Human3.6M: Large Scale Datasets and Predictive Methods for 3D Human Sensing in Natural Environments
- Catalin Ionescu, Dragos Papava, Vlad Olaru, C. Sminchisescu
- Computer ScienceIEEE Transactions on Pattern Analysis and Machine…
- 1 July 2014
We introduce a new dataset, Human3.6M, of 3.6 Million accurate 3D Human poses, acquired by recording the performance of 5 female and 6 male subjects, under 4 different viewpoints, for training…
CPMC: Automatic Object Segmentation Using Constrained Parametric Min-Cuts
- João Carreira, C. Sminchisescu
- Computer ScienceIEEE Transactions on Pattern Analysis and Machine…
- 1 July 2012
A novel framework to generate and rank plausible hypotheses for the spatial extent of objects in images using bottom-up computational processes and mid-level selection cues and it is shown that the algorithm can be used, successfully, in a segmentation-based visual object category recognition pipeline.
Constrained parametric min-cuts for automatic object segmentation
- João Carreira, C. Sminchisescu
- Computer ScienceIEEE Computer Society Conference on Computer…
- 13 June 2010
It is shown that this algorithm significantly outperforms the state of the art for low-level segmentation in the VOC09 segmentation dataset and achieves the same average best segmentation covering as the best performing technique to date.
Twin Gaussian Processes for Structured Prediction
- Liefeng Bo, C. Sminchisescu
- Computer ScienceInternational Journal of Computer Vision
- 1 March 2010
We describe twin Gaussian processes (TGP), a generic structured prediction method that uses Gaussian process (GP) priors on both covariates and responses, both multivariate, and estimates outputs by…
Semantic Segmentation with Second-Order Pooling
- João Carreira, Rui Caseiro, Jorge P. Batista, C. Sminchisescu
- Computer ScienceEuropean Conference on Computer Vision
- 7 October 2012
This paper introduces multiplicative second-order analogues of average and max-pooling that together with appropriate non-linearities lead to state-of-the-art performance on free-form region recognition, without any type of feature coding.
The Moving Pose: An Efficient 3D Kinematics Descriptor for Low-Latency Action Recognition and Detection
- M. Zanfir, Marius Leordeanu, C. Sminchisescu
- Computer ScienceIEEE International Conference on Computer Vision
- 1 December 2013
A fast, simple, yet powerful non-parametric Moving Pose (MP) framework that enables low-latency recognition, one-shot learning, and action detection in difficult unsegmented sequences and is real-time, scalable, and outperforms more sophisticated approaches on challenging benchmarks.
Matrix Backpropagation for Deep Networks with Structured Layers
- Catalin Ionescu, O. Vantzos, C. Sminchisescu
- Computer ScienceIEEE International Conference on Computer Vision
- 7 December 2015
A sound mathematical apparatus to formally integrate global structured computation into deep computation architectures and demonstrates that deep networks relying on second-order pooling and normalized cuts layers, trained end-to-end using matrix backpropagation, outperform counterparts that do not take advantage of such global layers.
Actions in the Eye: Dynamic Gaze Datasets and Learnt Saliency Models for Visual Recognition
- Stefan Mathe, C. Sminchisescu
- Computer ScienceIEEE Transactions on Pattern Analysis and Machine…
- 29 December 2013
This work complements existing state-of-the art large scale dynamic computer vision annotated datasets like Hollywood-2 and UCF Sports with human eye movements collected under the ecological constraints of visual action and scene context recognition tasks, and introduces novel dynamic consistency and alignment measures, which underline the remarkable stability of patterns of visual search among subjects.
Deep Learning of Graph Matching
- Andrei Zanfir, C. Sminchisescu
- Computer ScienceIEEE/CVF Conference on Computer Vision and…
- 1 June 2018
This work presents an end-to-end model that makes it possible to learn all parameters of the graph matching process, including the unary and pairwise node neighborhoods, represented as deep feature extraction hierarchies.
Efficient Match Kernel between Sets of Features for Visual Recognition
- Liefeng Bo, C. Sminchisescu
- Computer ScienceNIPS
- 7 December 2009
It is shown that bag-of-words representations commonly used in conjunction with linear classifiers can be viewed as special match kernels, which count 1 if two local features fall into the same regions partitioned by visual words and 0 otherwise.
...
...