Multiple Instance Learning (MIL) proposes a new paradigm when instance labeling, in the learning step, is not possible or infeasible, by assigning a single label (positive or negative) to a set of instances called bag. In this paper, an operator based on homogeneity of positive bags for MIL is introduced. Our method consists in removing instances from the positives bags according to their simil...

We propose a multiple instance learning approach to contentbased retrieval of classroom video for the purpose of supporting human assessing the learning environment. The key element of our approach is a mapping between the semantic concepts of the assessment system and features of the video that can be measured using techniques from the fields of computer vision and speech analysis. We report o...

Understanding and learning the subjective aspect of humans in Content-Based Image Retrieval has been an active research field during the past few years. However, how to effectively discover users’ concept patterns when there are multiple visual features existing in the retrieval system still remains a big issue. In this paper, we propose a multimedia data mining framework that incorporates Mult...

In this paper, we propose a number of adaptive prototype learning (APL) algorithms. They employ the same algorithmic scheme to determine the number and location of prototypes, but differ in the use of samples or the weighted averages of samples as prototypes, and also in the assumption of distance measures. To understand these algorithms from a theoretical viewpoint, we address their convergenc...

Instrumented gloves use a variety of sensors to provide information about the user's hand. They can be used for recognition of gestures; especially well-deened gesture sets such as sign languages. However, recognising gestures is a diicult task, due to intrapersonal and inter-personal variations in performing them. One approach to solving this problem is to use machine learning. In this case, s...

Multiple instance learning (MIL) can reduce the need for costly annotation in tasks such as semantic segmentation by weakening the required degree of supervision. We propose a novel MIL formulation of multi-class semantic segmentation learning by a fully convolutional network. In this setting, we seek to learn a semantic segmentation model from just weak image-level labels. The model is trained...

When supervising an object detector with weakly labeled data, most existing approaches are prone to trapping in the discriminative object parts, e.g., finding the face of a cat instead of the full body, due to lacking the supervision on the extent of full objects. To address this challenge, we incorporate object segmentation into the detector training, which guides the model to correctly locali...

In many cases, human actions can be identified not only by the singular observation of the human body in motion, but also properties of the surrounding scene and the related objects. In this paper, we look into this problem and propose an approach for human action recognition that integrates multiple feature channels from several entities such as objects, scenes and people. We formulate the pro...

Lazy learning algorithms retain their raw training examples and defer all example-processing until problem solving time (eg, case-based learning, instance-based learning, and nearest-neighbour methods). A case-based classifier will typically compare a new target query to every case in its case-base (its raw training data) before deriving a target classification. This can make lazy methods prohi...