HumanEva: Synchronized Video and Motion Capture Dataset and Baseline Algorithm for Evaluation of Articulated Human Motion
- L. Sigal, A. O. Balan, Michael J. Black
- Computer ScienceInternational Journal of Computer Vision
- 1 March 2010
A baseline algorithm for 3D articulated tracking that uses a relatively standard Bayesian framework with optimization in the form of Sequential Importance Resampling and Annealed Particle Filtering is described, and a variety of likelihood functions, prior models of human motion and the effects of algorithm parameters are explored.
HumanEva: Synchronized Video and Motion Capture Dataset for Evaluation of Articulated Human Motion
There is a need for common datasets that allow fair comparison between different methods and their design choices to establish the current state of the art, and it is argued that HumanEva-I will become a standard dataset for the evaluation of articulated human motion and pose estimation.
Tracking loose-limbed people
- L. Sigal, S. Bhatia, S. Roth, Michael J. Black, M. Isard
- Computer ScienceProceedings of the IEEE Computer Society…
- 19 July 2004
The problem of 3D human tracking as one of inference in a graphical model that is a collection of loosely-connected limbs and non-parametric belief propagation using a variation of particle filtering that can be applied over a general loopy graph is posed.
Multilevel Language and Vision Integration for Text-to-Clip Retrieval
- Huijuan Xu, Kun He, Bryan A. Plummer, L. Sigal, S. Sclaroff, Kate Saenko
- Computer ScienceAAAI Conference on Artificial Intelligence
- 13 April 2018
A multilevel model that integrates vision and language features earlier and more tightly than prior work is introduced, and text features are injected early on when generating clip proposals to help eliminate unlikely clips and thus speed up processing and boost performance.
A Quantitative Evaluation of Video-based 3D Person Tracking
- A. O. Balan, L. Sigal, Michael J. Black
- Computer ScienceIEEE International Workshop on Visual…
- 15 October 2005
The Bayesian estimation of 3D human motion from video sequences is quantitatively evaluated using synchronized, multi-camera, calibrated video and 3D ground truth poses acquired with a commercial motion capture system to suggest that in constrained laboratory environments, current methods perform quite well.
Learning Activity Progression in LSTMs for Activity Detection and Early Detection
This work designs novel ranking losses that directly penalize the model on violation of such monotonicities, which are used together with classification loss in training of LSTM models.
Measure Locally, Reason Globally: Occlusion-sensitive Articulated Pose Estimation
An extension of an approximate belief propagation algorithm (PAMPAS) that recovers the real-valued 2D pose of the body in the presence of occlusions, does not require strong priors over body pose and does a quantitatively better job of explaining image evidence than previous methods.
Image Generation From Layout
- Bo Zhao, Lili Meng, Weidong Yin, L. Sigal
- Computer ScienceComputer Vision and Pattern Recognition
- 28 November 2018
The proposed Layout2Im model significantly outperforms the previous state of the art, boosting the best reported inception score by 24.66% and 28.57% on the very challenging COCO-Stuff and Visual Genome datasets, respectively.
Implicit Probabilistic Models of Human Motion for Synthesis and Tracking
- H. Kjellström, Michael J. Black, L. Sigal
- Computer ScienceEuropean Conference on Computer Vision
- 28 May 2002
A low dimensional linear model of human motion is learned that is used to structure the example motion database into a binary tree and an approximate probabilistic tree search method exploits the coefficients of this low-dimensional representation and runs in sub-linear time.
High-Dimensional Feature Selection by Feature-Wise Kernelized Lasso
- M. Yamada, Wittawat Jitkrittum, L. Sigal, E. Xing, Masashi Sugiyama
- Computer ScienceNeural Computation
- 2 February 2012
It is shown that with particular choices of kernel functions, nonredundant features with strong statistical dependence on output values can be found in terms of kernel-based independence measures such as the Hilbert-Schmidt independence criterion and the globally optimal solution can be efficiently computed.