• Publications
  • Influence
The Role of Context for Object Detection and Semantic Segmentation in the Wild
A novel deformable part-based model is proposed, which exploits both local context around each candidate detection as well as global context at the level of the scene, which significantly helps in detecting objects at all scales. Expand
Detect What You Can: Detecting and Representing Objects Using Holistic Models and Body Parts
This work proposes a novel approach to handle large deformations and partial occlusions in animals in terms of body parts, and applies it to the six animal categories in the PASCAL VOC dataset and shows that it significantly improves state-of-the-art (by 4.1% AP) and provides a richer representation for objects. Expand
Articulated Pose Estimation by a Graphical Model with Image Dependent Pairwise Relations
This work specifies a graphical model for human pose which exploits the fact the local image measurements can be used both to detect parts (or joints) and also to predict the spatial relationships between them (Image Dependent Pairwise Relations). Expand
Joint Multi-person Pose Estimation and Semantic Part Segmentation
This paper proposes to solve the two tasks jointly for natural multi-person images, in which the estimated pose provides object-level shape prior to regularize part segments while the part-level segments constrain the variation of pose locations. Expand
Parsing occluded people by flexible compositions
  • X. Chen, A. Yuille
  • Computer Science
  • IEEE Conference on Computer Vision and Pattern…
  • 3 December 2014
This paper model humans using a graphical model which has a tree structure building on recent work and exploits the connectivity prior that, even in presence of occlusion, the visible nodes form a connected subtree of the graphical model to exploit part sharing. Expand
DeePM: A Deep Part-Based Model for Object Detection and Semantic Part Localization
This paper annotates semantic parts for all 20 object categories on the PASCAL VOC 2012 dataset, which provides information on object pose, occlusion, viewpoint and functionality and presents an end-to-end Object-Part R-CNN which learns an implicit feature representation for jointly mapping an image ROI to the object and part bounding boxes. Expand
Three-dimensional photocatalysts with a network structure
Three-dimensional (3D) photocatalysts with a network structure are presently attracting enormous research interests due to their excellent properties, such as a high specific surface area, highExpand
Separation-free TiO 2 -graphene hydrogel with 3D network structure for efficient photoelectrocatalytic mineralization
Herein, TiO2-graphene hydrogel (TGH) electrodes with 3D network structure were designed and fabricated successfully via the one-pot method and the photoelectrocatalytic mineralization ability overExpand
Co2 +-exchanged SAPO-5 and SAPO-34 as efficient heterogeneous catalysts for aerobic epoxidation of alkenes
Abstract Co-SAPO-5 and Co-SAPO-34 were prepared by a simple ion-exchange route and firstly applied in the aerobic epoxidation of alkenes. Both catalysts exhibited high activities in the epoxidationExpand
Hierarchical Real-Time Filtering for Continuous Glucose Sensor Data