• Publications
  • Influence
Mining actionlet ensemble for action recognition with depth cameras
Human action recognition is an important yet challenging task. The recently developed commodity depth sensors open up new possibilities of dealing with this problem but also present some uniqueExpand
  • 1,183
  • 205
A unified approach to salient object detection via low rank matrix recovery
  • X. Shen, Y. Wu
  • Computer Science
  • IEEE Conference on Computer Vision and Pattern…
  • 16 June 2012
Salient object detection is not a pure low-level, bottom-up process. Higher-level knowledge is important even for task-independent image saliency. We propose a unified model to incorporateExpand
  • 641
  • 92
Learning Fine-Grained Image Similarity with Deep Ranking
  • J. Wang, Yang Song, +5 authors Y. Wu
  • Computer Science
  • IEEE Conference on Computer Vision and Pattern…
  • 17 April 2014
Learning fine-grained image similarity is a challenging task. It needs to capture between-class and within-class image differences. This paper proposes a deep ranking model that employs deep learningExpand
  • 771
  • 61
Robust 3D Action Recognition with Random Occupancy Patterns
We study the problem of action recognition from depth sequences captured by depth cameras, where noise and occlusion are common problems because they are captured with a single commodity camera. InExpand
  • 450
  • 56
Cross-View Action Modeling, Learning, and Recognition
Existing methods on video-based action recognition are generally view-dependent, i.e., performing recognition from the same views seen in the training data. We present a novel multiviewExpand
  • 201
  • 45
Modeling the constraints of human hand motion
Hand motion capture is one of the most important parts of gesture interfaces. Many current approaches to this task generally involve a formidable nonlinear optimization problem in a large searchExpand
  • 304
  • 31
Discriminative subvolume search for efficient action detection
Actions are spatio-temporal patterns which can be characterized by collections of spatio-temporal invariant features. Detection of actions is to find the re-occurrences (e.g. through patternExpand
  • 243
  • 26
Discriminative Video Pattern Search for Efficient Action Detection
Actions are spatiotemporal patterns. Similar to the sliding window-based object detection, action detection finds the reoccurrences of such spatiotemporal patterns through pattern matching, byExpand
  • 168
  • 24
BIK1 interacts with PEPRs to mediate ethylene-induced immunity
Plants have evolved intricate immune mechanisms to combat pathogen infection. Upon perception of pathogen-derived signals, plants accumulate defense hormones such as ethylene (ET), jasmonate,Expand
  • 175
  • 22
Object retrieval and localization with spatially-constrained similarity measure and k-NN re-ranking
One fundamental problem in object retrieval with the bag-of-visual words (BoW) model is its lack of spatial information. Although various approaches are proposed to incorporate spatial constraintsExpand
  • 186
  • 21