Temporal Knowledge Graph Completion (TKGC) is a challenging task of predicting missing event links at future timestamps by leveraging established temporal structural knowledge. Given the formidable generative capabilities inherent in LLMs (LLMs), this paper proposes a novel approach to conceptualize temporal link prediction as an event generation task within the context of a historical event chain. We employ efficient fine-tuning methods to make LLMs adapt to specific graph textual information and patterns discovered in temporal timelines. Furthermore, we introduce structure-based historical data augmentation and the integration of reverse knowledge to emphasize LLMs' awareness of structural information, thereby enhancing their reasoning capabilities. We conduct thorough experiments on multiple widely used datasets and find that our fine-tuned model outperforms existing embedding-based models on multiple metrics, achieving SOTA results. We also carry out sufficient ablation experiments to explore the key influencing factors when LLMs perform structured temporal knowledge inference tasks.
This paper presents null-shot prompting. Null-shot prompting exploits hallucination in large language models (LLMs) by instructing LLMs to utilize information from the "Examples" section that never exists within the provided context to perform a task. While reducing hallucination is crucial and non-negligible for daily and critical uses of LLMs, we propose that in the current landscape in which these LLMs still hallucinate, it is possible, in fact, to exploit hallucination to increase performance in performing tasks compared to standard zero-shot prompting. Experiments with six LLMs show improvements in performance across the majority of eight datasets, including reading comprehension, arithmetic reasoning, and closed-book question answering. The observed inconsistency in increased relative performance across LLMs also potentially indicates a different degree of inherent hallucination in each model. These differences show that it is possible to utilize null-shot prompting as a way to detect degrees of hallucination in LLMs using existing benchmarking datasets. We also perform ablation studies, including experimenting with a modified version of null-shot prompting that incorporates ideas from zero-shot chain-of-thought prompting, which shows different trends of results.
When there is a need to define and adapt a robotic task based on a reference motion, Dynamic Movement Primitives (DMP) is a standard and efficient method for encoding it. The nominal trajectory is typically obtained through a Programming by Demonstration (PbD) approach, where the robot is taught a specific task through kinesthetic guidance. Subsequently, the motion is reproduced by the manipulator in terms of both geometric path and timing law. The basic approach for modifying the duration of the execution involves adjusting a time constant characterizing the model. On the contrary, the goal of this paper is to achieve complete decoupling between the geometric information of the task, encoded into the DMP, and the phase law governing the execution, allowing them to be chosen independently. This enables the optimization of the task duration to satisfy constraints such as velocity or acceleration or even to define a phase law dependent on external inputs, such as the force applied by a user in a co-manipulation task. As an example, this mechanism will be exploited to define a rehabilitation activity where the cobot assists humans in performing various pre-planned exercises.
Minimally invasive surgery (MIS) has revolutionized many procedures and led to reduced recovery time and risk of patient injury. However, MIS poses additional complexity and burden on surgical teams. Data-driven surgical vision algorithms are thought to be key building blocks in the development of future MIS systems with improved autonomy. Recent advancements in machine learning and computer vision have led to successful applications in analyzing videos obtained from MIS with the promise of alleviating challenges in MIS videos. Surgical scene and action understanding encompasses multiple related tasks that, when solved individually, can be memory-intensive, inefficient, and fail to capture task relationships. Multitask learning (MTL), a learning paradigm that leverages information from multiple related tasks to improve performance and aid generalization, is wellsuited for fine-grained and high-level understanding of MIS data. This review provides an overview of the current state-of-the-art MTL systems that leverage videos obtained from MIS. Beyond listing published approaches, we discuss the benefits and limitations of these MTL systems. Moreover, this manuscript presents an analysis of the literature for various application fields of MTL in MIS, including those with large models, highlighting notable trends, new directions of research, and developments.
Image compression constitutes a significant challenge amidst the era of information explosion. Recent studies employing deep learning methods have demonstrated the superior performance of learning-based image compression methods over traditional codecs. However, an inherent challenge associated with these methods lies in their lack of interpretability. Following an analysis of the varying degrees of compression degradation across different frequency bands, we propose the end-to-end optimized image compression model facilitated by the frequency-oriented transform. The proposed end-to-end image compression model consists of four components: spatial sampling, frequency-oriented transform, entropy estimation, and frequency-aware fusion. The frequency-oriented transform separates the original image signal into distinct frequency bands, aligning with the human-interpretable concept. Leveraging the non-overlapping hypothesis, the model enables scalable coding through the selective transmission of arbitrary frequency components. Extensive experiments are conducted to demonstrate that our model outperforms all traditional codecs including next-generation standard H.266/VVC on MS-SSIM metric. Moreover, visual analysis tasks (i.e., object detection and semantic segmentation) are conducted to verify the proposed compression method could preserve semantic fidelity besides signal-level precision.
