It is known that the human visual system performs a hierarchical information process in which early vision cues (or primitives) are fused in the visual cortex to compose complex shapes and descriptors. While different aspects of the process have been extensively studied, as the lens adaptation or the feature detection, some other,as the feature fusion, have been mostly left aside. In this work we elaborate on the fusion of early vision primitives using generalizations of the Choquet integral, and novel aggregation operators that have been extensively studied in recent years. We propose to use generalizations of the Choquet integral to sensibly fuse elementary edge cues, in an attempt to model the behaviour of neurons in the early visual cortex. Our proposal leads to a full-framed edge detection algorithm, whose performance is put to the test in state-of-the-art boundary detection datasets.

Monocular 3D object detection is an important task for autonomous driving considering its advantage of low cost. It is much more challenging compared to conventional 2D case due to its inherent ill-posed property, which is mainly reflected on the lack of depth information. Recent progress on 2D detection offers opportunities to better solving this problem. However, it is non-trivial to make a general adapted 2D detector work in this 3D task. In this technical report, we study this problem with a practice built on fully convolutional single-stage detector and propose a general framework FCOS3D. Specifically, we first transform the commonly defined 7-DoF 3D targets to image domain and decouple it as 2D and 3D attributes. Then the objects are distributed to different feature levels with the consideration of their 2D scales and assigned only according to the projected 3D-center for training procedure. Furthermore, the center-ness is redefined with a 2D Guassian distribution based on the 3D-center to fit the 3D target formulation. All of these make this framework simple yet effective, getting rid of any 2D detection or 2D-3D correspondence priors. Our solution achieves 1st place out of all the vision-only methods in the nuScenes 3D detection challenge of NeurIPS 2020. Code and models are released at https://github.com/open-mmlab/mmdetection3d.

Teamwork isn't just a human characteristic: Colonies of army ants will form living'scaffolding' to protect members from falling. The insects are blind and have no designated leader but, according to new research, they're able to use simple behavioral rules to develop these safety structures without the need for direct communication. Once a scaffold was built, worker ants were almost 100 percent protected from falling off steep inclines. Understanding how they design such complex structures could help engineers development self-healing materials and swarm robotics, researchers said. Army ants in Central American rainforests will build scaffolds out of their body to help them traverse steep terrain.

Recent machine-learning approaches to deterministic search and domain-independent planning employ policy learning to speed up search. Unfortunately, when attempting to solve a search problem by successively applying a policy, no guarantees can be given on solution quality. The problem of how to effectively use a learned policy within a bounded-suboptimal search algorithm remains largely as an open question. In this paper, we propose various ways in which such policies can be integrated into Focal Search, assuming that the policy is a neural network classifier. Furthermore, we provide mathematical foundations for some of the resulting algorithms. To evaluate the resulting algorithms over a number of policies with varying accuracy, we use synthetic policies which can be generated for a target accuracy for problems where the search space can be held in memory. We evaluate our focal search variants over three benchmark domains using our synthetic approach, and on the 15-puzzle using a neural network learned using 1.5 million examples. We observe that \emph{Discrepancy Focal Search}, which we show expands the node which maximizes an approximation of the probability that its corresponding path is a prefix of an optimal path, obtains, in general, the best results in terms of runtime and solution quality.

The investment of time and resources for better strategies and methodologies to tackle a potential pandemic is key to deal with potential outbreaks of new variants or other viruses in the future. In this work, we recreated the scene of a year ago, 2020, when the pandemic erupted across the world for the fifty countries with more COVID-19 cases reported. We performed some experiments in which we compare state-of-the-art machine learning algorithms, such as LSTM, against online incremental machine learning algorithms to adapt them to the daily changes in the spread of the disease and predict future COVID-19 cases. To compare the methods, we performed three experiments: In the first one, we trained the models using only data from the country we predicted. In the second one, we use data from all fifty countries to train and predict each of them. In the first and second experiment, we used a static hold-out approach for all methods. In the third experiment, we trained the incremental methods sequentially, using a prequential evaluation. This scheme is not suitable for most state-of-the-art machine learning algorithms because they need to be retrained from scratch for every batch of predictions, causing a computational burden. Results show that incremental methods are a promising approach to adapt to changes of the disease over time; they are always up to date with the last state of the data distribution, and they have a significantly lower computational cost than other techniques such as LSTMs.

