* Submitted to CVPR 2017 (10 pages, 5 figures)

**Click to Read Paper**

Symmetric Non-Rigid Structure from Motion for Category-Specific Object Structure Estimation

Sep 22, 2016

Yuan Gao, Alan Yuille

Sep 22, 2016

Yuan Gao, Alan Yuille

* Accepted to ECCV 2016

**Click to Read Paper**

**Click to Read Paper**

* Accepted to ECCV 2016

**Click to Read Paper**

This paper presents an approach to parsing humans when there is significant occlusion. We model humans using a graphical model which has a tree structure building on recent work [32, 6] and exploit the connectivity prior that, even in presence of occlusion, the visible nodes form a connected subtree of the graphical model. We call each connected subtree a flexible composition of object parts. This involves a novel method for learning occlusion cues. During inference we need to search over a mixture of different flexible models. By exploiting part sharing, we show that this inference can be done extremely efficiently requiring only twice as many computations as searching for the entire object (i.e., not modeling occlusion). We evaluate our model on the standard benchmarked "We Are Family" Stickmen dataset and obtain significant performance improvements over the best alternative algorithms.

* CVPR 15 Camera Ready

* CVPR 15 Camera Ready

**Click to Read Paper**
Semantic Part Segmentation using Compositional Model combining Shape and Appearance

Dec 18, 2014

Jianyu Wang, Alan Yuille

In this paper, we study the problem of semantic part segmentation for animals. This is more challenging than standard object detection, object segmentation and pose estimation tasks because semantic parts of animals often have similar appearance and highly varying shapes. To tackle these challenges, we build a mixture of compositional models to represent the object boundary and the boundaries of semantic parts. And we incorporate edge, appearance, and semantic part cues into the compositional model. Given part-level segmentation annotation, we develop a novel algorithm to learn a mixture of compositional models under various poses and viewpoints for certain animal classes. Furthermore, a linear complexity algorithm is offered for efficient inference of the compositional model using dynamic programming. We evaluate our method for horse and cow using a newly annotated dataset on Pascal VOC 2010 which has pixelwise part labels. Experimental results demonstrate the effectiveness of our method.
Dec 18, 2014

Jianyu Wang, Alan Yuille

**Click to Read Paper**

Articulated Pose Estimation by a Graphical Model with Image Dependent Pairwise Relations

Nov 04, 2014

Xianjie Chen, Alan Yuille

We present a method for estimating articulated human pose from a single static image based on a graphical model with novel pairwise relations that make adaptive use of local image measurements. More precisely, we specify 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). These spatial relationships are represented by a mixture model. We use Deep Convolutional Neural Networks (DCNNs) to learn conditional probabilities for the presence of parts and their spatial relationships within image patches. Hence our model combines the representational flexibility of graphical models with the efficiency and statistical power of DCNNs. Our method significantly outperforms the state of the art methods on the LSP and FLIC datasets and also performs very well on the Buffy dataset without any training.
Nov 04, 2014

Xianjie Chen, Alan Yuille

* NIPS 2014 Camera Ready

**Click to Read Paper**

Efficient variational inference in large-scale Bayesian compressed sensing

Sep 05, 2011

George Papandreou, Alan Yuille

We study linear models under heavy-tailed priors from a probabilistic viewpoint. Instead of computing a single sparse most probable (MAP) solution as in standard deterministic approaches, the focus in the Bayesian compressed sensing framework shifts towards capturing the full posterior distribution on the latent variables, which allows quantifying the estimation uncertainty and learning model parameters using maximum likelihood. The exact posterior distribution under the sparse linear model is intractable and we concentrate on variational Bayesian techniques to approximate it. Repeatedly computing Gaussian variances turns out to be a key requisite and constitutes the main computational bottleneck in applying variational techniques in large-scale problems. We leverage on the recently proposed Perturb-and-MAP algorithm for drawing exact samples from Gaussian Markov random fields (GMRF). The main technical contribution of our paper is to show that estimating Gaussian variances using a relatively small number of such efficiently drawn random samples is much more effective than alternative general-purpose variance estimation techniques. By reducing the problem of variance estimation to standard optimization primitives, the resulting variational algorithms are fully scalable and parallelizable, allowing Bayesian computations in extremely large-scale problems with the same memory and time complexity requirements as conventional point estimation techniques. We illustrate these ideas with experiments in image deblurring.
Sep 05, 2011

George Papandreou, Alan Yuille

* Proc. IEEE Workshop on Information Theory in Computer Vision and Pattern Recognition (in conjunction with ICCV-11), pp. 1332-1339, Barcelona, Spain, Nov. 2011

* 8 pages, 3 figures, appears in Proc. IEEE Workshop on Information Theory in Computer Vision and Pattern Recognition (in conjunction with ICCV-11), Barcelona, Spain, Nov. 2011

**Click to Read Paper**

* MIT CBMM Memo No. 088

**Click to Read Paper**

Generating Multiple Diverse Hypotheses for Human 3D Pose Consistent with 2D Joint Detections

Aug 20, 2017

Ehsan Jahangiri, Alan L. Yuille

Aug 20, 2017

Ehsan Jahangiri, Alan L. Yuille

* accepted to ICCV 2017 (PeopleCap)

