Results 1 -
9 of
9
H.: Who blocks who: Simultaneous clothing segmentation for grouping images
- In: Proceedings of IEEE International Conference on Computer Vision
, 2011
"... Clothing is one of the most informative cues of human appearance. In this paper, we propose a novel multi-person clothing segmentation algorithm for highly occluded images. The key idea is combining blocking models to address the person-wise occlusions. In contrary to the traditional layered model t ..."
Abstract
-
Cited by 14 (1 self)
- Add to MetaCart
(Show Context)
Clothing is one of the most informative cues of human appearance. In this paper, we propose a novel multi-person clothing segmentation algorithm for highly occluded images. The key idea is combining blocking models to address the person-wise occlusions. In contrary to the traditional layered model that tries to solve the full layer ranking problem, the proposed blocking model partitions the problem into a series of pair-wise ones and then determines the local blocking relationship based on individual and contextual information. Thus, it is capable of dealing with cases with a large number of people. Additionally, we propose a layout model formulated as Markov Network which incorporates the blocking relationship to pursue an approximately optimal clothing layout for group people. Experiments demonstrated on a group images dataset show the effectiveness of our algorithm. 1.
Augmenting CRFs with Boltzmann Machine Shape Priors for Image Labeling
"... indicates equal contribution Conditional random fields (CRFs) provide powerful tools for building models to label image segments. They are particularly well-suited to modeling local interactions among adjacent regions (e.g., superpixels). However, CRFs are limited in dealing with complex, global (lo ..."
Abstract
-
Cited by 10 (3 self)
- Add to MetaCart
(Show Context)
indicates equal contribution Conditional random fields (CRFs) provide powerful tools for building models to label image segments. They are particularly well-suited to modeling local interactions among adjacent regions (e.g., superpixels). However, CRFs are limited in dealing with complex, global (long-range) interactions between regions. Complementary to this, restricted Boltzmann machines (RBMs) can be used to model global shapes produced by segmentation models. In this work, we present a new model that uses the combined power of these two network types to build a state-of-the-art labeler. Although the CRF is a good baseline labeler, we show how an RBM can be added to the architecture to provide a global shape bias that complements the local modeling provided by the CRF. We demonstrate its labeling performance for the parts of complex face images from the Labeled Faces in the Wild data set. This hybrid model produces results that are both quantitatively and qualitatively better than the CRF alone. In addition to high-quality labeling results, we demonstrate that the hidden units in the RBM portion of our model can be interpreted as face attributes that have been learned without any attribute-level supervision. 1.
What Are Good Parts for Hair Shape Modeling?
"... Hair plays an important role in human appearance. However, hair segmentation is still a challenging problem partially due to the lack of an effective model to handle its arbitrary shape variations. In this paper, we present a part-based model robust to hair shape and environment variations. The key ..."
Abstract
-
Cited by 5 (0 self)
- Add to MetaCart
(Show Context)
Hair plays an important role in human appearance. However, hair segmentation is still a challenging problem partially due to the lack of an effective model to handle its arbitrary shape variations. In this paper, we present a part-based model robust to hair shape and environment variations. The key idea of our method is to identify local parts by promoting the effectiveness of the part-based model. To this end, we propose a measurable statistic, called Subspace Clustering Dependency (SC-Dependency), to estimate the co-occurrence probabilities between local shapes. SC-Dependency guarantees output reasonability and allows us to evaluate the effectiveness of part-wise constraints in an information-theoretic way. Then we formulate the part identification problem as an MRF that aims to optimize the effectiveness of the potential functions. Experiments are performed on a set of consumer images and show our algorithm’s capability and robustness to handle hair shape variations and extreme environment conditions. 1.
Isomorphic manifold inference for hair segmentation
- In Proc. Int. Conf. Automatic Face and Gesture Recognition (FG
, 2013
"... Abstract—Hair segmentation is challenging due to the diverse appearance, irregular region boundary and the influence of complex background. To deal with this problem, we propose a novel method, named Isomorphic Manifold Inference (IMI). Given a head-shoulder image, a Coarse Hair Probability Map (Coa ..."
Abstract
-
Cited by 1 (0 self)
- Add to MetaCart
(Show Context)
Abstract—Hair segmentation is challenging due to the diverse appearance, irregular region boundary and the influence of complex background. To deal with this problem, we propose a novel method, named Isomorphic Manifold Inference (IMI). Given a head-shoulder image, a Coarse Hair Probability Map (Coarse HPM), each element of which represents the probability of the pixel being hair, is initially calculated by exploring hair location and color priors. Then, based on an observation that similar Coarse HPMs imply similar segmentations, we formulate Coarse HPM and corresponding ground segmentation (Optimal HPM) as a pair of isomorphic manifolds. Under this formulation, final hair segmentation is inferred from the Coarse HPM with regression techniques. In this way, the IMI implicitly exploits the hair-specific prior embodied in the training set. Extensive experimental comparisons are conducted and the results strongly encourage the method. The generality of IMI to other class-specific image segmentation is also discussed. Keywords-Hair segmentation; Shape prior; Isomorphic
The Shape-Time Random Field for Semantic Video Labeling
"... We propose a novel discriminative model for semantic labeling in videos by incorporating a prior to model both the shape and temporal dependencies of an object in video. A typical approach for this task is the conditional random field (CRF), which can model local interactions among ad-jacent regions ..."
