Benchmark datasets play a central role in the organization of machine learning research. They coordinate researchers around shared research problems and serve as a measure of progress towards shared goals. Despite the foundational role of benchmarking practices in this field, relatively little attention has been paid to the dynamics of benchmark dataset use and reuse, within or across machine learning subcommunities. In this paper, we dig into these dynamics. We study how dataset usage patterns differ across machine learning subcommunities and across time from 2015-2020. We find increasing concentration on fewer and fewer datasets within task communities, significant adoption of datasets from other tasks, and concentration across the field on datasets that have been introduced by researchers situated within a small number of elite institutions. Our results have implications for scientific evaluation, AI ethics, and equity/access within the field.

Sparse events, such as malign attacks in real-time network traffic, have caused big organisations an immense hike in revenue loss. This is due to the excessive growth of the network and its exposure to a plethora of people. The standard methods used to detect intrusions are not promising and have significant failure to identify new malware. Moreover, the challenges in handling high volume data with sparsity, high false positives, fewer detection rates in minor class, training time and feature engineering of the dimensionality of data has promoted deep learning to take over the task with less time and great results. The existing system needs improvement in solving real-time network traffic issues along with feature engineering. Our proposed work overcomes these challenges by giving promising results using deep-stacked autoencoders in two stages. The two-stage deep learning combines with shallow learning using the random forest for classification in the second stage. This made the model get well with the latest Canadian Institute for Cybersecurity - Intrusion Detection System 2017 (CICIDS-2017) dataset. Zero false positives with admirable detection accuracy were achieved.

As companies strive toward a frictionless digital experience, they must find ways to improve customer loyalty and trust. How will digital customer experience evolve in the coming year? The pandemic-induced explosion of ecommerce and the acceleration of digital transformation means that most companies will re-examine and revamp their customer experience strategies and capabilities in the coming year. With customer loyalty increasingly difficult to gain and sustain, pioneering, data-powered technologies will improve the seamlessness of these digital experiences and deliver better brand engagement. A dozen leaders in the customer experience (CX) space spanning a range of industries – including healthcare, travel, insurance, and banking – met to discuss challenges and solutions, and debate the direction of travel in the coming year.

One year ago Google artificial intelligence researcher Timnit Gebru tweeted, "I was fired" and ignited a controversy over the freedom of employees to question the impact of their company's technology. Thursday, she launched a new research institute to ask questions about responsible use of artificial intelligence that Gebru says Google and other tech companies won't. "Instead of fighting from the inside, I want to show a model for an independent institution with a different set of incentive structures," says Gebru, who is founder and executive director of Distributed Artificial Intelligence Research (DAIR). The first part of the name is a reference to her aim to be more inclusive than most AI labs--which skew white, Western, and male--and to recruit people from parts of the world rarely represented in the tech industry. Gebru was ejected from Google after clashing with bosses over a research paper urging caution with new text-processing technology enthusiastically adopted by Google and other tech companies.

Fusion technique is a key research topic in multimodal sentiment analysis. The recent attention-based fusion demonstrates advances over simple operation-based fusion. However, these fusion works adopt single-scale, i.e., token-level or utterance-level, unimodal representation. Such single-scale fusion is suboptimal because that different modality should be aligned with different granularities. This paper proposes a fusion model named ScaleVLAD to gather multi-Scale representation from text, video, and audio with shared Vectors of Locally Aggregated Descriptors to improve unaligned multimodal sentiment analysis. These shared vectors can be regarded as shared topics to align different modalities. In addition, we propose a self-supervised shifted clustering loss to keep the fused feature differentiation among samples. The backbones are three Transformer encoders corresponding to three modalities, and the aggregated features generated from the fusion module are feed to a Transformer plus a full connection to finish task predictions. Experiments on three popular sentiment analysis benchmarks, IEMOCAP, MOSI, and MOSEI, demonstrate significant gains over baselines.

Self-supervised learning aims to learn image feature representations without the usage of manually annotated labels. It is often used as a precursor step to obtain useful initial network weights which contribute to faster convergence and superior performance of downstream tasks. While self-supervision allows one to reduce the domain gap between supervised and unsupervised learning without the usage of labels, the self-supervised objective still requires a strong inductive bias to downstream tasks for effective transfer learning. In this work, we present our material and texture based self-supervision method named MATTER (MATerial and TExture Representation Learning), which is inspired by classical material and texture methods. Material and texture can effectively describe any surface, including its tactile properties, color, and specularity. By extension, effective representation of material and texture can describe other semantic classes strongly associated with said material and texture. MATTER leverages multi-temporal, spatially aligned remote sensing imagery over unchanged regions to learn invariance to illumination and viewing angle as a mechanism to achieve consistency of material and texture representation. We show that our self-supervision pre-training method allows for up to 24.22% and 6.33% performance increase in unsupervised and fine-tuned setups, and up to 76% faster convergence on change detection, land cover classification, and semantic segmentation tasks.

We present an approach for 3D global human mesh recovery from monocular videos recorded with dynamic cameras. Our approach is robust to severe and long-term occlusions and tracks human bodies even when they go outside the camera's field of view. To achieve this, we first propose a deep generative motion infiller, which autoregressively infills the body motions of occluded humans based on visible motions. Additionally, in contrast to prior work, our approach reconstructs human meshes in consistent global coordinates even with dynamic cameras. Since the joint reconstruction of human motions and camera poses is underconstrained, we propose a global trajectory predictor that generates global human trajectories based on local body movements. Using the predicted trajectories as anchors, we present a global optimization framework that refines the predicted trajectories and optimizes the camera poses to match the video evidence such as 2D keypoints. Experiments on challenging indoor and in-the-wild datasets with dynamic cameras demonstrate that the proposed approach outperforms prior methods significantly in terms of motion infilling and global mesh recovery.

Natural language generation from structured data mainly focuses on surface-level descriptions, suffering from uncontrollable content selection and low fidelity. Previous works leverage logical forms to facilitate logical knowledge-conditioned text generation. Though achieving remarkable progress, they are data-hungry, which makes the adoption for real-world applications challenging with limited data. To this end, this paper proposes a unified framework for logical knowledge-conditioned text generation in the few-shot setting. With only a few seeds logical forms (e.g., 20/100 shot), our approach leverages self-training and samples pseudo logical forms based on content and structure consistency. Experimental results demonstrate that our approach can obtain better few-shot performance than baselines.

The overhead buzzing of unmanned aerial vehicles (UAVs) – aka drones – is an increasingly familiar sound in many parts of the world. Whether these helicopter-like devices are flown for fun, military purposes or commercial reasons, the global drone market is predicted to increase annually by nearly 14% between 2020 and 2025. Drones can give operators a birds-eye view of events – including natural disasters – as they unfold. And they can open up difficult-to-access places for emergency supplies to be delivered. This makes them well-suited to help in the response to humanitarian and environmental challenges.

The graph represents a network of 1,493 Twitter users whose tweets in the requested range contained "tech4good", or who were replied to or mentioned in those tweets. The network was obtained from the NodeXL Graph Server on Saturday, 27 November 2021 at 19:25 UTC. The requested start date was Saturday, 27 November 2021 at 01:01 UTC and the maximum number of days (going backward) was 14. The maximum number of tweets collected was 7,500. The tweets in the network were tweeted over the 13-day, 6-hour, 0-minute period from Saturday, 13 November 2021 at 08:34 UTC to Friday, 26 November 2021 at 14:35 UTC.