This work presents a first evaluation of using spatio-temporal receptive fields from a recently proposed time-causal spatiotemporal scale-space framework as primitives for video analysis. We propose a new family of video descriptors based on regional statistics of spatio-temporal receptive field responses and evaluate this approach on the problem of dynamic texture recognition. Our approach generalises a previously used method, based on joint histograms of receptive field responses, from the spatial to the spatio-temporal domain and from object recognition to dynamic texture recognition. The time-recursive formulation enables computationally efficient time-causal recognition. The experimental evaluation demonstrates competitive performance compared to state of the art. In particular, it is shown that binary versions of our dynamic texture descriptors achieve improved performance compared to a large range of similar methods using different primitives either handcrafted or learned from data. Further, our qualitative and quantitative investigation into parameter choices and the use of different sets of receptive fields highlights the robustness and flexibility of our approach. Together, these results support the descriptive power of this family of time-causal spatio-temporal receptive fields, validate our approach for dynamic texture recognition and point towards the possibility of designing a range of video analysis methods based on these new time-causal spatio-temporal primitives.
Abstract. This work presents an evaluation of using time-causal scalespace filters as primitives for video analysis. For this purpose, we present a new family of video descriptors based on regional statistics of spatiotemporal scale-space filter responses and evaluate this approach on the problem of dynamic texture recognition. Our approach generalises a previously used method, based on joint histograms of receptive field responses, from the spatial to the spatio-temporal domain. We evaluate one member in this family, constituting a joint binary histogram, on two widely used dynamic texture databases. The experimental evaluation shows competitive performance compared to previous methods for dynamic texture recognition, especially on the more complex DynTex database. These results support the descriptive power of time-causal spatio-temporal scale-space filters as primitives for video analysis.
The ability to handle large scale variations is crucial for many real-world visual tasks. A straightforward approach for handling scale in a deep network is to process an image at several scales simultaneously in a set of scale channels. Scale invariance can then, in principle, be achieved by using weight sharing between the scale channels together with max or average pooling over the outputs from the scale channels. The ability of such scale-channel networks to generalise to scales not present in the training set over significant scale ranges has, however, not previously been explored. In this paper, we present a systematic study of this methodology by implementing different types of scale-channel networks and evaluating their ability to generalise to previously unseen scales. We develop a formalism for analysing the covariance and invariance properties of scale-channel networks, including exploring their relations to scale-space theory, and exploring how different design choices, unique to scaling transformations, affect the overall performance of scale-channel networks. We first show that two previously proposed scale-channel network designs, in one case, generalise no better than a standard CNN to scales not present in the training set, and in the second case, have limited scale generalisation ability. We explain theoretically and demonstrate experimentally why generalisation fails or is limited in these cases. We then propose a new type of foveated scale-channel architecture, where the scale channels process increasingly larger parts of the image with decreasing resolution. This new type of scale-channel network is shown to generalise extremely well, provided sufficient image resolution and the absence of boundary effects. Our proposed FovMax and FovAvg networks perform almost identically over a scale range of 8, also when training on single-scale training data, and do also give improved performance when learning from data sets with large scale variations in the small sample regime.
No abstract
Background National lead time goals have been implemented across Sweden to standardize and improve cancer patient care. However, the prognostic impact of lead times has not yet been studied in patients with colorectal cancer and peritoneal metastases scheduled for cytoreductive surgery and hyperthermic intraperitoneal chemotherapy (CRS + HIPEC). Aim To study the correlation between lead times and overall survival and operability. Methods One hundred forty-eight patients with peritoneal metastases originating from colorectal cancer and scheduled for CRS + HIPEC from June 2012 to December 2019 were identified using a HIPEC register at Uppsala University Hospital. Data were collected from medical records concerning operability, overall survival, recurrence and time from diagnosis, and decision to operate to the date of surgery. Patients who had neoadjuvant therapy or no malignant cells in the resected specimens were excluded. Statistical calculations were made with the chi-squared test, Cox regression analysis, and log-rank test. Results The median age was 66 years (27–82). Ninety-five were women and 53 were men. One hundred six underwent CRS + HIPEC, 13 CRS only, and 29 were inoperable (open-close). No difference in overall survival was seen when comparing patients with lead times ≤ 34 days and ≥ 35 days from the decision to operate at the multidisciplinary conference to the surgery but there was a higher frequency of open-close (p = 0.023) in the group with longer lead time. Factors that impacted overall survival were open-close (p < 0.001), liver metastases (p = 0.003), and peritoneal cancer index score ≥ 20 (p < 0.001). Conclusion A long lead time from multidisciplinary conference to surgery has no direct impact on overall survival but can result in more cases of inoperability. In a larger cohort, this might translate into decreased survival, and efforts should therefore be made to complete preoperative work up as soon as possible and reduce overall time span. Important factors for survival are related to patient selection and extent of disease.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.