Abstract: Pedestrian classifiers decide which image windows contain a pedestrian. In practice, such classifiers provide a relatively high response at neighbor windows overlapping a pedestrian, while the responses around potential false positives are expected to be lower. An analogous reasoning applies for image sequences. If there is a pedestrian located within a frame, the same pedestrian is expected to appear close to the same location in neighbor frames. Therefore, such a location has chances of receiving high classification scores during several frames, while false positives are expected to be more spurious. In this paper we propose to exploit such correlations for improving the accuracy of base pedestrian classifiers. In particular, we propose to use two-stage classifiers which not only rely on the image descriptors required by the base classifiers but also on the response of such base classifiers in a given spatiotemporal neighborhood. More specifically, we train pedestrian classifiers using a stacked sequential learning (SSL) paradigm. We use a new pedestrian dataset we have acquired from a car to evaluate our proposal at different frame rates. We also test on a well known dataset: Caltech. The obtained results show that our SSL proposal boosts detection accuracy significantly with a minimal impact on the computational cost. Interestingly, SSL improves more the accuracy at the most dangerous situations, i.e. when a pedestrian is close to the camera.

Abstract: Despite recent significant advances, pedestrian detection continues to be an extremely challenging problem in real scenarios. In order to develop a detector that successfully operates under these conditions, it becomes critical to leverage upon multiple cues, multiple imaging modalities and a strong multi-view classifier that accounts for different pedestrian views and poses. In this paper we provide an extensive evaluation that gives insight into how each of these aspects (multi-cue, multimodality and strong multi-view classifier) affect performance both individually and when integrated together. In the multimodality component we explore the fusion of RGB and depth maps obtained by high-definition LIDAR, a type of modality that is only recently starting to receive attention. As our analysis reveals, although all the aforementioned aspects significantly help in improving the performance, the fusion of visible spectrum and depth information allows to boost the accuracy by a much larger margin. The resulting detector not only ranks among the top best performers in the challenging KITTI benchmark, but it is built upon very simple blocks that are easy to implement and computationally efficient. These simple blocks can be easily replaced with more sophisticated ones recently proposed, such as the use of convolutional neural networks for feature representation, to further improve the accuracy.

Abstract: In this work, we develop a generic framework that is able to handle the document retrieval problem in various scenarios such as searching for full page matches or retrieving the counterparts for specific document areas, focusing on their structural similarity or letting their visual resemblance to play a dominant role. Based on the spatial indexing technique, we propose to search for matches of local key-region pairs carrying both structural and visual information from the collection while a scheme allowing to adjust the relative contribution of structural and visual similarity is presented.
Based on the fact that the structure of documents is tightly linked with the distance among their elements, we firstly introduce an efficient detector named Distance Transform based Maximally Stable Extremal Regions (DTMSER). We illustrate that this detector is able to efficiently extract the structure of a document image as a dendrogram (hierarchical tree) of multi-scale key-regions that roughly correspond to letters, words and paragraphs. We demonstrate that, without benefiting from the structure information, the key-regions extracted by the DTMSER algorithm achieve better results comparing with state-of-the-art methods while much less amount of key-regions are employed.
We subsequently propose a pair-wise Bag of Words (BoW) framework to efficiently embed the explicit structure extracted by the DTMSER algorithm. We represent each document as a list of key-region pairs that correspond to the edges in the dendrogram where inclusion relationship is encoded. By employing those structural key-region pairs as the pooling elements for generating the histogram of features, the proposed method is able to encode the explicit inclusion relations into a BoW representation. The experimental results illustrate that the pair-wise BoW, powered by the embedded structural information, achieves remarkable improvement over the conventional BoW and spatial pyramidal BoW methods.
To handle various retrieval scenarios in one framework, we propose to directly query a series of key-region pairs, carrying both structure and visual information, from the collection. We introduce the spatial indexing techniques to the document retrieval community to speed up the structural relationship computation for key-region pairs. We firstly test the proposed framework in a full page retrieval scenario where structurally similar matches are expected. In this case, the pair-wise querying method achieves notable improvement over the BoW and spatial pyramidal BoW frameworks. Furthermore, we illustrate that the proposed method is also able to handle focused retrieval situations where the queries are defined as a specific interesting partial areas of the images. We examine our method on two types of focused queries: structure-focused and exact queries. The experimental results show that, the proposed generic framework obtains nearly perfect precision on both types of focused queries while it is the first framework able to tackle structure-focused queries, setting a new state of the art in the field.
Besides, we introduce a line verification method to check the spatial consistency among the matched key-region pairs. We propose a computationally efficient version of line verification through a two step implementation. We first compute tentative localizations of the query and subsequently employ them to divide the matched key-region pairs into several groups, then line verification is performed within each group while more precise bounding boxes are computed. We demonstrate that, comparing with the standard approach (based on RANSAC), the line verification proposed generally achieves much higher recall with slight loss on precision on specific queries.

