Most existing approaches for learning action models work by extracting suitable low-level features and then training appropriate classifiers. Such approaches require large amounts of training data and do not generaliz...
详细信息
ISBN:
(数字)9781424469857
ISBN:
(纸本)9781424469840
Most existing approaches for learning action models work by extracting suitable low-level features and then training appropriate classifiers. Such approaches require large amounts of training data and do not generalize well to variations in viewpoint, scale and across datasets. Some work has been done recently to learn multi-view action models from Mocap data, but obtaining such data is time consuming and requires costly infrastructure. We present a method that addresses both these issues by learning action models from just a few video training samples. We model each action as a sequence of primitive actions, represented as functions which transform the actor's state. We formulate model learning as a curve-fitting problem, and present a novel algorithm for learning human actions by lifting 2D annotations of a few keyposes to 3D and interpolating between them. Actions are inferred by sampling the models and accumulating the feature weights learned discriminatively using a latent state Perceptron algorithm. We show results comparable to state-of-art on the standard Weizmann dataset, with a much smaller train:test ratio, and also in datasets for visual gesture recognition and cluttered grocery store environments.
The acquisition of new scientific knowledge and the evolution of the needs of the society regularly call into question the orientations of research. Means to recall and visualize these evolutions are thus necessary. T...
详细信息
The acquisition of new scientific knowledge and the evolution of the needs of the society regularly call into question the orientations of research. Means to recall and visualize these evolutions are thus necessary. The existing tools for research survey give only one fixed vision of the research activity, which does not allow performing tasks of dynamic topic mining. The objective of this paper is thus to propose a new incremental approach in order to follow the evolution of research themes and research groups for a scientific discipline given in terms of emergence or decline. These behaviors are detectable by various methods of filtering. However, our choice is made on the exploitation of neural clustering methods in a multi-view context. This new approach makes it possible to take into account the incremental and chronological aspect of information by opening the way to the detection of convergences and divergences of research themes and groups.
To extract the salient features of the image more effectively and improve the performance of multi-focus image fusion, for the shortcomings of Curvelet which can not capture the texture information, According to the r...
详细信息
A hierarchical stereo matching algorithm with adaptive threshold is presented. The backwards matching strategy with disparity predetermined and the adaptive matching threshold updating method based on candidates match...
详细信息
A new image based activity recognition method for a person wearing a video camera below the neck is presented in this paper. The wearable device is used to capture video data in front of the wearer. Although the weare...
详细信息
A new image based activity recognition method for a person wearing a video camera below the neck is presented in this paper. The wearable device is used to capture video data in front of the wearer. Although the wearer never appears in the video, his or her physical activity is analyzed and recognized using the recorded scene changes resulting from the motion of the wearer. Correspondence features are extracted from adjacent frames and inaccurate matches are removed based on a set of constraints imposed by the camera model. Motion histograms are defined and calculated within a frame and we define a new feature called accumulated motion distribution derived from motion statistics in each frame. A Support Vector Machine (SVM) classifier is trained with this feature and used to classify physical activities in different scenes. Our results show that different types of activities can be recognized in low resolution, field acquired real-world video.
Computation of functional regional scores requires proper identification of LV contours. On one hand, manual segmentation is robust, but it is time consuming and requires high expertise. On the other hand, the tag pat...
详细信息
Computation of functional regional scores requires proper identification of LV contours. On one hand, manual segmentation is robust, but it is time consuming and requires high expertise. On the other hand, the tag pattern in TMR sequences is a problem for automatic segmentation of LV boundaries. We propose a segmentation method based on a predictor-corrector (Active Contours - Shape Models) scheme. Special stress is put in the definition of the AC external forces. First, we introduce a semantic description of the LV that discriminates myocardial tissue by using texture and motion descriptors. Second, in order to ensure convergence regardless of the initial contour, the external energy is decoupled according to the orientation of the edges in the image potential. We have validated the model in terms of error in segmented contours and accuracy of regional clinical scores.
We demonstrate a concept of computervision as a secure, live service on the Internet. We show a platform to distribute a real lime vision algorithm using simple widely available web technologies, such as Adobe Flash....
详细信息
ISBN:
(纸本)9781424439942
We demonstrate a concept of computervision as a secure, live service on the Internet. We show a platform to distribute a real lime vision algorithm using simple widely available web technologies, such as Adobe Flash. We allow a user to access this service without downloading an executable or sharing the image stream with anyone. We support developers to publish without distribution complexity Finally the platform supports user-permitted aggregation of data for computervision research or analysis. We describe results a simple distributed motion detection algorithm. We discuss future scenarios for organically extending the horizon of computervision research.
We investigate the problem of recognizing words from video, fingerspelled using the British Sign Language (BSL) fingerspelling alphabet. This is a challenging task since the BSL alphabet involves both hands occluding ...
详细信息
ISBN:
(纸本)9781424439942
We investigate the problem of recognizing words from video, fingerspelled using the British Sign Language (BSL) fingerspelling alphabet. This is a challenging task since the BSL alphabet involves both hands occluding each other and contains signs which are ambiguous from the observer's viewpoint. The main contributions of our work include: (i) recognition based on hand shape alone, not requiring motion cues;(ii) robust visual features for hand shape recognition;(iii) scalability to large lexicon recognition with no re-training. We report results on a dataset of 1,000 low quality web-cam videos of 100 words. The proposed method achieves a word recognition accuracy of 98.9%.
Laughter detection is an important area of interest in the Affective Computing and Human-computer Interaction fields. In this paper we propose a multi-modal methodology, based on the fusion of audio and visual cues to...
详细信息
ISBN:
(纸本)9781424439942
Laughter detection is an important area of interest in the Affective Computing and Human-computer Interaction fields. In this paper we propose a multi-modal methodology, based on the fusion of audio and visual cues to deal with the laughter recognition problem in face-to-face conversations. The audio features are extracted from the spectogram and the video features are obtained estimating the mouth movement degree and using a smile and laughter classifier Finally, the multi-modal cues are included in a sequential classifier Results over videos from the public discussion blog of the New York Times show that both types of features perform better when considered together by the classifier Moreover the sequential methodology shows to significantly, outperform the results obtained by an Adaboost classifier
暂无评论