In this paper, we present a novel end-to-end learning neural network, i.e., MATNet, for zero-shot video object segmentation (ZVOS). Motivated by the human visual attention behavior, MATNet leverages motion cues as a bottom-up signal to guide the perception of object appearance. To achieve this, an asymmetric attention block, named Motion-Attentive Transition (MAT), is proposed within a two-stream encoder network to firstly identify moving regions and then attend appearance learning to capture the full extent of objects. Putting MATs in different convolutional layers, our encoder becomes deeply interleaved, allowing for close hierarchical interactions between object apperance and motion. Such a biologically-inspired design is proven to be superb to conventional two-stream structures, which treat motion and appearance independently in separate streams and often suffer severe overfitting to object appearance. Moreover, we introduce a bridge network to modulate multi-scale spatiotemporal features into more compact, discriminative and scale-sensitive representations, which are subsequently fed into a boundary-aware decoder network to produce accurate segmentation with crisp boundaries. We perform extensive quantitative and qualitative experiments on four challenging public benchmarks, i.e., DAVIS16, DAVIS17, FBMS and YouTube-Objects. Results show that our method achieves compelling performance against current state-of-the-art ZVOS methods. To further demonstrate the generalization ability of our spatiotemporal learning framework, we extend MATNet to another relevant task: dynamic visual attention prediction (DVAP). The experiments on two popular datasets (i.e., Hollywood-2 and UCF-Sports) further verify the superiority of our model. Our implementations have been made publicly available at https://github.com/tfzhou/MATNet.

Acquiring sufficient ground-truth supervision to train deep visual models has been a bottleneck over the years due to the data-hungry nature of deep learning. This is exacerbated in some structured prediction tasks, such as semantic segmentation, which require pixel-level annotations. This work addresses weakly supervised semantic segmentation (WSSS), with the goal of bridging the gap between image-level annotations and pixel-level segmentation. To achieve this, we propose, for the first time, a novel group-wise learning framework for WSSS. The framework explicitly encodes semantic dependencies in a group of images to discover rich semantic context for estimating more reliable pseudo ground-truths, which are subsequently employed to train more effective segmentation models. In particular, we solve the group-wise learning within a graph neural network (GNN), wherein input images are represented as graph nodes, and the underlying relations between a pair of images are characterized by graph edges. We then formulate semantic mining as an iterative reasoning process which propagates the common semantics shared by a group of images to enrich node representations. Moreover, in order to prevent the model from paying excessive attention to common semantics, we further propose a graph dropout layer to encourage the graph model to capture more accurate and complete object responses. With the above efforts, our model lays the foundation for more sophisticated and flexible group-wise semantic mining. We conduct comprehensive experiments on the popular PASCAL VOC 2012 and COCO benchmarks, and our model yields state-of-the-art performance. In addition, our model shows promising performance in weakly supervised object localization (WSOL) on the CUB-200-2011 dataset, demonstrating strong generalizability. Our code is available at: https://github.com/Lixy1997/Group-WSSS .

Accurate cellular traffic prediction is conducive to managing communication networks, but challenging, due to dynamic temporal variations and complicated spatial correlations. In this letter, a novel Spatial-Temporal Transformer (ST-Tran) is proposed to explore spatial and temporal sequence information simultaneously. A temporal transformer block is designed to learn temporal features of every grid in a communication network by modeling its traffic flows during both recent and periodic time intervals. Meanwhile, the spatial characteristics of every grid are cooperated with the information of its related grids to generate spatial predictions in the spatial transformer block. An output block is further proposed to merge the temporal and spatial information into a final prediction. Experimental results on a large real-world dataset verify the effectiveness of the ST-Tran. The source code is available at https://github.com/liuqingyao11/ST-Tran .

In order to detect hearing loss more efficiently and accurately, this study proposed a new method based on fractional Fourier transform (FRFT). Three-dimensional volumetric magnetic resonance images were obtained from 15 patients with left-sided hearing loss (LHL), 20 healthy controls (HC), and 14 patients with right-sided hearing loss (RHL). Twenty-five FRFT spectrums were reduced by principal component analysis with thresholds of 90%, 95%, and 98%, respectively. The classifier is the single-hidden-layer feed-forward neural network (SFN) trained by the Levenberg–Marquardt algorithm. The results showed that the accuracies of all three classes are higher than 95%. In all, our method is promising and may raise interest from other researchers.