Abstract: The mixture of parts model has been successfully applied to solve the 2D
human pose estimation problem either as an explicitly trained body part model
or as latent variables for pedestrian detection. Even in the era of massive
applications of deep learning techniques, the mixture of parts model is still
effective in solving certain problems, especially in the case with limited
numbers of training samples. In this paper, we consider using the mixture of
parts model for pose estimation, wherein a tree structure is utilized for
representing relations between connected body parts. This strategy facilitates
training and inferencing of the model but suffers from double counting
problems, where one detected body part is counted twice due to lack of
constrains among unconnected body parts. To solve this problem, we propose a
generalized solution in which various part attributes are captured by multiple
features so as to avoid the double counted problem. Qualitative and
quantitative experimental results on a public available dataset demonstrate the
effectiveness of our proposed method.
An Effective Solution to Double Counting Problem in Human Pose Estimation – ResearchGate. Available from: http://www.researchgate.net/publication/271218491AnEffectiveSolutiontoDoubleCountingProbleminHumanPose_Estimation [accessed Oct 22, 2015].

Abstract: Bilinear models have been successfully applied to separate two factors, for example, pose variances and different identities in face recognition problems. Asymmetric model is a type of bilinear model which models a system in the most concise way. But seldom there are works exploring the applications of asymmetric bilinear model on face recognition problem with illumination changes. In this work, we propose enhanced asymmetric model for illumination-robust face recognition. Instead of initializing the factor probabilities randomly, we initialize them with nearest neighbor method and optimize them for the test data. Above that, we update the factor model to be identified. We validate the proposed method on a designed data sample and extended Yale B dataset. The experiment results show that the enhanced asymmetric models give promising results and good recognition accuracies.

Abstract: In order to increase the classification performance obtained using Error-Correcting Output Codes designs (ECOC), introducing weights in the decoding phase of the ECOC has attracted a lot of interest. In this work, we present a method for ECOC designs that focuses on increasing hypothesis margin on the data samples given a base classifier. While achieving this, we implicitly reward the base classifiers with high performance, whereas punish those with low performance. The resulting objective function is of the fractional programming type and we deal with this problem through the Dinkelbach’s Algorithm. The conducted tests over well known UCI datasets show that the presented method is superior to the unweighted decoding and that it outperforms the results of the state-of-the-art weighted decoding methods in most of the performed experiments.

Abstract: ChaLearn is organizing for IJCNN 2015 an Automatic Machine Learning challenge (AutoML) to solve classification and regression problems from given feature representations, without any human intervention. This is a challenge with code
submission: the code submitted can be executed automatically on the challenge servers to train and test learning machines on new datasets. However, there is no obligation to submit code. Half of the prizes can be won by just submitting prediction results.
There are six rounds (Prep, Novice, Intermediate, Advanced, Expert, and Master) in which datasets of progressive difficulty are introduced (5 per round). There is no requirement to participate in previous rounds to enter a new round. The rounds alternate AutoML phases in which submitted code is “blind tested” on
datasets the participants have never seen before, and Tweakathon phases giving time (' 1 month) to the participants to improve their methods by tweaking their code on those datasets. This challenge will push the state-of-the-art in fully automatic machine learning on a wide range of problems taken from real world
applications. The platform will remain available beyond the termination of the challenge: http://codalab.org/AutoML