Abstract
-
Cited by 1 (1 self)
- Add to MetaCart
(Show Context)
We propose a novel discriminative model for semantic labeling in videos by incorporating a prior to model both the shape and temporal dependencies of an object in video. A typical approach for this task is the conditional random field (CRF), which can model local interactions among ad-jacent regions in a video frame. Recent work [16, 14] has shown how to incorporate a shape prior into a CRF for improving labeling performance, but it may be difficult to model temporal dependencies present in video by using this prior. The conditional restricted Boltzmann machine (CRBM) can model both shape and temporal dependencies, and has been used to learn walking styles from motion-capture data. In this work, we incorporate a CRBM prior into a CRF framework and present a new state-of-the-art model for the task of semantic labeling in videos. In partic-ular, we explore the task of labeling parts of complex face scenes from videos in the YouTube Faces Database (YFDB). Our combined model outperforms competitive baselines both qualitatively and quantitatively. 1.
Using Structural Patches Tiling to Guide Human Head-Shoulder Segmentation
"... In this paper, we propose a novel and effective structural patches tiling procedure which is able to generate high quality probabilistic masks to guide semantic segmentation. In this structural patches tiling procedure, we first apply a local patch structure classifier trained by random forest to th ..."
Abstract
- Add to MetaCart
(Show Context)
In this paper, we propose a novel and effective structural patches tiling procedure which is able to generate high quality probabilistic masks to guide semantic segmentation. In this structural patches tiling procedure, we first apply a local patch structure classifier trained by random forest to the input image in a sliding window manner, and then construct an MRF iteratively optimized to assemble a high quality probabilistic mask from responses collected from the previous stage. Our main contributions are twofold: A patch-based classification procedure which is fast and capable of capturing rich local structures compared with pixel-based ones; a flexible Markovian sliding window merging algorithm which integrates context information into traditional sliding window method. Without loss of generality, we use head-shoulder segmentation to illustrate this procedure’s power. Experiments on daily photos and comparisons with previous work demonstratethatweareabletoachievestate-of-the-artheadshouldersegmentationresultsthankstothisstructuralpatches tiling procedure.
Hair Style Retrieval by Semantic Mapping on Informative Patches
"... Abstract—Hair is an important aspect of human appearance. Hair color has been employed to facilitate face retrieval in literature, but hair style is still dismissed because of the challenges of its segmentation. In this paper, we propose a novel hair style retrieval algorithm in unconstrained enviro ..."
Abstract
- Add to MetaCart
(Show Context)
Abstract—Hair is an important aspect of human appearance. Hair color has been employed to facilitate face retrieval in literature, but hair style is still dismissed because of the challenges of its segmentation. In this paper, we propose a novel hair style retrieval algorithm in unconstrained environments. In contrary to defining similarity based on features, we base our measurement directly on hair shapes. To bridge the “semantic gap ” between low-level features and high-level hairstyle, we incorporate mapping function which integrates local and pairwise evidences in MRF framework. Additionally, we propose a RankBoost learning algorithm to select the most informative patches integrating the heuristic information of mapping function accuracy. Our method is applied to the “Labeled Faces in the Wild ” dataset and yields promising results. I.
Who Blocks Who: Simultaneous Segmentation of Occluded Objects
, 2012
"... Abstract In this paper, we present a simultaneous segmentation algorithm for multiple highly-occluded objects, which combines high-level knowledge and low-level information in a unified framework. The high-level knowledge provides sophis-ticated shape priors with the consideration of blocking relati ..."
Abstract
- Add to MetaCart
(Show Context)
Abstract In this paper, we present a simultaneous segmentation algorithm for multiple highly-occluded objects, which combines high-level knowledge and low-level information in a unified framework. The high-level knowledge provides sophis-ticated shape priors with the consideration of blocking relationship between nearby objects. Different from conventional layered model which attempts to solve the full ordering problem, we decompose the problem into a series of pairwise ones and this makes our algorithm scalable to a large number of objects. Objects are segmented in pixel level with higher-order soft constraints from superpixels, by a dual-level conditional random field. The model is optimized alternately by object layout and pixel-wise segmentation. We evaluate our system on different objects, i.e., clothing and pedestrian, and show impressive segmentation results and significant improvement over state-of-the-art segmentation algorithms.
