排序方式: 共有10条查询结果,搜索用时 15 毫秒
1
1.
This paper presents a method to capture human pose from individual real-world RGB images using a deep learning technique. The current works on estimating human pose by deep learning are designed in a detection or a regression framework, and in a part-based manner. As a new perspective, we introduce a classification scheme for this problem, which reasons the pose holistically. To the best of our knowledge, this is the first work for holistic human pose classification task that owes its feasibility to the great power of convolutional neural networks in feature learning. After training a convolutional neural network to classify the input image to one of the KeyPoses, the final pose is computed as a linear combination of several KeyPoses. In this new holistic classification attitude, the vast and high degree of freedom human pose space is divided into a finite number of subspaces and the convolutional neural network shows promising results in learning the features of each subspace. Empirical results (PCP and PCK rates) demonstrate that the proposed scheme is successfully able to understand human pose (i.e., predict a valid, true and coarse pose) in real-world unconstrained images with challenges like severe occlusion, high articulation, low quality and cluttered background. Furthermore, using the proposed method, the need for defining a complex model (such as appearance model or joints pairwise relations) is relieved. We have also verified a potential application of our proposed method in semantic image retrieval based on human pose. 相似文献
2.
Multimedia Tools and Applications - Extensive use of three dimensional models in various areas indicates the importance of 3D data retrieval accuracy. In this paper, a directional graph, is... 相似文献
3.
4.
5.
Mohammadali Hajizadeh Hossein Ebrahimnezhad 《Computer Animation and Virtual Worlds》2016,27(6):556-576
Efficient compression techniques are required for animated mesh sequences with fixed connectivity and time‐varying geometry. In this paper, we propose a key‐frame‐based technique for three‐dimensional dynamic mesh compression. First, key‐frames are extracted from the animated sequence. Extracted key‐frames are then linearly combined using blending weights to predict the vertex locations of the other frames. These blending weights play a key role in the proposed algorithm because the prediction performance and the required number of key‐frames greatly depend on these weights. We present a novel method in order to compute the optimum blending weight that makes it possible to predict location of the vertices of the non‐key frames with the minimum number of key‐frames. The residual prediction errors are finally quantized and encoded using Huffman coding and another heuristic method. Experimental results on different test sequences with various sizes, topologies, and geometries demonstrate the privileged performance of the proposed method compared with the previous techniques. Copyright © 2015 John Wiley & Sons, Ltd. 相似文献
6.
7.
8.
9.
Hajizadeh Mohammadali Ebrahimnezhad Hossein 《Multimedia Tools and Applications》2018,77(15):19347-19375
Multimedia Tools and Applications - Dynamic 3D mesh compression is of great practical important issues in computer graphics and multimedia applications. In this paper, an efficient compression... 相似文献
10.
Mahdikhanlou Khadijeh Ebrahimnezhad Hossein 《Multimedia Tools and Applications》2020,79(31-32):22235-22259
Multimedia Tools and Applications - American sign language recognition is still a research focus in computer vision community. Recently, most researches mainly extract low-level features for hand... 相似文献
1