This survey reviews advances in human motion capture and analysis from 2000 to 2006,
following a previous survey of papers up to 2000 [TB Moeslund, E. Granum, A survey of …

Semantic part localization can facilitate fine-grained categorization by explicitly isolating
subtle appearance differences associated with specific object parts. Methods for pose …

Multi-resolution image features may be approximated via extrapolation from nearby scales,
rather than being computed explicitly. This fundamental insight allows us to design object …

Learning 3D models of all animals in nature requires massively scaling up existing
solutions. With this ultimate goal in mind we develop 3D-Fauna an approach that learns a …

We study the question of feature sets for robust visual object recognition; adopting linear
SVM based human detection as a test case. After reviewing existing edge and gradient …

In this paper we present a computationally efficient framework for part-based modeling and
recognition of objects. Our work is motivated by the pictorial structure models introduced by …

The task of 2-D articulated human pose estimation in natural images is extremely
challenging due to the high level of variation in human appearance. These variations arise …

Due to advances in information technology (eg, digital video cameras, ubiquitous sensors),
the automatic detection of human behaviors from video is a very recent research topic. In this …

We present a fast and accurate algorithm for computing the 2D pose of objects in images
called cascaded pose regression (CPR). CPR progressively refines a loosely specified …

We demonstrate a multiscale pedestrian detector operating in near real time (∼ 6 fps on
640x480 images) with state-of-the-art detection performance. The computational bottleneck …