We propose a network for Congested Scene Recognition called CSRNet to provide a data-driven and deep learning method that can understand highly congested scenes and perform accurate count estimation as well as present highquality density maps. The proposed CSRNet is composed of two major components: a convolutional neural network (CNN) as the front-end for 2D feature extraction and a dilated CNN for the back-end, which uses dilated kernels to deliver larger reception fields and to replace pooling operations. CSRNet is an easy-trained model because of its pure convolutional structure. We demonstrate CSRNet on four datasets (ShanghaiTech dataset, the UCF CC 50 dataset, the WorldEXPO'10 dataset, and the UCSD dataset) and we deliver the state-of-the-art performance. In the Shang-haiTech Part B dataset, CSRNet achieves 47.3% lower Mean Absolute Error (MAE) than the previous state-of-theart method. We extend the targeted applications for counting other objects, such as the vehicle in TRANCOS dataset. Results show that CSRNet significantly improves the output quality with 15.4% lower MAE than the previous state-ofthe-art approach.

The Visual Object Tracking challenge VOT2018 is the sixth annual tracker benchmarking activity organized by the VOT initiative. Results of over eighty trackers are presented; many are state-of-the-art trackers published at major computer vision conferences or in journals in the recent years. The evaluation included the standard VOT and other popular methodologies for short-term tracking analysis and a "real-time" experiment simulating a situation where a tracker processes images as if provided by a continuously running sensor. A long-term tracking subchallenge has been introduced to the set of standard VOT sub-challenges. The new subchallenge focuses on long-term tracking properties, namely coping with target disappearance and reappearance. A new dataset has been compiled and a performance evaluation methodology that focuses on long-term tracking capabilities has been adopted. The VOT toolkit has been updated to support both standard short-term and the new longterm tracking subchallenges. Performance of the tested trackers typically by far exceeds standard baselines. The source code for most of the trackers is publicly available from the VOT page. The dataset, the evaluation kit and the results are publicly available at the challenge website 60 .

In this paper, we propose a novel end-to-end trainable Video Question Answering (VideoQA) framework with three major components: 1) a new heterogeneous memory which can effectively learn global context information from appearance and motion features; 2) a redesigned question memory which helps understand the complex semantics of question and highlights queried subjects; and 3) a new multimodal fusion layer which performs multi-step reasoning by attending to relevant visual and textual hints with selfupdated attention. Our VideoQA model firstly generates the global context-aware visual and textual features respectively by interacting current inputs with memory contents. After that, it makes the attentional fusion of the multimodal visual and textual representations to infer the correct answer. Multiple cycles of reasoning can be made to iteratively refine attention weights of the multimodal data and improve the final representation of the QA pair. Experimental results demonstrate our approach achieves state-of-theart performance on four VideoQA benchmark datasets.

Recent algorithms in convolutional neural networks (CNN) considerably advance the fine-grained image classification, which aims to differentiate subtle differences among subordinate classes. However, previous studies have rarely focused on learning a fined-grained and structured feature representation that is able to locate similar images at different levels of relevance, e.g., discovering cars from the same make or the same model, both of which require high precision. In this paper, we propose two main contributions to tackle this problem. 1) A multitask learning framework is designed to effectively learn fine-grained feature representations by jointly optimizing both classification and similarity constraints. 2) To model the multi-level relevance, label structures such as hierarchy or shared attributes are seamlessly embedded into the framework by generalizing the triplet loss. Extensive and thorough experiments have been conducted on three finegrained datasets, i.e., the Stanford car, the Car-333, and the food datasets, which contain either hierarchical labels or shared attributes. Our proposed method has achieved very competitive performance, i.e., among state-of-the-art classification accuracy when not using parts. More importantly, it significantly outperforms previous fine-grained feature representations for image retrieval at different levels of relevance.

