Building embodied intelligent agents that can interact with 3D indoor environments has received increasing research attention in recent years. While most works focus on single-object or agent-object visual functionality and affordances, our work proposes to study a new kind of visual relationship that is also important to perceive and model -- inter-object functional relationships (e.g., a switch on the wall turns on or off the light, a remote control operates the TV). Humans often spend little or no effort to infer these relationships, even when entering a new room, by using our strong prior knowledge (e.g., we know that buttons control electrical devices) or using only a few exploratory interactions in cases of uncertainty (e.g., multiple switches and lights in the same room). In this paper, we take the first step in building AI system learning inter-object functional relationships in 3D indoor environments with key technical contributions of modeling prior knowledge by training over large-scale scenes and designing interactive policies for effectively exploring the training scenes and quickly adapting to novel test scenes. We create a new benchmark based on the AI2Thor and PartNet datasets and perform extensive experiments that prove the effectiveness of our proposed method. Results show that our model successfully learns priors and fast-interactive-adaptation strategies for exploring inter-object functional relationships in complex 3D scenes. Several ablation studies further validate the usefulness of each proposed module.

Hearing loss is a major health problem and psychological burden in humans. Mouse models offer a possibility to elucidate genes involved in the underlying developmental and pathophysiological mechanisms of hearing impairment. To this end, large-scale mouse phenotyping programs include auditory phenotyping of single-gene knockout mouse lines. Using the auditory brainstem response (ABR) procedure, the German Mouse Clinic and similar facilities worldwide have produced large, uniform data sets of averaged ABR raw data of mutant and wildtype mice. In the course of standard ABR analysis, hearing thresholds are assessed visually by trained staff from series of signal curves of increasing sound pressure level. This is time-consuming and prone to be biased by the reader as well as the graphical display quality and scale. In an attempt to reduce workload and improve quality and reproducibility, we developed and compared two methods for automated hearing threshold identification from averaged ABR raw data: a supervised approach involving two combined neural networks trained on human-generated labels and a self-supervised approach, which exploits the signal power spectrum and combines random forest sound level estimation with a piece-wise curve fitting algorithm for threshold finding. We show that both models work well, outperform human threshold detection, and are suitable for fast, reliable, and unbiased hearing threshold detection and quality control. In a high-throughput mouse phenotyping environment, both methods perform well as part of an automated end-to-end screening pipeline to detect candidate genes for hearing involvement. Code for both models as well as data used for this work are freely available.

Rolling bearings are one of the most widely used bearings in industrial machines. Deterioration in the condition of rolling bearings can result in the total failure of rotating machinery. AI-based methods are widely applied in the diagnosis of rolling bearings. Hybrid NN-based methods have been shown to achieve the best diagnosis results. Typically, raw data is generated from accelerometers mounted on the machine housing. However, the diagnostic utility of each signal is highly dependent on the location of the corresponding accelerometer. This paper proposes a novel hybrid CNN-MLP model-based diagnostic method which combines mixed input to perform rolling bearing diagnostics. The method successfully detects and localizes bearing defects using acceleration data from a shaft-mounted wireless acceleration sensor. The experimental results show that the hybrid model is superior to the CNN and MLP models operating separately, and can deliver a high detection accuracy of 99,6% for the bearing faults compared to 98% for CNN and 81% for MLP models.

When many labels are possible, choosing a single one can lead to low precision. A common alternative, referred to as top-$K$ classification, is to choose some number $K$ (commonly around 5) and to return the $K$ labels with the highest scores. Unfortunately, for unambiguous cases, $K>1$ is too many and, for very ambiguous cases, $K \leq 5$ (for example) can be too small. An alternative sensible strategy is to use an adaptive approach in which the number of labels returned varies as a function of the computed ambiguity, but must average to some particular $K$ over all the samples. We denote this alternative average-$K$ classification. This paper formally characterizes the ambiguity profile when average-$K$ classification can achieve a lower error rate than a fixed top-$K$ classification. Moreover, it provides natural estimation procedures for both the fixed-size and the adaptive classifier and proves their consistency. Finally, it reports experiments on real-world image data sets revealing the benefit of average-$K$ classification over top-$K$ in practice. Overall, when the ambiguity is known precisely, average-$K$ is never worse than top-$K$, and, in our experiments, when it is estimated, this also holds.

Sports video analysis is a prevalent research topic due to the variety of application areas, ranging from multimedia intelligent devices with user-tailored digests up to analysis of athletes' performance. The Sports Video task is part of the MediaEval 2021 benchmark. This task tackles fine-grained action detection and classification from videos. The focus is on recordings of table tennis games. Running since 2019, the task has offered a classification challenge from untrimmed video recorded in natural conditions with known temporal boundaries for each stroke. This year, the dataset is extended and offers, in addition, a detection challenge from untrimmed videos without annotations. This work aims at creating tools for sports coaches and players in order to analyze sports performance. Movement analysis and player profiling may be built upon such technology to enrich the training experience of athletes and improve their performance.

