Search results

Search-based structured prediction methods have shown promising successes in both computer vision and natural language processing recently. However, most existing search-based approaches lead to a complex multi-stage learning process, which is ill-suited for scene labeling probelms with a high-dimensional output space. In this paper, a stacked learning to search method is proposed to address scene labeling tasks. We design a simplified search process consisting of a sequence of ranking fucntions, which are learned based on a stacked learning strategy to prevent over-fitting. Our method is able to encode rich prior knowledge by incorporating a variety of local and global scene features. In addition, we estimate a labeling confidence map to further improve the search efficiency from two aspects: first, it constrains the search space more effectively by pruning out low-quality solutions based on confidence scores and second, we employ the confidence map as an additional ranking feature to improve its prediction performance and thus reduce the search steps. Our approach is evaluated on both semantic segmentation and geometric labeling tasks, including the Stanford Background, Sift Flow, Geometric Context, and NYUv2 RGB-D data set. The competitive results demonstrate that our stacked learning to search method provides and effective alternative paradigm for scene labeling. ; This work was supported by the National Natural Science Foundation of China under Grant 61571026. The work of F. Cheng was supported by the China Scholarship Council. The work of X. He was supported in part by the Australian Government through the Department of Communications and in part by the Australian Research Council through the ICT Center of Excellence Program

Contour completion plays an important role in visual perception, where the goal is to group fragmented low-level edge elements into perceptually coherent and salient contours. Most existing methods for contour completion have focused on pixelwise detection accuracy. In contrast, fewer methods have addressed the global contour closure effect, despite psychological evidences for its importance. This paper proposes a purely contour-based higher order CRF model to achieve contour closure, through local connectedness approximation. This leads to a simplified problem structure, where our higher order inference problem can be transformed into an integer linear program and be solved efficiently. Compared with the methods based on the same bottom-up edge detector, our method achieves a superior contour grouping ability (measured by Rand index), a comparable precision-recall performance, and more visually pleasing results. Our results suggest that contour closure can be effectively achieved in contour domain, in contrast to a popular view that segmentation is essential for this purpose. ; This work was supported by the NICTA Research Center of Excellence Funded by the Australian Government through the Australian Research Council. The work H. Li was supported by the Australia Research Council (ARC) via an ARC Discovery Project.

The visual prosthesis (or "bionic eye") has become a reality but provides a low resolution view of the world. Simulating prosthetic vision in normal-vision observers, previous studies report good face recognition ability using tasks that allow recognition to be achieved on the basis of information that survives low resolution well, including basic category (sex, age) and extra-face information (hairstyle, glasses). Here, we test within-category individuation for face-only information (e.g., distinguishing between multiple Caucasian young men with hair covered). Under these conditions, recognition was poor (although above chance) even for a simulated 40 × 40 array with all phosphene elements assumed functional, a resolution above the upper end of current-generation prosthetic implants. This indicates that a significant challenge is to develop methods to improve face identity recognition. Inspired by "bionic ear" improvements achieved by altering signal input to match high-level perceptual (speech) requirements, we test a high-level perceptual enhancement of face images, namely face caricaturing (exaggerating identity information away from an average face). Results show caricaturing improved identity recognition in memory and/or perception (degree by which two faces look dissimilar) down to a resolution of 32 × 32 with 30% phosphene dropout. Findings imply caricaturing may offer benefits for patients at resolutions realistic for some current-generation or in-development implants. ; We would like to thanks our funding sources: Australian Research Council (ARC) DP150100684; ARC Centre of Excellence in Cognition and its Disorders (project number CE110001021); Australian Government as represented by the Department of Broadband, Communications, and the Digital Economy; ARC Information and Communication Technologies Centre of Excellence Program; and ARC Special Research Initiative in Bionic Vision Science and Technology grant to Bionic Vision Australia.