We recently described the cikA (circadian input kinase A) gene, whose product supplies environmental information to the circadian oscillator in the cyanobacterium Synechococcus elongatus PCC 7942. CikA possesses three distinct domains: a GAF, a histidine protein kinase (HPK), and a receiver domain similar to those of the response regulator family. To determine how CikA functions in providing circadian input, we constructed modified alleles to tag and truncate the protein, allowing analysis of each domain individually. CikA covalently bound bilin chromophores in vitro, even though it lacks the expected ligand residues, and the GAF domain influenced but did not entirely account for this function. Full-length CikA and truncated variants that carry the HPK domain showed autophosphorylation activity. Deletion of the GAF domain or the N-terminal region adjacent to GAF dramatically reduced autophosphorylation, whereas elimination of the receiver domain increased activity 10-fold. Assays to test phosphorelay from the HPK to the cryptic receiver domain, which lacks the conserved aspartyl residue that serves as a phosphoryl acceptor in response regulators, were negative. We propose that the cryptic receiver is a regulatory domain that interacts with an unknown protein partner to modulate the autokinase activity of CikA but does not work as bona fide receiver domain in a phosphorelay.

HighlightRice transcription factor OsNF-YB1 is specifically expressed in the aleurone layer of developing endosperm and forms protein complexes consisting of OsNF-YB1, OsNF-YC and ERF to regulate grain filling and endosperm development.

Background: Ocular and childhood myasthenia gravis (MG) cases seem relatively more common in Oriental than in Caucasian populations, but there have been no comprehensive serological studies on patients from mainland China. Methods: 391 unselected patients with MG attending Tongji Hospital in WuHan (the largest hospital in the province of HuBei, China) were studied during a 15-month period; most had already received treatment for their condition. Results: The male to female ratio was 0.8. 50% of the patients were children (,15 years), and age at onset showed a single peak at between 5 and 10 years of age. 64% of the children and 66% of the adults were positive for acetylcholine receptor (AChR) antibodies but the antibody titres were lower than in similar Caucasian studies, although this was partly due to the high incidence of ocular MG. Of the 43 patients with generalised MG without AChR antibodies, only 1 had muscle-specific kinase antibodies (2.5%) and 2 had voltage-gated calcium channel antibodies indicating probable Lambert-Eaton myasthenic syndrome. 75% of the children, compared with only 28% of the adults, had ocular MG. Thymoma was evident by MRI in 1.5% of children and in 20% of adults. Despite most patients having received prednisone, very few had obtained full clinical remission. Conclusion: This study emphasises the frequency of early childhood onset with ocular symptoms and shows that many of these patients have AChR antibodies. By contrast, patients presenting in later age seem to be very uncommon in comparison with recent studies in Caucasian populations.

Automatic analysis of histopathological images has been widely utilized leveraging computational image-processing methods and modern machine learning techniques. Both computer-aided diagnosis (CAD) and content-based image-retrieval (CBIR) systems have been successfully developed for diagnosis, disease detection, and decision support in this area. Recently, with the ever-increasing amount of annotated medical data, large-scale and data-driven methods have emerged to offer a promise of bridging the semantic gap between images and diagnostic information. In this paper, we focus on developing scalable image-retrieval techniques to cope intelligently with massive histopathological images. Specifically, we present a supervised kernel hashing technique which leverages a small amount of supervised information in learning to compress a 10 000-dimensional image feature vector into only tens of binary bits with the informative signatures preserved. These binary codes are then indexed into a hash table that enables real-time retrieval of images in a large database. Critically, the supervised information is employed to bridge the semantic gap between low-level image features and high-level diagnostic information. We build a scalable image-retrieval framework based on the supervised hashing technique and validate its performance on several thousand histopathological images acquired from breast microscopic tissues. Extensive evaluations are carried out in terms of image classification (i.e., benign versus actionable categorization) and retrieval tests. Our framework achieves about 88.1% classification accuracy as well as promising time efficiency. For example, the framework can execute around 800 queries in only 0.01 s, comparing favorably with other commonly used dimensionality reduction and feature selection methods.