Clinical decision support tools rooted in machine learning and optimization can provide significant value to healthcare providers, including through better management of intensive care units. In particular, it is important that the patient discharge task addresses the nuanced trade-off between decreasing a patient's length of stay (and associated hospitalization costs) and the risk of readmission or even death following the discharge decision. This work introduces an end-to-end general framework for capturing this trade-off to recommend optimal discharge timing decisions given a patient's electronic health records. A data-driven approach is used to derive a parsimonious, discrete state space representation that captures a patient's physiological condition. Based on this model and a given cost function, an infinite-horizon discounted Markov decision process is formulated and solved numerically to compute an optimal discharge policy, whose value is assessed using off-policy evaluation strategies. Extensive numerical experiments are performed to validate the proposed framework using real-life intensive care unit patient data.

The Mixup scheme suggests mixing a pair of samples to create an augmented training sample and has gained considerable attention recently for improving the generalizability of neural networks. A straightforward and widely used extension of Mixup is to combine with regional dropout-like methods: removing random patches from a sample and replacing it with the features from another sample. Albeit their simplicity and effectiveness, these methods are prone to create harmful samples due to their randomness. To address this issue, 'maximum saliency' strategies were recently proposed: they select only the most informative features to prevent such a phenomenon. However, they now suffer from lack of sample diversification as they always deterministically select regions with maximum saliency, injecting bias into the augmented data. In this paper, we present, a novel, yet simple Mixup-variant that captures the best of both worlds. Our idea is two-fold. By stochastically sampling the features and 'grafting' them onto another sample, our method effectively generates diverse yet meaningful samples. Its second ingredient is to produce the label of the grafted sample by mixing the labels in a saliency-calibrated fashion, which rectifies supervision misguidance introduced by the random sampling procedure. Our experiments under CIFAR, Tiny-ImageNet, and ImageNet datasets show that our scheme outperforms the current state-of-the-art augmentation strategies not only in terms of classification accuracy, but is also superior in coping under stress conditions such as data corruption and object occlusion.

Kalendar AI, a San Francisco-based startup that's been building on top of GPT-3's language model -- developing a SaaS for automating lead generation and sales outreach to make it easier for companies to get initial meetings with prospective customers -- has raised $3.2 million in pre-seed funding from 500 Startups; The Lean Startup author, Eric Ries; VC firms Village Global and Metaplanet; and 20 angel investors (including CEOs of "popular" but undisclosed companies). "Our AI technology writes personalized invitations to ideal customers with personalized decks -- inviting them to take a meeting," explains founder and CEO Ravi Vadrevu. The SaaS was launched in February this year, although the startup itself -- which is called Kriya Inc -- was founded back in 2017 and had been bootstrapping prior to raising this pre-seed. The idea for the b2b product is to automate the time-consuming and expensive process of sales outreach, including locating and pitching leads, as well as to offer tools to streamline and enhance initial sales meetings. Kalendar AI claims to have amassed a database of 340M "ideal customer profiles" upon which it unleashes its AI sales rep bots to send "personalized" pitches (including "interactive presentations that convert into one-click meetings") to likely looking customers. "Our solution brings down the time to initiate a conversation to book an appointment from 7 days to 30 seconds from a sales perspective," claims Vadrevu, who also argues there are big productivity wins from a marketing perspective vs other channels.

A Confusion matrix is an N x N matrix used for evaluating the performance of a classification model, where N is the number of target classes. The matrix compares the actual target values with those predicted by the machine learning model. This gives us a view of how well our classification model is performing and what kinds of errors it is making. A confusion matrix is a summary of prediction results on a classification problem. The number of correct and incorrect predictions are summarized with count values and broken down by each class.

The ever-increasing amount of user-generated content online has led, in recent years, to an expansion in research and investment in automated content analysis tools. Scrutiny of automated content analysis has accelerated during the COVID-19 pandemic, as social networking services have placed a greater reliance on these tools due to concerns about health risks to their moderation staff from in-person work. At the same time, there are important policy debates around the world about how to improve content moderation while protecting free expression and privacy. In order to advance these debates, we need to understand the potential role of automated content analysis tools. This paper explains the capabilities and limitations of tools for analyzing online multimedia content and highlights the potential risks of using these tools at scale without accounting for their limitations. It focuses on two main categories of tools: matching models and computer prediction models. Matching models include cryptographic and perceptual hashing, which compare user-generated content with existing and known content. Predictive models (including computer vision and computer audition) are machine learning techniques that aim to identify characteristics of new or previously unknown content.