BACKGROUND: Concussion, or mild traumatic brain injury, is a major public health concern affecting 42 million individuals globally each year. However, little is known regarding concussion risk factors across all concussion settings as most concussion research has focused on only sport-related or military-related concussive injuries. METHODS: The current study is part of the Concussion, Assessment, Research, and Education (CARE) Consortium, a multi-site investigation on the natural history of concussion. Cadets at three participating service academies completed annual baseline assessments, which included demographics, medical history, and concussion history, along with the Sport Concussion Assessment Tool (SCAT) symptom checklist and Brief Symptom Inventory (BSI-18). Clinical and research staff recorded the date and injury setting at time of concussion. Generalized mixed models estimated concussion risk with service academy as a random effect. Since concussion was a rare event, the odds ratios were assumed to approximate relative risk. RESULTS: Beginning in 2014, 10,604 (n = 2421, 22.83% female) cadets enrolled over 3 years. A total of 738 (6.96%) cadets experienced a concussion, 301 (2.84%) concussed cadets were female. Female sex and previous concussion were the most consistent estimators of concussion risk across all concussion settings. Compared to males, females had 2.02 (95% CI: 1.70-2.40) times the risk of a concussion regardless of injury setting, and greater relative risk when the concussion occurred during sport (Odds Ratio (OR): 1.38 95% CI: 1.07-1.78). Previous concussion was associated with 1.98 (95% CI: 1.65-2.37) times increased risk for any incident concussion, and the magnitude was relatively stable across all concussion settings (OR: 1.73 to 2.01). Freshman status was also associated with increased overall concussion risk, but was driven by increased risk for academy training-related concussions (OR: 8.17 95% CI: 5.87-11.37). Medical history of headaches in the past 3 months, diagnosed ADD/ADHD, and BSI-18 Somatization symptoms increased overall concussion risk. CONCLUSIONS: Various demographic and medical history factors are associated with increased concussion risk. While certain factors (e.g. sex and previous concussion) are consistently associated with increased concussion risk, regardless of concussion injury setting, other factors significantly influence concussion risk within specific injury settings. Further research is required to determine whether these risk factors may aid in concussion risk reduction or prevention.

CONTEXT: Assessments of the duration of concussion recovery have primarily been limited to sport-related concussions and male contact sports. Furthermore, whereas durations of symptoms and return-to-activity (RTA) protocols encompass total recovery, the trajectory of each duration has not been examined separately. OBJECTIVE: To identify individual (eg, demographics, medical history), initial concussion injury (eg, symptoms), and external (eg, site) factors associated with symptom duration and RTA-protocol duration after concussion. DESIGN: Cohort study. SETTING: Three US military service academies. PATIENTS OR OTHER PARTICIPANTS: A total of 10 604 cadets at participating US military service academies enrolled in the study and completed a baseline evaluation and up to 5 postinjury evaluations. A total of 726 cadets (451 men, 275 women) sustained concussions during the study period. MAIN OUTCOME MEASURE(S): Number of days from injury (1) until the participant became asymptomatic and (2) to complete the RTA protocol. RESULTS: Varsity athlete cadets took less time than nonvarsity cadets to become asymptomatic (hazard ratio [HR] = 1.75, 95% confidence interval = 1.38, 2.23). Cadets who reported less symptom severity on the Sport Concussion Assessment Tool, third edition (SCAT3), within 48 hours of concussion had 1.45 to 3.77 times shorter symptom-recovery durations than those with more symptom severity. Similar to symptom duration, varsity status was associated with a shorter RTA-protocol duration (HR = 1.74, 95% confidence interval = 1.34, 2.25), and less symptom severity on the SCAT3 was associated with a shorter RTA-protocol duration (HR range = 1.31 to 1.47). The academy that the cadet attended was associated with the RTA-protocol duration (P < .05). CONCLUSIONS: The initial total number of symptoms reported and varsity athlete status were strongly associated with symptom and RTA-protocol durations. These findings suggested that external (varsity status and academy) and injury (symptom burden) factors ...