• Publications
  • Influence
The Secrets of Salient Object Segmentation
An extensive evaluation of fixation prediction and salient object segmentation algorithms as well as statistics of major datasets identifies serious design flaws of existing salient object benchmarks and proposes a new high quality dataset that offers both fixation and salient objects segmentation ground-truth. Expand
Statistical color models with application to skin detection
This work describes the construction of color models for skin and non-skin classes from a dataset of nearly 1 billion labeled pixels and believes this work is the most comprehensive and detailed exploration of skin color models to date. Expand
Video Segmentation by Tracking Many Figure-Ground Segments
An unsupervised video segmentation approach by simultaneously tracking multiple holistic figure-ground segments that outperforms state-of-the-art approaches in the dataset, showing its efficiency and robustness to challenges in different video sequences. Expand
CENTRIST: A Visual Descriptor for Scene Categorization
  • Jianxin Wu, James M. Rehg
  • Computer Science, Medicine
  • IEEE Transactions on Pattern Analysis and Machine…
  • 1 August 2011
CENsus TRansform hISTogram (CENTRIST), a new visual descriptor for recognizing topological places or scene categories, is introduced and is shown to be a holistic representation and has strong generalizability for category recognition. Expand
Learning to recognize objects in egocentric activities
The key to this approach is a robust, unsupervised bottom up segmentation method, which exploits the structure of the egocentric domain to partition each frame into hand, object, and background categories and uses Multiple Instance Learning to match object instances across sequences. Expand
Multiple Hypothesis Tracking Revisited
It is demonstrated that a classical MHT implementation from the 90's can come surprisingly close to the performance of state-of-the-art methods on standard benchmark datasets, and it is shown that appearance models can be learned efficiently via a regularized least squares framework. Expand
Statistical Color Models with Application to Skin Detection
This work describes the construction of color models for skin and non-skin classes from a dataset of nearly 1 billion labelled pixels and suggests that color can be a more powerful cue for detecting people in unconstrained imagery than was previously suspected. Expand
Motion Coherent Tracking with Multi-label MRF optimization
This work proposes a novel energy formulation which incorporates both segmentation and motion estimation in a single framework, and utilizes state-of-the-art methods to efficiently optimize over a large number of discrete labels. Expand
Learning to Recognize Daily Actions Using Gaze
An inference method is presented that can predict the best sequence of gaze locations and the associated action label from an input sequence of images and demonstrates improvements in action recognition rates and gaze prediction accuracy relative to state-of-the-art methods. Expand
Fine-Grained Head Pose Estimation Without Keypoints
An elegant and robust way to determine pose is presented by training a multi-loss convolutional neural network on 300W-LP, a large synthetically expanded dataset, to predict intrinsic Euler angles directly from image intensities through joint binned pose classification and regression. Expand