Federated learning (FL) brings collaborative intelligence into industries without centralized training data to accelerate the process of Industry 4.0 on the edge computing level. FL solves the dilemma in which enterprises wish to make the use of data intelligence with security concerns. To accelerate industrial Internet of things with the further leverage of FL, existing achievements on FL are developed from three aspects: 1) define terminologies and elaborate a general framework of FL for accommodating various scenarios; 2) discuss the state-of-the-art of FL on fundamental researches including data partitioning, privacy preservation, model optimization, local model transportation, personalization, motivation mechanism, platform & tools, and benchmark; 3) discuss the impacts of FL from the economic perspective. To attract more attention from industrial academia and practice, a FL-transformed manufacturing paradigm is presented, and future research directions of FL are given and possible immediate applications in Industry 4.0 domain are also proposed.

This paper presents the PALI team's winning system for SemEval-2021 Task 2: Multilingual and Cross-lingual Word-in-Context Disambiguation. We fine-tune XLM-RoBERTa model to solve the task of word in context disambiguation, i.e., to determine whether the target word in the two contexts contains the same meaning or not. In the implementation, we first specifically design an input tag to emphasize the target word in the contexts. Second, we construct a new vector on the fine-tuned embeddings from XLM-RoBERTa and feed it to a fully-connected network to output the probability of whether the target word in the context has the same meaning or not. The new vector is attained by concatenating the embedding of the [CLS] token and the embeddings of the target word in the contexts. In training, we explore several tricks, such as the Ranger optimizer, data augmentation, and adversarial training, to improve the model prediction. Consequently, we attain first place in all four cross-lingual tasks.

Zero-shot learning aims to recognize unseen objects using their semantic representations. Most existing works use visual attributes labeled by humans, not suitable for large-scale applications. In this paper, we revisit the use of documents as semantic representations. We argue that documents like Wikipedia pages contain rich visual information, which however can easily be buried by the vast amount of non-visual sentences. To address this issue, we propose a semi-automatic mechanism for visual sentence extraction that leverages the document section headers and the clustering structure of visual sentences. The extracted visual sentences, after a novel weighting scheme to distinguish similar classes, essentially form semantic representations like visual attributes but need much less human effort. On the ImageNet dataset with over 10,000 unseen classes, our representations lead to a 64% relative improvement against the commonly used ones.

Google is putting a bunch of iconic Japanese characters in Search as augmented reality objects you can interact with. The tech giant is giving you the chance to bring 14 familiar characters from anime, video games and TV shows into your environment, including Pac-Man and Hello Kitty. Apparently, Pac-Man remains the most-searched animated icon on Google, especially (for some reason) in Peru. Its worldwide search interest more than doubles the second-most searched character, Hello Kitty. Aside from those two, you'll also be able to summon Ultraman, Evangelion and Gundam robots, as well as Little Twin Stars characters into your space.

Police in Texas investigating a Tesla car crash in which two men died will serve search warrants on the company to ascertain if the vehicle's autopilot mode was engaged at the time of the incident. However Tesla's CEO, Elon Musk, has said the self-driving feature was not being used, based on an internal probe by the company. In the incident, two men, both in their 50s, were killed after their 2019 Tesla Model S crashed into a tree and caught fire. According to police reports, the car was travelling at a high speed and failed to negotiate a curve in the road. Texas police noted that nobody was at the driving seat at the time of impact, raising doubts about the involvement of the car's autopilot mode.