Saliency detection for images has been studied for many years, for which a lot of methods have been designed. In saliency detection, background priors, which are often regarded as pseudo-background, are effective clues to find salient objects in images. Although image boundary is commonly used as background priors, it does not work well for images of complex scenes and videos. In this paper, we explore how to identify the background priors for a video and propose a saliency-based method to detect the visual objects by using the background priors. For a video, we integrate multiple pairs of scale-invariant feature transform flows from long-range frames, and a bidirectional consistency propagation is conducted to obtain the accurate and sufficient temporal background priors, which are combined with spatial background priors to generate spatiotemporal background priors. Next, a novel dual-graph-based structure using spatiotemporal background priors is put forward in the computation of saliency maps, fully taking advantage of appearance and motion information in videos. Experimental results on different challenging data sets show that the proposed method robustly and accurately detects the video objects in both simple and complex scenes and achieves better performance compared with other the state-of-the-art video saliency models.
Nowadays, label distribution learning is among the state-of-the-art methodologies in facial age estimation. It takes the age of each facial image instance as a label distribution with a series of age labels rather than the single chronological age label that is commonly used. However, this methodology is deficient in its simple decision-making criterion: the final predicted age is only selected at the one with maximum description degree. In many cases, different age labels may have very similar description degrees. Consequently, blindly deciding the estimated age by virtue of the highest description degree would miss or neglect other valuable age labels that may contribute a lot to the final predicted age. In this paper, we propose a strategic decision-making label distribution learning algorithm (SDM-LDL) with a series of strategies specialized for different types of age label distribution. Experimental results from the most popular aging face database, FG-NET, show the superiority and validity of all the proposed strategic decision-making learning algorithms over the existing label distribution learning and other single-label learning algorithms for facial age estimation. The inner properties of SDM-LDL are further explored with more advantages.
21 January 2025 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Recently, several spatial-temporal memory-based methods have verified that storing intermediate frames with masks as memory helps segment target objects in videos. However, they mainly focus on better matching between the current frame and memory frames without paying attention to the quality of the memory. Consequently, frames with poor segmentation masks may be memorized, leading to error accumulation problems. Besides, the linear increase of memory frames with the growth of frame numbers limits the ability of the models to handle long videos. To this end, we propose a Quality-aware Dynamic Memory Network (QDMN) to evaluate the segmentation quality of each frame, allowing the memory bank to selectively store accurately segmented frames and prevent error accumulation. Then, we combine the segmentation quality with temporal consistency to dynamically update the memory bank and make the models can handle videos of arbitrary length. The above operation ensures the reliability of memory frames and improves the quality of memory at the frame level. Moreover, we observe that the memory features extracted from reliable frames still contain noise and have limited representation capabilities. To address this problem, we propose to perform memory enhancement and anchoring on the basis of QDMN to improve the quality of memory from the feature level, resulting in a more robust and effective network QDMN++. Our method achieves state-of-the-art performance on all popular benchmarks. Moreover, extensive experiments demonstrate that the proposed memory screening mechanism can be applied to any memory-based methods as generic plugins.
Ordinal hyperplane ranking achieves superior performance in facial age estimation. However, further experiments show that this approach suffers from its ideal ranking rule, which sometimes causes unnecessary estimation deviations and degrades performance. Two approaches with new ranking rules are proposed, which minimise accidental deviations of binary classifiers and tactfully combine the accuracy and obtained label in each binary classification substep for the ranking criteria. Moreover, at first the extreme learning machine is introduced into facial age estimation, taking full advantage of its high learning speed and accuracy. Experimental results from public datasets are presented to demonstrate that the proposed algorithms reduce the mean absolute error and improve age estimation performance while reducing runtime significantly.
We present a spectrum-based framework, utilizing low and high spectral latent features, to colorize the grayscale image. Current image colorization algorithms, despite significant achievements, constantly struggle with color bleeding and low color saturation. One of the main reasons causing such phenomena is vanilla convolutions in modern neural networks focus on local and fixed scales. To alleviate this issue, we propose a novel approach called Low and High Spectral Colorization(LoHiSC). LoHiSC is based on a new colorization network that uses fast fourier convolution(FFC), which is capable of efficiently connecting two distant locations and has a global receptive field. Particularly, our proposed LoHiSC improves FFC by splitting it into two main branches, one is cascaded with low pass spectral filter, and another with high pass spectral filter, for the reason we experimently find that colors are mainly concentrated in the low frequency part, while contours and edges in the high frequency part. Moreover, we propose a frequency domain loss which is beneficial to restore challenging artifacts of grayscale image colorization. Experiments on both synthetic dataset and real-world old photos demonstrate our method improves the stat-of-the-art and achieves compelling colorizing results.
13 September 2015 in Mathematical Problems in Engineering
Recently the state-of-the-art facial age estimation methods are almost originated from solving complicated mathematical optimization problems and thus consume huge quantities of time in the training process. To refrain from such algorithm complexity while maintaining a high estimation accuracy, we propose a multifeature extreme ordinal ranking machine (MFEORM) for facial age estimation. Experimental results clearly demonstrate that the proposed approach can sharply reduce the runtime (even up to nearly one hundred times faster) while achieving comparable or better estimation performances than the state-of-the-art approaches. The inner properties of MFEORM are further explored with more advantages.