ERNet: An Efficient and Reliable Human-Object Interaction Detection Network.

Human-Object Interaction (HOI) detection recognizes how persons interact with objects, which is advantageous in autonomous systems such as self-driving vehicles and collaborative robots. However, current HOI detectors are often plagued by model inefficiency and unreliability when making a prediction, which consequently limits its potential for real-world scenarios. In this paper, we address these challenges by proposing ERNet, an end-to-end trainable convolutional-transformer network for HOI detection. The proposed model employs an efficient multi-scale deformable attention to effectively capture vital HOI features. We also put forward a novel detection attention module to adaptively generate semantically rich instance and interaction tokens. These tokens undergo pre-emptive detections to produce initial region and vector proposals that also serve as queries which enhances the feature refinement process in the transformer decoders. Several impactful enhancements are also applied to improve the HOI representation learning. Additionally, we utilize a predictive uncertainty estimation framework in the instance and interaction classification heads to quantify the uncertainty behind each prediction. By doing so, we can accurately and reliably predict HOIs even under challenging scenarios. Experiment results on the HICO-Det, V-COCO, and HOI-A datasets demonstrate that the proposed model achieves state-of-the-art performance in detection accuracy and training efficiency. Codes are publicly available at https://github.com/Monash-CyPhi-AI-Research-Lab/ernet.

Doing More with Moiré Pattern Detection in Digital Photos.

Detecting moiré patterns in digital photographs is meaningful as it provides priors towards image quality evaluation and demoiréing tasks. In this paper, we present a simple yet efficient framework to extract moiré edge maps from images with moiré patterns. The framework includes a strategy for training triplet (natural image, moiré layer, and their synthetic mixture) generation, and a Moiré Pattern Detection Neural Network (MoireDet) for moiré edge map estimation. This strategy ensures consistent pixel-level alignments during training, accommodating characteristics of a diverse set of camera-captured screen images and real-world moiré patterns from natural images. The design of three encoders in MoireDet exploits both high-level contextual and low-level structural features of various moiré patterns. Through comprehensive experiments, we demonstrate the advantages of MoireDet: better identification precision of moiré images on two datasets, and a marked improvement over state-of-the-art demoiréing methods.

Spatio-Temporal Point Process for Multiple Object Tracking.

Multiple object tracking (MOT) focuses on modeling the relationship of detected objects among consecutive frames and merge them into different trajectories. MOT remains a challenging task as noisy and confusing detection results often hinder the final performance. Furthermore, most existing research are focusing on improving detection algorithms and association strategies. As such, we propose a novel framework that can effectively predict and mask-out the noisy and confusing detection results before associating the objects into trajectories. In particular, we formulate such "bad" detection results as a sequence of events and adopt the spatio-temporal point process to model such events. Traditionally, the occurrence rate in a point process is characterized by an explicitly defined intensity function, which depends on the prior knowledge of some specific tasks. Thus, designing a proper model is expensive and time-consuming, with also limited ability to generalize well. To tackle this problem, we adopt the convolutional recurrent neural network (conv-RNN) to instantiate the point process, where its intensity function is automatically modeled by the training data. Furthermore, we show that our method captures both temporal and spatial evolution, which is essential in modeling events for MOT. Experimental results demonstrate notable improvements in addressing noisy and confusing detection results in MOT data sets. An improved state-of-the-art performance is achieved by incorporating our baseline MOT algorithm with the spatio-temporal point process model.

MLife: a lite framework for machine learning lifecycle initialization.

Machine learning (ML) lifecycle is a cyclic process to build an efficient ML system. Though a lot of commercial and community (non-commercial) frameworks have been proposed to streamline the major stages in the ML lifecycle, they are normally overqualified and insufficient for an ML system in its nascent phase. Driven by real-world experience in building and maintaining ML systems, we find that it is more efficient to initialize the major stages of ML lifecycle first for trial and error, followed by the extension of specific stages to acclimatize towards more complex scenarios. For this, we introduce a simple yet flexible framework, MLife, for fast ML lifecycle initialization. This is built on the fact that data flow in MLife is in a closed loop driven by bad cases, especially those which impact ML model performance the most but also provide the most value for further ML model development-a key factor towards enabling enterprises to fast track their ML capabilities. Better yet, MLife is also flexible enough to be easily extensible to more complex scenarios for future maintenance. For this, we introduce two real-world use cases to demonstrate that MLife is particularly suitable for ML systems in their early phases.

Design and Implementation of Fast Spoken Foul Language Recognition with Different End-to-End Deep Neural Network Architectures.

