v34i07.6829 ◽

2020 ◽

Vol 34 (07) ◽

pp. 11612-11619

Author(s):

Qinying Liu ◽

Zilei Wang

Keyword(s):

State Of The Art ◽

The State ◽

Action Detection ◽

Fine Grained ◽

The Third ◽

One Stage ◽

The Family ◽

Main Components ◽

Temporal Action ◽

Boundary Refinement

Temporal action detection is a challenging task due to vagueness of action boundaries. To tackle this issue, we propose an end-to-end progressive boundary refinement network (PBRNet) in this paper. PBRNet belongs to the family of one-stage detectors and is equipped with three cascaded detection modules for localizing action boundary more and more precisely. Specifically, PBRNet mainly consists of coarse pyramidal detection, refined pyramidal detection, and fine-grained detection. The first two modules build two feature pyramids to perform the anchor-based detection, and the third one explores the frame-level features to refine the boundaries of each action instance. In the fined-grained detection module, three frame-level classification branches are proposed to augment the frame-level features and update the confidence scores of action instances. Evidently, PBRNet integrates the anchor-based and frame-level methods. We experimentally evaluate the proposed PBRNet and comprehensively investigate the effect of the main components. The results show PBRNet achieves the state-of-the-art detection performances on two popular benchmarks: THUMOS'14 and ActivityNet, and meanwhile possesses a high inference speed.

Download Full-text