Results 1 - 10 of 16

Progressive search space reduction for human pose estimation

by Vittorio Ferrari, Manuel Marín-jiménez, Andrew Zisserman - In CVPR , 2008
"... The objective of this paper is to estimate 2D human pose as a spatial configuration of body parts in TV and movie video shots. Such video material is uncontrolled and extremely challenging. We propose an approach that progressively reduces the search space for body parts, to greatly improve the chan ..."
Abstract - Cited by 226 (30 self) - Add to MetaCart
shot, by soft-labeling every pixel as belonging to a particular body part or to the background. We demonstrate upper-body pose estimation by an extensive evaluation over 70000 frames from four episodes of the TV series Buffy the vampire slayer, and present an application to fullbody action recognition

Improved human parsing with a full relational model

by Duan Tran, David Forsyth - In ECCV , 2010
"... Abstract. We show quantitative evidence that a full relational model of the body performs better at upper body parsing than the standard tree model, despite the need to adopt approximate inference and learning procedures. Our method uses an approximate search for inference, and an approximate struct ..."
Abstract - Cited by 36 (3 self) - Add to MetaCart
structure learning method to learn. We compare our method to state of the art methods on our dataset (which depicts a wide range of poses), on the standard Buffy dataset, and on the reduced PASCAL dataset published recently. Our results suggest that the Buffy dataset over emphasizes poses where the arms

Adaptive pose priors for pictorial structures

by Chris Jordan, Ben Taskar - In Proc. CVPR , 2010
"... Pictorial structure (PS) models are extensively used for part-based recognition of scenes, people, animals and multi-part objects. To achieve tractability, the structure and parameterization of the model is often restricted, for example, by assuming tree dependency structure and unimodal, data-indep ..."
Abstract - Cited by 44 (3 self) - Add to MetaCart
80 % to 86 % on the Buffy dataset [8]), while using only 15% of the training data as exemplars. 1.

1 Articulated Human Detection with Flexible Mixtures-of-Parts

by Yi Yang, Deva Ramanan
"... Abstract—We describe a method for articulated human detection and human pose estimation in static images based on a new representation of deformable part models. Rather than modeling articulation using a family of warped (rotated and foreshortened) templates, we use a mixture of small, non-oriented ..."
Abstract - Cited by 65 (2 self) - Add to MetaCart
-of-the-art system for pose estimation, improving past work on the challenging Parse and Buffy datasets, while being orders of magnitude faster.

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

by 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 adap-tive use of local image measurements. More precisely, we specify a graphical model for human pose which exploits the fact the local image measu ..."
Abstract - Cited by 13 (3 self) - Add to MetaCart
performs very well on the Buffy dataset without any training. 1

Cascaded Models for Articulated Pose Estimation

by Benjamin Sapp, Alexander Toshev, Ben Taskar - ECCV 2010 , 2010
"... Abstract. We address the problem of articulated human pose estimation by learning a coarse-to-fine cascade of pictorial structure models. While the fine-level state-space of poses of individual parts is too large to permit the use of rich appearance models, most possibilities can be ruled out by eff ..."
Abstract - Cited by 72 (4 self) - Add to MetaCart
for the final level pictorial structure model. The final level uses much more expensive segmentation, contour and shape features in the model for the remaining filtered set of candidates. We evaluate our framework on the challenging Buffy and PASCAL human pose datasets, improving the state-of-the-art.

Human Instance Segmentation from Video using Detector-based Conditional Random Fields

by Vibhav Vineet, Jonathan Warrell, Lubor Ladicky, Philip H. S. Torr , 2011
"... In this work, we propose a method for instance based human segmentation in images and videos, extending the recent detector-based conditional random field model of Ladicky et.al. Instance based human segmentation involves pixel level labeling of an image, partitioning it into distinct human instance ..."
Abstract - Cited by 2 (0 self) - Add to MetaCart
extensively evaluate our proposed method on the Buffy dataset with our new segmented ground truth images, and show a substantial improvement over existing CRF methods. These new annotations will be made available for future use as well.

Hierarchical CRF with Product Label Spaces for Parts-based Models Gemma Roig 1, ∗ Xavier Boix 2,∗

by Fernando De, Torre Joan, Serrat Carles Vilella, Ln X Ln, X Lm, X Lm, Le X Le, Ln X Ln, Lm X Lm
"... Abstract — Non-rigid object detection is a challenging open research problem in computer vision. It is a critical part in many applications such as image search, surveillance, humancomputer interaction or image auto-annotation. Most successful approaches to non-rigid object detection make use of par ..."
Abstract - Add to MetaCart
method on two applications: facial feature detection on the Multi-PIE database and human pose estimation on the Buffy dataset.

Story-based Video Retrieval in TV series using Plot Synopses

by Makarand Tapaswi, Martin Bäuml, Rainer Stiefelhagen - In ACM International Conference on Multimedia Retrieval , 2014
"... We present a novel approach to search for plots in the story-line of structured videos such as TV series. To this end, we propose to align natural language descriptions of the videos, such as plot synopses, with the corresponding shots in the video. Guided by subtitles and person identities the alig ..."
Abstract - Cited by 4 (1 self) - Add to MetaCart
the align-ment problem is formulated as an optimization task over all possible assignments and solved efficiently using dynamic programming. We evaluate our approach on a novel dataset comprising of the complete season 5 of Buffy the Vampire Slayer, and show good alignment performance and the abil-ity

Face Recognition in Movie Trailers via Mean Sequence Sparse Representation-based Classification

by Enrique G. Ortiz, Alan Wright, Mubarak Shah
"... This paper presents an end-to-end video face recognition system, addressing the difficult problem of identifying a video face track using a large dictionary of still face images of a few hundred people, while rejecting unknown individuals. A straightforward application of the popularℓ 1-minimization ..."
Abstract - Cited by 10 (0 self) - Add to MetaCart
Dataset collected from 101 movie trailers on YouTube. Finally, we show that our method matches or outperforms the state-of-the-art on three existing datasets (YouTube Celebrities, YouTube Faces, and Buffy) and our unconstrained Movie Trailer Face Dataset. More importantly, our method excels at rejecting
Results 1 - 10 of 16