Given the excessive foul language identified in audio and video files and the detrimental consequences to an individual's character and behaviour, content censorship is crucial to filter profanities from young viewers with higher exposure to uncensored content. Although manual detection and censorship were implemented, the methods proved tedious. Inevitably, misidentifications involving foul language owing to human weariness and the low performance in human visual systems concerning long screening time occurred. As such, this paper proposed an intelligent system for foul language censorship through a mechanized and strong detection method using advanced deep Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) through Long Short-Term Memory (LSTM) cells. Data on foul language were collected, annotated, augmented, and analysed for the development and evaluation of both CNN and RNN configurations. Hence, the results indicated the feasibility of the suggested systems by reporting a high volume of curse word identifications with only 2.53% to 5.92% of False Negative Rate (FNR). The proposed system outperformed state-of-the-art pre-trained neural networks on the novel foul language dataset and proved to reduce the computational cost with minimal trainable parameters.

Group Reidentification with Multigrained Matching and Integration.

The task of reidentifying groups of people under different camera views is an important yet less-studied problem. Group reidentification (Re-ID) is a very challenging task since it is not only adversely affected by common issues in traditional single-object Re-ID problems, such as viewpoint and human pose variations, but also suffers from changes in group layout and group membership. In this paper, we propose a novel concept of group granularity by characterizing a group image by multigrained objects: individual people and subgroups of two and three people within a group. To achieve robust group Re-ID, we first introduce multigrained representations which can be extracted via the development of two separate schemes, that is, one with handcrafted descriptors and another with deep neural networks. The proposed representation seeks to characterize both appearance and spatial relations of multigrained objects, and is further equipped with importance weights which capture variations in intragroup dynamics. Optimal group-wise matching is facilitated by a multiorder matching process which, in turn, dynamically updates the importance weights in iterative fashion. We evaluated three multicamera group datasets containing complex scenarios and large dynamics, with experimental results demonstrating the effectiveness of our approach.

AP-Loss for Accurate One-Stage Object Detection.

One-stage object detectors are trained by optimizing classification-loss and localization-loss simultaneously, with the former suffering much from extreme foreground-background class imbalance issue due to the large number of anchors. This paper alleviates this issue by proposing a novel framework to replace the classification task in one-stage detectors with a ranking task, and adopting the average-precision loss (AP-loss) for the ranking problem. Due to its non-differentiability and non-convexity, the AP-loss cannot be optimized directly. For this purpose, we develop a novel optimization algorithm, which seamlessly combines the error-driven update scheme in perceptron learning and backpropagation algorithm in deep networks. We provide in-depth analyses on the good convergence property and computational complexity of the proposed algorithm, both theoretically and empirically. Experimental results demonstrate notable improvement in addressing the imbalance issue in object detection over existing AP-based optimization algorithms. An improved state-of-the-art performance is achieved in one-stage detectors based on AP-loss over detectors using classification-losses on various standard benchmarks. The proposed framework is also highly versatile in accommodating different network architectures. Code is available at https://github.com/cccorn/AP-loss.

Towards Automatic Skeleton Extraction With Skeleton Grafting.

This article introduces a novel approach to generate visually promising skeletons automatically without any manual tuning. In practice, it is challenging to extract promising skeletons directly using existing approaches. This is because they either cannot fully preserve shape features, or require manual intervention, such as boundary smoothing and skeleton pruning, to justify the eye-level view assumption. We propose an approach here that generates backbone and dense skeletons by shape input, and then extends the backbone branches via skeleton grafting from the dense skeleton to ensure a well-integrated output. Based on our evaluation, the generated skeletons best depict the shapes at levels that are similar to human perception. To evaluate and fully express the properties of the extracted skeletons, we introduce two potential functions within the high-order matching protocol to improve the accuracy of skeleton-based matching. These two functions fuse the similarities between skeleton graphs and geometrical relations characterized by multiple skeleton endpoints. Experiments on three high-order matching protocols show that the proposed potential functions can effectively reduce the number of incorrect matches.

WatchPose: A View-Aware Approach for Camera Pose Data Collection in Industrial Environments.

Collecting correlated scene images and camera poses is an essential step towards learning absolute camera pose regression models. While the acquisition of such data in living environments is relatively easy by following regular roads and paths, it is still a challenging task in constricted industrial environments. This is because industrial objects have varied sizes and inspections are usually carried out with non-constant motions. As a result, regression models are more sensitive to scene images with respect to viewpoints and distances. Motivated by this, we present a simple but efficient camera pose data collection method, WatchPose, to improve the generalization and robustness of camera pose regression models. Specifically, WatchPose tracks nested markers and visualizes viewpoints in an Augmented Reality- (AR) based manner to properly guide users to collect training data from broader camera-object distances and more diverse views around the objects. Experiments show that WatchPose can effectively improve the accuracy of existing camera pose regression models compared to the traditional data acquisition method. We also introduce a new dataset, Industrial10, to encourage the community to adapt camera pose regression methods for more complex environments.

A Survey of Automatic Facial Micro-Expression Analysis: Databases, Methods, and Challenges.

