Online encyclopedias, such as Wikipedia, have been well-developed and researched in the last two decades. One can find any attributes or other information of a wiki item on a wiki page edited by a community of volunteers. However, the traditional text, images and tables can hardly express some aspects of an wiki item. For example, when we talk about ``Shiba Inu'', one may care more about ``How to feed it'' or ``How to train it not to protect its food''. Currently, short-video platforms have become a hallmark in the online world. Whether you're on TikTok, Instagram, Kuaishou, or YouTube Shorts, short-video apps have changed how we consume and create content today. Except for producing short videos for entertainment, we can find more and more authors sharing insightful knowledge widely across all walks of life. These short videos, which we call knowledge videos, can easily express any aspects (e.g. hair or how-to-feed) consumers want to know about an item (e.g. Shiba Inu), and they can be systematically analyzed and organized like an online encyclopedia. In this paper, we propose Kuaipedia, a large-scale multi-modal encyclopedia consisting of items, aspects, and short videos lined to them, which was extracted from billions of videos of Kuaishou (Kwai), a well-known short-video platform in China. We first collected items from multiple sources and mined user-centered aspects from millions of users' queries to build an item-aspect tree. Then we propose a new task called ``multi-modal item-aspect linking'' as an expansion of ``entity linking'' to link short videos into item-aspect pairs and build the whole short-video encyclopedia. Intrinsic evaluations show that our encyclopedia is of large scale and highly accurate. We also conduct sufficient extrinsic experiments to show how Kuaipedia can help fundamental applications such as entity typing and entity linking.
Abstractive summarization has made tremendous progress in recent years. In this work, we perform fine-grained human annotations to evaluate long document abstractive summarization systems (i.e., models and metrics) with the aim of implementing them to generate reliable summaries. For long document abstractive models, we show that the constant strive for state-of-the-art ROUGE results can lead us to generate more relevant summaries but not factual ones. For long document evaluation metrics, human evaluation results show that ROUGE remains the best at evaluating the relevancy of a summary. It also reveals important limitations of factuality metrics in detecting different types of factual errors and the reasons behind the effectiveness of BARTScore. We then suggest promising directions in the endeavor of developing factual consistency metrics. Finally, we release our annotated long document dataset with the hope that it can contribute to the development of metrics across a broader range of summarization settings.
Cameras capture sensor RAW images and transform them into pleasant RGB images, suitable for the human eyes, using their integrated Image Signal Processor (ISP). Numerous low-level vision tasks operate in the RAW domain (e.g. image denoising, white balance) due to its linear relationship with the scene irradiance, wide-range of information at 12bits, and sensor designs. Despite this, RAW image datasets are scarce and more expensive to collect than the already large and public RGB datasets. This paper introduces the AIM 2022 Challenge on Reversed Image Signal Processing and RAW Reconstruction. We aim to recover raw sensor images from the corresponding RGBs without metadata and, by doing this, "reverse" the ISP transformation. The proposed methods and benchmark establish the state-of-the-art for this low-level vision inverse problem, and generating realistic raw sensor readings can potentially benefit other tasks such as denoising and super-resolution.
For the Hilti Challenge 2022, we created two systems, one building upon the other. The first system is FL2BIPS which utilizes the iEKF algorithm FAST-LIO2 and Bayesian ICP PoseSLAM, whereas the second system is GTSFM, a structure from motion pipeline with factor graph backend optimization powered by GTSAM
Safely interacting with other traffic participants is one of the core requirements for autonomous driving, especially in intersections and occlusions. Most existing approaches are designed for particular scenarios and require significant human labor in parameter tuning to be applied to different situations. To solve this problem, we first propose a learning-based Interaction Point Model (IPM), which describes the interaction between agents with the protection time and interaction priority in a unified manner. We further integrate the proposed IPM into a novel planning framework, demonstrating its effectiveness and robustness through comprehensive simulations in highly dynamic environments.
