Name
Abstract | ||
|---|---|---|
We consider detecting objects in an image by iteratively selecting from a set of arbitrarily shaped candidate regions. Our generic approach, which we term visual chunking, reasons about the locations of multiple object instances in an image while expressively describing object boundaries. We design an optimization criterion for measuring the performance of a list of such detections as a natural extension to a common per-instance metric. We present an efficient algorithm with provable performance for building a high-quality list of detections from any candidate set of region-based proposals. We also develop a simple class-specific algorithm to generate a candidate region instance in near-linear time in the number of low-level superpixels that outperforms other region generating methods. In order to make predictions on novel images at testing time without access to ground truth, we develop learning approaches to emulate these algorithms' behaviors. We demonstrate that our new approach outperforms sophisticated baselines on benchmark datasets. |
Year | DOI | Venue |
|---|---|---|
2014 | 10.1109/ICRA.2015.7139960 | IEEE International Conference on Robotics and Automation |
Keywords | Field | DocType |
object detection,optimisation,list prediction framework,object boundaries,optimization,per-instance metric,region-based object detection,shaped candidate regions,visual chunking | Object detection,Data mining,Pattern recognition,Computer science,Image segmentation,Greedy algorithm,Prediction algorithms,Ground truth,Chunking (psychology),Artificial intelligence,Semantics | Journal |
Volume | Issue | ISSN |
abs/1410.7376 | 1 | 1050-4729 |
Citations | PageRank | References |
1 | 0.37 | 40 |
Authors | ||
4 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Nicholas Rhinehart | 1 | 28 | 4.87 |
| Jiaji Zhou | 2 | 45 | 4.90 |
| Martial Hebert | 3 | 11277 | 1146.89 |
| J. Andrew Bagnell | 4 | 3919 | 217.49 |