Sort:
Research Article Issue
Expression Complementary Disentanglement Network for Facial Expression Recognition
Chinese Journal of Electronics 2024, 33(3): 742-752
Published: 05 May 2024
Abstract PDF (5.5 MB) Collect
Downloads:0

Disentangling facial expressions from other disturbing facial attributes in face images is an essential topic for facial expression recognition. Previous methods only care about facial expression disentanglement (FED) itself, ignoring the negative effects of other facial attributes. Due to the annotations on limited facial attributes, it is difficult for existing FED solutions to disentangle all disturbance from the input face. To solve this issue, we propose an expression complementary disentanglement network (ECDNet). ECDNet proposes to finish the FED task during a face reconstruction process, so as to address all facial attributes during disentanglement. Different from traditional reconstruction models, ECDNet reconstructs face images by progressively generating and combining facial appearance and matching geometry. It designs the expression incentive (EIE) and expression inhibition (EIN) mechanisms, inducing the model to characterize the disentangled expression and complementary parts precisely. Facial geometry and appearance, generated in the reconstructed process, are dealt with to represent facial expressions and complementary parts, respectively. The combination of distinctive reconstruction model, EIE, and EIN mechanisms ensures the completeness and exactness of the FED task. Experimental results on RAF-DB, AffectNet, and CAER-S datasets have proven the effectiveness and superiority of ECDNet.

Open Access Article Issue
3D Single Object Tracking with Multi-View Unsupervised Center Uncertainty Learning
CAAI Artificial Intelligence Research 2023, 2: 9150016
Published: 08 October 2023
Abstract PDF (4.3 MB) Collect
Downloads:156

Center point localization is a major factor affecting the performance of 3D single object tracking. Point clouds themselves are a set of discrete points on the local surface of an object, and there is also a lot of noise in the labeling. Therefore, directly regressing the center coordinates is not very reasonable. Existing methods usually use volumetric-based, point-based, and view-based methods, with a relatively single modality. In addition, the sampling strategies commonly used usually result in the loss of object information, and holistic and detailed information is beneficial for object localization. To address these challenges, we propose a novel Multi-view unsupervised center Uncertainty 3D single object Tracker (MUT). MUT models the potential uncertainty of center coordinates localization using an unsupervised manner, allowing the model to learn the true distribution. By projecting point clouds, MUT can obtain multi-view depth map features, realize efficient knowledge transfer from 2D to 3D, and provide another modality information for the tracker. We also propose a former attraction probability sampling strategy that preserves object information. By using both holistic and detailed descriptors of point clouds, the tracker can have a more comprehensive understanding of the tracking environment. Experimental results show that the proposed MUT network outperforms the baseline models on the KITTI dataset by 0.8% and 0.6% in precision and success rate, respectively, and on the NuScenes dataset by 1.4%, and 6.1% in precision and success rate, respectively. The code is made available at https://github.com/abchears/MUT.git.

Open Access Research Article Issue
Face image retrieval based on shape and texture feature fusion
Computational Visual Media 2017, 3(4): 359-368
Published: 02 August 2017
Abstract PDF (2.7 MB) Collect
Downloads:31

Humongous amounts of data bring various challenges to face image retrieval. This paper proposes an efficient method to solve those problems. Firstly, we use accurate facial landmark locations as shape features. Secondly, we utilise shape priors to provide discriminative texture features for convolutional neural networks. These shape and texture features are fused to make the learned representation more robust. Finally, in order to increase efficiency, a coarse-to-fine search mechanism is exploited to efficiently find similar objects. Extensive experiments on the CASIA-WebFace, MSRA-CFW, and LFW datasets illustrate the superiority of our method.

Total 3
1/11GOpage