We propose a novel visual tracking algorithm based on the representations from a discriminatively trained Convolutional Neural Network (CNN). Our algorithm pretrains a CNN using a large set of videos with tracking groundtruths to obtain a generic target representation. Our network is composed of shared layers and multiple branches of domain-specific layers, where domains correspond to individual training sequences and each branch is responsible for binary classification to identify the target in each domain. We train the network with respect to each domain iteratively to obtain generic target representations in the shared layers. When tracking a target in a new sequence, we construct a new network by combining the shared layers in the pretrained CNN with a new binary classification layer, which is updated online. Online tracking is performed by evaluating the candidate windows randomly sampled around the previous target state. The proposed algorithm illustrates outstanding performance compared with stateof-the-art methods in existing tracking benchmarks.

No abstract

The Visual Object Tracking challenge 2014, VOT2014, aims at comparing short-term single-object visual trackers that do not apply pre-learned models of object appearance. Results of 38 trackers are presented. The number of tested trackers makes VOT 2014 the largest benchmark on short-term tracking to date. For each participating tracker, a short description is provided in the appendix. Features of the VOT2014 challenge that go beyond its VOT2013 predecessor are introduced: (i) a new VOT2014 dataset with full annotation of targets by rotated bounding boxes and per-frame attribute, (ii) extensions of the VOT2013 evaluation methodology, (iii) a new unit for tracking speed assessment less dependent on the hardware and (iv) the VOT2014 evaluation toolkit that significantly speeds up execution of experiments. The dataset, the evaluation kit as well as the results are publicly available at the challenge website (http://​votchallenge.​net)

We propose Dual Attention Networks (DANs) which jointly leverage visual and textual attention mechanisms to capture fine-grained interplay between vision and language. DANs attend to specific regions in images and words in text through multiple steps and gather essential information from both modalities. Based on this framework, we introduce two types of DANs for multimodal reasoning and matching, respectively. The reasoning model allows visual and textual attentions to steer each other during collaborative inference, which is useful for tasks such as Visual Question Answering (VQA). In addition, the matching model exploits the two attention mechanisms to estimate the similarity between images and sentences by focusing on their shared semantics. Our extensive experiments validate the effectiveness of DANs in combining vision and language, achieving the state-of-the-art performance on public benchmarks for VQA and image-text matching.

Background Mammography is the current standard for breast cancer screening. This study aimed to develop an artificial intelligence (AI) algorithm for diagnosis of breast cancer in mammography, and explore whether it could benefit radiologists by improving accuracy of diagnosis. Methods In this retrospective study, an AI algorithm was developed and validated with 170 230 mammography examinations collected from five institutions in South Korea, the USA, and the UK, including 36 468 cancer positive confirmed by biopsy, 59 544 benign confirmed by biopsy (8827 mammograms) or follow-up imaging (50 717 mammograms), and 74 218 normal. For the multicentre, observer-blinded, reader study, 320 mammograms (160 cancer positive, 64 benign, 96 normal) were independently obtained from two institutions. 14 radiologists participated as readers and assessed each mammogram in terms of likelihood of malignancy (LOM), location of malignancy, and necessity to recall the patient, first without and then with assistance of the AI algorithm. The performance of AI and radiologists was evaluated in terms of LOM-based area under the receiver operating characteristic curve (AUROC) and recall-based sensitivity and specificity. Findings The AI standalone performance was AUROC 0•959 (95% CI 0•952-0•966) overall, and 0•970 (0•963-0•978) in the South Korea dataset, 0•953 (0•938-0•968) in the USA dataset, and 0•938 (0•918-0•958) in the UK dataset. In the reader study, the performance level of AI was 0•940 (0•915-0•965), significantly higher than that of the radiologists without AI assistance (0•810, 95% CI 0•770-0•850; p<0•0001). With the assistance of AI, radiologists' performance was improved to 0•881 (0•850-0•911; p<0•0001). AI was more sensitive to detect cancers with mass (53 [90%] vs 46 [78%] of 59 cancers detected; p=0•044) or distortion or asymmetry (18 [90%] vs ten [50%] of 20 cancers detected; p=0•023) than radiologists. AI was better in detection of T1 cancers (73 [91%] vs 59 [74%] of 80; p=0•0039) or node-negative cancers (104 [87%] vs 88 [74%] of 119; p=0•0025) than radiologists. Interpretation The AI algorithm developed with large-scale mammography data showed better diagnostic performance in breast cancer detection compared with radiologists. The significant improvement in radiologists' performance when aided by AI supports application of AI to mammograms as a diagnostic support tool.