Over the last few years, automatic facial micro-expression analysis has garnered increasing attention from experts across different disciplines because of its potential applications in various fields such as clinical diagnosis, forensic investigation and security systems. Advances in computer algorithms and video acquisition technology have rendered machine analysis of facial micro-expressions possible today, in contrast to decades ago when it was primarily the domain of psychiatrists where analysis was largely manual. Indeed, although the study of facial micro-expressions is a well-established field in psychology, it is still relatively new from the computational perspective with many interesting problems. In this survey, we present a comprehensive review of state-of-the-art databases and methods for micro-expressions spotting and recognition. Individual stages involved in the automation of these tasks are also described and reviewed at length. In addition, we also deliberate on the challenges and future directions in this growing field of automatic facial micro-expression analysis.

Five-year trends in perioperative red blood cell transfusion from index cases in five surgical specialties: 2011 to 2015.

BACKGROUND: Red blood cell (RBC) transfusion can be life-saving; however, the risks of RBC transfusion have been increasingly recognized, and current guidelines recommend restrictive transfusion in most patients. We hypothesized that RBC transfusions are decreasing in surgical patients. STUDY DESIGN AND METHODS: A retrospective review of the National Surgical Quality Improvement Program database was performed from 2011 to 2015. Index cases in five surgical specialties were studied: neurosurgery, thoracic surgery, gynecologic surgery, orthopedic surgery, and vascular surgery. Patient characteristics, preoperative laboratory values, and surgery details were compared between years. The study's primary outcome was perioperative RBC transfusion, which was compared over the 5-year period for each specialty. Secondary outcomes were myocardial infarction and renal failure after surgery. In addition, trends in RBC transfusion between low-risk and high-risk patients and between emergency and elective surgery were examined. RESULTS: RBC transfusion decreased in all surgical specialties except for thoracic and gynecologic surgery. RBC transfusion decreased substantially in orthopedic surgery, falling from 22.4% in 2011 to 6.3% in 2015 (p ≤ 0.0001). High-risk patients had greater reductions in the receipt of RBC transfusion than low-risk patients, and there were no increases in myocardial infarction or renal failure after surgery in any specialty. CONCLUSION: RBC transfusion appears to be decreasing across multiple surgical specialties, with no apparent increase in myocardial infarctions or renal failure. This likely represents an important improvement in patient care. Continued efforts are needed to develop patient blood management programs and further reduce RBC transfusion.

Efficient spatio-temporal local binary patterns for spontaneous facial micro-expression recognition.

Micro-expression recognition is still in the preliminary stage, owing much to the numerous difficulties faced in the development of datasets. Since micro-expression is an important affective clue for clinical diagnosis and deceit analysis, much effort has gone into the creation of these datasets for research purposes. There are currently two publicly available spontaneous micro-expression datasets--SMIC and CASME II, both with baseline results released using the widely used dynamic texture descriptor LBP-TOP for feature extraction. Although LBP-TOP is popular and widely used, it is still not compact enough. In this paper, we draw further inspiration from the concept of LBP-TOP that considers three orthogonal planes by proposing two efficient approaches for feature extraction. The compact robust form described by the proposed LBP-Six Intersection Points (SIP) and a super-compact LBP-Three Mean Orthogonal Planes (MOP) not only preserves the essential patterns, but also reduces the redundancy that affects the discriminality of the encoded features. Through a comprehensive set of experiments, we demonstrate the strengths of our approaches in terms of recognition accuracy and efficiency.

Inhibitory effect of Quassia amara Linn. crude bark extract on Entamoeba histolytica in vitro

BACKGROUND: Entamoeba histolytica is an important etiologic agent of diarrhea. Globally, it is estimated to infect 40 to 50 million people and cause 40,000 to 100,000 deaths per year. Metronidazole is effective but can cause adverse reactions in certain individuals. In search of alternatives, traditional medicinal plants are being studied. Several plants in Family Simaroubaceae have shown anti-amoebic activity. Quassia amara, a member of this family has not been tested.OBJECTIVE: To determine the effect of Q. amara crude extract on Entamoeba histolytica in vitro.METHODS: Initial testing of 104 µg/ml ethanolic bark extract was performed. Counts were made after 72 hours. Three trials in triplicates were performed.Nine (9) dilutions of extract were then tested (18.8 to 5,00 µg/ml). Test tubes were checked for viable amoeba after 24-hour and 72-hour incubation. Minimum inhibitory concentrations (MIC) were determined for the two incubation periods. At least two trials in triplicates for each dilution were performed. metronidazole served as positive control.RESULTS: At 104 µg/ml incubated for 72 hours, no viable amoeba was obtained and counted. The MIC after 24 hours was 5,000 µg/ml, while the MIC at 72 hours was 37.5 µg/ml.CONCLUSION: Q. amara crude extract has inhibitory effects on E. histolycain vitro.