The graph structure of road networks is critical for downstream tasks of autonomous driving systems, such as global planning, motion prediction and control. In the past, the road network graph is usually manually annotated by human experts, which is time-consuming and labor-intensive. To obtain the road network graph with better effectiveness and efficiency, automatic approaches for road network graph detection are required. Previous works either post-process semantic segmentation maps or propose graph-based algorithms to directly predict the road network graph. However, previous works suffer from hard-coded heuristic processing algorithms and inferior final performance. To enhance the previous SOTA (State-of-the-Art) approach RNGDet, we add an instance segmentation head to better supervise the model training, and enable the model to leverage multi-scale features of the backbone network. Since the new proposed approach is improved from RNGDet, it is named RNGDet++. All approaches are evaluated on a large publicly available dataset. RNGDet++ outperforms baseline models on almost all metrics scores. It improves the topology correctness APLS (Average Path Length Similarity) by around 3\%. The demo video and supplementary materials are available on our project page \url{https://tonyxuqaq.github.io/projects/RNGDetPlusPlus/}.
Marking-level high-definition maps (HD maps) are of great significance for autonomous vehicles, especially in large-scale, appearance-changing scenarios where autonomous vehicles rely on markings for localization and lanes for safe driving. In this paper, we propose a highly feasible framework for automatically building a marking-level HD map using a simple sensor setup (one or more monocular cameras). We optimize the position of the marking corners to fit the result of marking segmentation and simultaneously optimize the inverse perspective mapping (IPM) matrix of the corresponding camera to obtain an accurate transformation from the front view image to the bird's-eye view (BEV). In the quantitative evaluation, the built HD map almost attains centimeter-level accuracy. The accuracy of the optimized IPM matrix is similar to that of the manual calibration. The method can also be generalized to build HD maps in a broader sense by increasing the types of recognizable markings.
With the rapid development of autonomous vehicles, there witnesses a booming demand for high-definition maps (HD maps) that provide reliable and robust prior information of static surroundings in autonomous driving scenarios. As one of the main high-level elements in the HD map, the road lane centerline is critical for downstream tasks, such as prediction and planning. Manually annotating lane centerline HD maps by human annotators is labor-intensive, expensive and inefficient, severely restricting the wide application and fast deployment of autonomous driving systems. Previous works seldom explore the centerline HD map mapping problem due to the complicated topology and severe overlapping issues of road centerlines. In this paper, we propose a novel method named CenterLineDet to create the lane centerline HD map automatically. CenterLineDet is trained by imitation learning and can effectively detect the graph of lane centerlines by iterations with vehicle-mounted sensors. Due to the application of the DETR-like transformer network, CenterLineDet can handle complicated graph topology, such as lane intersections. The proposed approach is evaluated on a large publicly available dataset Nuscenes, and the superiority of CenterLineDet is well demonstrated by the comparison results. This paper is accompanied by a demo video and a supplementary document that are available at \url{https://tonyxuqaq.github.io/projects/CenterLineDet/}.
Robots are integrating more huge-size models to enrich functions and improve accuracy, which leads to out-of-control computing pressure. And thus robots are encountering bottlenecks in computing power and battery capacity. Fog or cloud robotics is one of the most anticipated theories to address these issues. Approaches of cloud robotics have developed from system-level to node-level. However, the present node-level systems are not flexible enough to dynamically adapt to changing conditions. To address this, we present ElasticROS, which evolves the present node-level systems into an algorithm-level one. ElasticROS is based on ROS and ROS2. For fog and cloud robotics, it is the first robot operating system with algorithm-level collaborative computing. ElasticROS develops elastic collaborative computing to achieve adaptability to dynamic conditions. The collaborative computing algorithm is the core and challenge of ElasticROS. We abstract the problem and then propose an algorithm named ElasAction to address. It is a dynamic action decision algorithm based on online learning, which determines how robots and servers cooperate. The algorithm dynamically updates parameters to adapt to changes of conditions where the robot is currently in. It achieves elastically distributing of computing tasks to robots and servers according to configurations. In addition, we prove that the regret upper bound of the ElasAction is sublinear, which guarantees its convergence and thus enables ElasticROS to be stable in its elasticity. Finally, we conducted experiments with ElasticROS on common tasks of robotics, including SLAM, grasping and human-robot dialogue, and then measured its performances in latency, CPU usage and power consumption. The algorithm-level ElasticROS performs significantly better than the present node-level system.