A robust automatic micro-expression recognition system would have broad applications in national safety, police interrogation, and clinical diagnosis. Developing such a system requires high quality databases with sufficient training samples which are currently not available. We reviewed the previously developed micro-expression databases and built an improved one (CASME II), with higher temporal resolution (200 fps) and spatial resolution (about 280×340 pixels on facial area). We elicited participants' facial expressions in a well-controlled laboratory environment and proper illumination (such as removing light flickering). Among nearly 3000 facial movements, 247 micro-expressions were selected for the database with action units (AUs) and emotions labeled. For baseline evaluation, LBP-TOP and SVM were employed respectively for feature extraction and classifier with the leave-one-subject-out cross-validation method. The best performance is 63.41% for 5-class classification.
Micro-expressions are short, involuntary facial expressions which reveal hidden emotions. Micro-expressions are important for understanding humans' deceitful behavior. Psychologists have been studying them since the 1960's. Currently the attention is elevated in both academic fields and in media. However, while general facial expression recognition (FER) has been intensively studied for years in computer vision, little research has been done in automatically analyzing microexpressions. The biggest obstacle to date has been the lack of a suitable database. In this paper we present a novel Spontaneous Micro-expression Database SMIC, which includes 164 microexpression video clips elicited from 16 participants. Microexpression detection and recognition performance are provided as baselines. SMIC provides sufficient source material for comprehensive testing of automatic systems for analyzing microexpressions, which has not been possible with any previously published database.
Background Progression of Parkinson’s disease (PD) is characterized by motor deficits, which eventually respond less to dopaminergic therapy and, thus, pose a therapeutic challenge. Deep brain stimulation has proven efficacy, but carries risks and is not possible in all patients. Non-invasive brain stimulation has shown promising results and may provide a therapeutic alternative. Objective To investigate the efficacy of transcranial direct current stimulation (tDCS) in the treatment of PD Design Randomized, double blind, sham-controlled study. Setting Research institution Methods We investigated efficacy of anodal tDCS applied to the motor and prefrontal cortices in 8 sessions over 2.5 weeks. Assessment over a 3-month period included timed tests of gait (primary outcome measure) and bradykinesia in the upper extremities, UPDRS, Serial Reaction Time Task, Beck Depression Inventory, Health Survey and self-assessment of mobility. Results Twenty-five PD patients were investigated, 13 receiving tDCS and 12 sham stimulation. TDCS improved gait by some measures for a short time and improved bradykinesia in both the on- and off-states for longer than 3 months. Changes in UPDRS, reaction time, physical and mental well-being, and self-assessed mobility did not differ between tDCS and sham intervention. Conclusion TDCS of the motor and prefrontal cortices may have therapeutic potential in PD, but better stimulation parameters need to be established to make the technique clinically viable.
Abstract-Micro-expressions (MEs) are rapid, involuntary facial expressions which reveal emotions that people do not intend to show. Studying MEs is valuable as recognizing them has many important applications, particularly in forensic science and psychotherapy. However, analyzing spontaneous MEs is very challenging due to their short duration and low intensity. Automatic ME analysis includes two tasks: ME spotting and ME recognition. For ME spotting, previous studies have focused on posed rather than spontaneous videos. For ME recognition, the performance of previous studies is low. To address these challenges, we make the following contributions: (i) We propose the first method for spotting spontaneous MEs in long videos (by exploiting feature difference contrast). This method is training free and works on arbitrary unseen videos. (ii) We present an advanced ME recognition framework, which outperforms previous work by a large margin on two challenging spontaneous ME databases (SMIC and CASMEII). (iii) We propose the first automatic ME analysis system (MESR), which can spot and recognize MEs from spontaneous video data. Finally, we show our method outperforms humans in the ME recognition task by a large margin, and achieves comparable performance to humans at the very challenging task of spotting and then recognizing spontaneous MEs.
Face anti-spoofing (FAS) plays a vital role in face recognition systems. Most state-of-the-art FAS methods 1) rely on stacked convolutions and expert-designed network, which is weak in describing detailed fine-grained information and easily being ineffective when the environment varies (e.g., different illumination), and 2) prefer to use long sequence as input to extract dynamic features, making them difficult to deploy into scenarios which need quick response. Here we propose a novel frame level FAS method based on Central Difference Convolution (CDC), which is able to capture intrinsic detailed patterns via aggregating both intensity and gradient information. A network built with CDC, called the Central Difference Convolutional Network (CDCN), is able to provide more robust modeling capacity than its counterpart built with vanilla convolution. Furthermore, over a specifically designed CDC search space, Neural Architecture Search (NAS) is utilized to discover a more powerful network structure (CDCN++), which can be assembled with Multiscale Attention Fusion Module (MAFM) for further boosting performance. Comprehensive experiments are performed on six benchmark datasets to show that 1) the proposed method not only achieves superior performance on intra-dataset testing (especially 0.2% ACER in Protocol-1 of OULU-NPU dataset), 2) it also generalizes well on cross-dataset testing (particularly 6.5% HTER from CASIA-MFSD to Replay-Attack datasets). The codes are available at https://github.com/ZitongYu/CDCN.
A B S T R A C T PurposeBiliary cancers (BCs) carry a poor prognosis, but targeting the RAS/RAF/mitogen-activated protein kinase kinase (MEK)/extracellular signal-related kinase (ERK) pathway is of significance. Selumetinib is an inhibitor of MEK1/2, so this trial was designed to determine the safety and efficacy of selumetinib in BC. Patients and MethodsThis was a multi-institutional phase II study of selumetinib at 100 mg given orally twice per day to patients with advanced BC. The primary end point was response rate. All patients were required to provide tissue before enrolling. The levels of phosphorylated ERK (pERK) and AKT (pAKT) were assessed by immunohistochemistry. Tumors were genotyped for the presence of BRAF-and/or RAS-activating mutations. ResultsTwenty-eight eligible patients with a median age of 55.6 years were enrolled. Thirty-nine percent of patients had received one prior systemic therapy. Three patients (12%) had a confirmed objective response. Another 17 patients (68%) experienced stable disease (SD), 14 of whom (56%) experienced prolonged SD (Ͼ 16 weeks). Patients gained an average nonfluid weight of 8.6 pounds. Median progression-free survival was 3.7 months (95% CI, 3.5 to 4.9) and median overall survival was 9.8 months (95% CI, 5.97 to not available). Toxicities were mild, with rash (90%) and xerostomia (54%) being most frequent. Only one patient experienced grade 4 toxicity (fatigue). All patients had tissue available for analysis. No BRAF V600E mutations were found. Two patients with short-lived SD had KRAS mutations. Absence of pERK staining was associated with lack of response. ConclusionSelumetinib displays interesting activity and acceptable tolerability in patients with metastatic BC. Our results warrant further evaluation of selumetinib in patients with metastatic BC.
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.