In this paper, we propose a CNN-based framework for online MOT. This framework utilizes the merits of single object trackers in adapting appearance models and searching for target in the next frame. Simply applying single object tracker for MOT will encounter the problem in computational efficiency and drifted results caused by occlusion. Our framework achieves computational efficiency by sharing features and using ROI-Pooling to obtain individual features for each target. Some online learned target-specific CNN layers are used for adapting the appearance model for each target. In the framework, we introduce spatialtemporal attention mechanism (STAM) to handle the drift caused by occlusion and interaction among targets. The visibility map of the target is learned and used for inferring the spatial attention map. The spatial attention map is then applied to weight the features. Besides, the occlusion status can be estimated from the visibility map, which controls the online updating process via weighted loss on training samples with different occlusion statuses in different frames. It can be considered as temporal attention mechanism. The proposed algorithm achieves 34.3% and 46.0% in MOTA on challenging MOT15 and MOT16 benchmark dataset respectively.

Recognizing visual relationships subject-predicate-object among any pair of localized objects is pivotal for image understanding. Previous studies have shown remarkable progress in exploiting linguistic priors or external textual information to improve the performance. In this work, we investigate an orthogonal perspective based on feature interactions. We show that by encouraging deep message propagation and interactions between local object features and global predicate features, one can achieve compelling performance in recognizing complex relationships without using any linguistic priors. To this end, we present two new pooling cells to encourage feature interactions: (i) Contrastive ROI Pooling Cell, which has a unique deROI pooling that inversely pools local object features to the corresponding area of global predicate features. (ii) Pyramid ROI Pooling Cell, which broadcasts global predicate features to reinforce local object features. The two cells constitute a Spatiality-Context-Appearance Module (SCA-M), which can be further stacked consecutively to form our final Zoom-Net. We further shed light on how one could resolve ambiguous and noisy object and predicate annotations by Intra-Hierarchical trees (IH-tree). Extensive experiments conducted on Visual Genome dataset [1] demonstrate the effectiveness of our feature-oriented approach compared to state-of-theart methods (Acc@1 11.42% from 8.16% [2]) that depend on explicit modeling of linguistic interactions. We further show that SCA-M can be incorporated seamlessly into existing approaches [2] to improve the performance by a large margin. The source code will be released on https://github.com/gjyin91/ZoomNet.

Background: Protein remote homology detection and fold recognition are central problems in bioinformatics. Currently, discriminative methods based on support vector machine (SVM) are the most effective and accurate methods for solving these problems. A key step to improve the performance of the SVM-based methods is to find a suitable representation of protein sequences.

Numerous calc-alkaline granitoid intrusions in the eastern Kunlun Orogen provide a valuable opportunity to constrain the evolution of the orogen. The age and genesis of these intrusions, however, remain poorly understood. The granitoid intrusions near the Balong region, eastern Kunlun Orogen, consist of granodiorite, diorite and syenogranite. The granodiorite contains crystallized segregations, abundant mafic microgranular enclaves (MMEs) and small quartz diorite stocks. In situ zircon U–Pb dating reveals that the granodiorites and quartz diorites were emplaced between 263 and 241 Ma, whereas the syenogranite was produced at c. 231 Ma. The granodiorite and quartz diorite have a calc-alkaline affinity and are metaluminous and Na-rich, with slightly enriched Sr–Nd isotope compositions. The granodiorite is characterized by fractionated REE patterns, whereas the quartz diorite displays a relatively flat REE pattern. The MMEs are consistent with the granodiorite in terms of incompatible elements and Sr–Nd isotope composition. Compared to the granodiorite and diorite, the syenogranite has higher SiO2, K, Rb, Th and Sr contents and a lower Rb/Sr ratio. The results presented here, when combined with regional geological data, indicate that the granodiorite and quartz diorite were derived from dehydration melting of mafic lower crustal rocks during the N-directed subduction of the Anyemaqen ocean lithosphere in Late Permian–Middle Triassic times, whereas the syenogranite was produced at a higher crustal level in a syn-collisional setting compared to the granodiorite.