Recently, some weakly supervised multi-object tracking (MOT) methods learn identity embedding features with pseudo identity labels rather than the high-cost manual ones. However, these pseudo identity labels may conta...
详细信息
Salient object detection, experienced several decades, has been an active and popular topic in computer vision. Although a large amount of detection algorithms have been proposed, the obtained saliency maps are still ...
详细信息
Salient object detection, experienced several decades, has been an active and popular topic in computer vision. Although a large amount of detection algorithms have been proposed, the obtained saliency maps are still not satisfying enough. To this end, we proposed a simple and novel supervised algorithm to detect a pure background saliency map using conditional random fields (CRF) and saliency cues. Most existing CRF approaches set up the probabilistic graphical models with pixel-wise eight neighborhood grid-shaped graph, while our superpixel level graph handling can not only simplify the model but also promote the performance due to the superpixel level two-ring with pseudo-background neighborhood system. It is intuitive and easy to interpret. As a result, the saliency maps generated by the proposed model have relatively pure background regions. Extensive experimental evaluations on six benchmark datasets with pixel-wise ground truths validated the robustness and effectiveness of the proposed saliency model.
In this manuscript, we propose an automatic sketch synthesis algorithm based on embedded hidden Markov model (E-HMM) and selective ensemble strategy. The E-HMM is used to model the nonlinear relationship between a pho...
详细信息
In this manuscript, we propose an automatic sketch synthesis algorithm based on embedded hidden Markov model (E-HMM) and selective ensemble strategy. The E-HMM is used to model the nonlinear relationship between a photo-sketch pair firstly, and then a series of pseudo-sketches, which are generated based on several learned models for a given photo, are integrated together with selective ensemble strategy to synthesize a finer face pseudo-sketch. The experimental results illustrate that the proposed algorithm achieves satisfactory effect of sketch synthesis.
Multimodal hashing, which conducts effective and efficient nearest neighbor search across heterogeneous data on large-scale multimedia databases, has been attracting increasing interest, given the explosive growth of ...
详细信息
Heterogeneous face recognition (HFR) refers to matching face images acquired from different sources (i.e., different sensors or different wavelengths) for identification. HFR plays an important role in both biometrics...
详细信息
Solving Level Set Equation (LSE) by using the classical methods, mostly based on finite differences approximations, costs a lot of computer time particularly when processing high dimensional large-scale data. In recen...
详细信息
Solving Level Set Equation (LSE) by using the classical methods, mostly based on finite differences approximations, costs a lot of computer time particularly when processing high dimensional large-scale data. In recent years, the Lattice Boltzmann Method (LBM) has attracted much attention as a fast alternative approach for solving LSE. The LBM is explicit and highly parallelizable. In this paper, we use the LBM to solve the LSE, we propose an Unsigned Pressure Force (UPF) based on region attribute, which can effectively and efficiently stop the contour at weak blurred edges. The experiments on synthetic and real images illustrate the performance of the proposed method.
This paper reports on the suitability of the SUSAN filter for the removal of artifacts that result from quantization errors in wavelet video coding. In this paper two extensions of the original filter are described. T...
详细信息
With the rapid development of deep learning techniques as well as increasingly more visual information being made publicly available on the Internet, image translation methods have achieved great progress and encourag...
详细信息
This paper presents a fast and robust level set method for image segmentation. To enhance the robustness against noise, we embed a Markov random field (MRF) energy function to the conventional level set energy functio...
详细信息
Recently, some weakly supervised multi-object tracking (MOT) methods learn identity embedding features with pseudo identity labels rather than the high-cost manual ones. However, these pseudo identity labels may conta...
详细信息
Recently, some weakly supervised multi-object tracking (MOT) methods learn identity embedding features with pseudo identity labels rather than the high-cost manual ones. However, these pseudo identity labels may contain many false or missing identities, which adversely affect the optimization of tracking networks, resulting in interrupted trajectories of occluded targets. To effectively reconnect the interrupted trajectories caused by noisy pseudo labels, we propose a novel weakly supervised MOT method based on a Trajectory-Reconnecting Transformer (TRTMOT). TRT-MOT performs feature decoupling to extract discriminative embedding features for reconnecting trajectories of occluded targets. Experimental results show that TRTMOT outperforms previous weakly supervised MOT methods by at least +3.6 and +5.6 on MOTA for the MOT17 and MOT20 datasets, respectively.
暂无评论