**Click to Read Paper**

Exploiting Symmetry and/or Manhattan Properties for 3D Object Structure Estimation from Single and Multiple Images

Mar 29, 2017

Yuan Gao, Alan L. Yuille

Mar 29, 2017

Yuan Gao, Alan L. Yuille

* Accepted to CVPR 2017

**Click to Read Paper**

Complexity of Representation and Inference in Compositional Models with Part Sharing

Jan 16, 2013

Alan L. Yuille, Roozbeh Mottaghi

Jan 16, 2013

Alan L. Yuille, Roozbeh Mottaghi

* ICLR 2013

**Click to Read Paper**

OriNet: A Fully Convolutional Network for 3D Human Pose Estimation

Nov 12, 2018

Chenxu Luo, Xiao Chu, Alan Yuille

Nov 12, 2018

Chenxu Luo, Xiao Chu, Alan Yuille

* BMVC 2018 - Proceedings of the British Machine Vision Conference 2018

* BMVC 2018. Code available at https://github.com/chenxuluo/OriNet-demo

**Click to Read Paper**

Parsing Semantic Parts of Cars Using Graphical Models and Segment Appearance Consistency

Jun 11, 2014

Wenhao Lu, Xiaochen Lian, Alan Yuille

This paper addresses the problem of semantic part parsing (segmentation) of cars, i.e.assigning every pixel within the car to one of the parts (e.g.body, window, lights, license plates and wheels). We formulate this as a landmark identification problem, where a set of landmarks specifies the boundaries of the parts. A novel mixture of graphical models is proposed, which dynamically couples the landmarks to a hierarchy of segments. When modeling pairwise relation between landmarks, this coupling enables our model to exploit the local image contents in addition to spatial deformation, an aspect that most existing graphical models ignore. In particular, our model enforces appearance consistency between segments within the same part. Parsing the car, including finding the optimal coupling between landmarks and segments in the hierarchy, is performed by dynamic programming. We evaluate our method on a subset of PASCAL VOC 2010 car images and on the car subset of 3D Object Category dataset (CAR3D). We show good results and, in particular, quantify the effectiveness of using the segment appearance consistency in terms of accuracy of part localization and segmentation.
Jun 11, 2014

Wenhao Lu, Xiaochen Lian, Alan Yuille

* 12 pages, CBMM memo

**Click to Read Paper**

* NIPS 2012 Workshop on Human Computation for Science and Computational Sustainability

**Click to Read Paper**

CLEVR-Ref+: Diagnosing Visual Reasoning with Referring Expressions

Jan 03, 2019

Runtao Liu, Chenxi Liu, Yutong Bai, Alan Yuille

Jan 03, 2019

Runtao Liu, Chenxi Liu, Yutong Bai, Alan Yuille

* All data and code concerning CLEVR-Ref+ and IEP-Ref have been released at https://cs.jhu.edu/~cxliu/2019/clevr-ref+

**Click to Read Paper**

* To Appear in IJCAI 2017

**Click to Read Paper**

Semi-Supervised Sparse Representation Based Classification for Face Recognition with Insufficient Labeled Samples

Mar 24, 2017

Yuan Gao, Jiayi Ma, Alan L. Yuille

This paper addresses the problem of face recognition when there is only few, or even only a single, labeled examples of the face that we wish to recognize. Moreover, these examples are typically corrupted by nuisance variables, both linear (i.e., additive nuisance variables such as bad lighting, wearing of glasses) and non-linear (i.e., non-additive pixel-wise nuisance variables such as expression changes). The small number of labeled examples means that it is hard to remove these nuisance variables between the training and testing faces to obtain good recognition performance. To address the problem we propose a method called Semi-Supervised Sparse Representation based Classification (S$^3$RC). This is based on recent work on sparsity where faces are represented in terms of two dictionaries: a gallery dictionary consisting of one or more examples of each person, and a variation dictionary representing linear nuisance variables (e.g., different lighting conditions, different glasses). The main idea is that (i) we use the variation dictionary to characterize the linear nuisance variables via the sparsity framework, then (ii) prototype face images are estimated as a gallery dictionary via a Gaussian Mixture Model (GMM), with mixed labeled and unlabeled samples in a semi-supervised manner, to deal with the non-linear nuisance variations between labeled and unlabeled samples. We have done experiments with insufficient labeled samples, even when there is only a single labeled sample per person. Our results on the AR, Multi-PIE, CAS-PEAL, and LFW databases demonstrate that the proposed method is able to deliver significantly improved performance over existing methods.
Mar 24, 2017

Yuan Gao, Jiayi Ma, Alan L. Yuille

* To appear in IEEE Transactions on Image Processing, 2017

**Click to Read Paper**

DeePM: A Deep Part-Based Model for Object Detection and Semantic Part Localization

Jan 26, 2016

Jun Zhu, Xianjie Chen, Alan L. Yuille

Jan 26, 2016

Jun Zhu, Xianjie Chen, Alan L. Yuille

* the final revision to ICLR 2016, in which some color errors in the figures are fixed

**Click to Read Paper**

PASCAL Boundaries: A Class-Agnostic Semantic Boundary Dataset

Nov 25, 2015

Vittal Premachandran, Boyan Bonev, Alan L. Yuille

Nov 25, 2015

Vittal Premachandran, Boyan Bonev, Alan L. Yuille

**Click to Read Paper**