Completely occluded and dense object instance segmentation (IS) is an important and challenging task. Although current amodal IS methods can predict invisible regions of occluded objects, they are difficult to directly predict completely occluded objects. For dense object IS, existing box-based methods are overly dependent on the performance of bounding box detection. In this paper, we propose CFNet, a coarse-to-fine IS framework for completely occluded and dense objects, which is based on box prompt-based segmentation foundation models (BSMs). Specifically, CFNet first detects oriented bounding boxes (OBBs) to distinguish instances and provide coarse localization information. Then, it predicts OBB prompt-related masks for fine segmentation. To predict completely occluded object instances, CFNet performs IS on occluders and utilizes prior geometric properties, which overcomes the difficulty of directly predicting completely occluded object instances. Furthermore, based on BSMs, CFNet reduces the dependence on bounding box detection performance, improving dense object IS performance. Moreover, we propose a novel OBB prompt encoder for BSMs. To make CFNet more lightweight, we perform knowledge distillation on it and introduce a Gaussian smoothing method for teacher targets. Experimental results demonstrate that CFNet achieves the best performance on both industrial and publicly available datasets.
Keeping a vehicle well-localized within a prebuilt-map is at the core of any autonomous vehicle navigation system. In this work, we show that both standard SIR sampling and rejection-based optimal sampling are suitable for efficient (10 to 20 ms) real-time pose tracking without feature detection that is using raw point clouds from a 3D LiDAR. Motivated by the large amount of information captured by these sensors, we perform a systematic statistical analysis of how many points are actually required to reach an optimal ratio between efficiency and positioning accuracy. Furthermore, initialization from adverse conditions, e.g., poor GPS signal in urban canyons, we also identify the optimal particle filter settings required to ensure convergence. Our findings include that a decimation factor between 100 and 200 on incoming point clouds provides a large savings in computational cost with a negligible loss in localization accuracy for a VLP-16 scanner. Furthermore, an initial density of $\sim$2 particles/m$^2$ is required to achieve 100% convergence success for large-scale ($\sim$100,000 m$^2$), outdoor global localization without any additional hint from GPS or magnetic field sensors. All implementations have been released as open-source software.
3D Reconstruction of moving articulated objects without additional information about object structure is a challenging problem. Current methods overcome such challenges by employing category-specific skeletal models. Consequently, they do not generalize well to articulated objects in the wild. We treat an articulated object as an unknown, semi-rigid skeletal structure surrounded by nonrigid material (e.g., skin). Our method simultaneously estimates the visible (explicit) representation (3D shapes, colors, camera parameters) and the implicit skeletal representation, from motion cues in the object video without 3D supervision. Our implicit representation consists of four parts. (1) Skeleton, which specifies how semi-rigid parts are connected. (2) \textcolor{black}{Skinning Weights}, which associates each surface vertex with semi-rigid parts with probability. (3) Rigidity Coefficients, specifying the articulation of the local surface. (4) Time-Varying Transformations, which specify the skeletal motion and surface deformation parameters. We introduce an algorithm that uses physical constraints as regularization terms and iteratively estimates both implicit and explicit representations. Our method is category-agnostic, thus eliminating the need for category-specific skeletons, we show that our method outperforms state-of-the-art across standard video datasets.
As a tech company, Grab has expanded from transportation to food delivery, aiming to serve Southeast Asia with hyperlocalized applications. Information about places as transportation destinations can help to improve our knowledge about places as restaurants, so long as the spatial entity resolution problem between these datasets can be solved. In this project, we attempted to recognize identical place entities from databases of Points-of-Interest (POI) and GrabFood restaurants, using their spatial and textual attributes, i.e., latitude, longitude, place name, and street address. Distance metrics were calculated for these attributes and fed to tree-based classifiers. POI-restaurant matching was conducted separately for Singapore, Philippines, Indonesia, and Malaysia. Experimental estimates demonstrate that a matching POI can be found for over 35% of restaurants in these countries. As part of these estimates, test datasets were manually created, and RandomForest, AdaBoost, Gradient Boosting, and XGBoost perform well, with most accuracy, precision, and recall scores close to or higher than 90% for matched vs. unmatched classification. To the authors' knowledge, there are no previous published scientific papers devoted to matching of spatial entities for the Southeast Asia region.
Black-box deep learning approaches have showcased significant potential in the realm of medical image analysis. However, the stringent trustworthiness requirements intrinsic to the medical field have catalyzed research into the utilization of Explainable Artificial Intelligence (XAI), with a particular focus on concept-based methods. Existing concept-based methods predominantly apply concept annotations from a single perspective (e.g., global level), neglecting the nuanced semantic relationships between sub-regions and concepts embedded within medical images. This leads to underutilization of the valuable medical information and may cause models to fall short in harmoniously balancing interpretability and performance when employing inherently interpretable architectures such as Concept Bottlenecks. To mitigate these shortcomings, we propose a multi-modal explainable disease diagnosis framework that meticulously aligns medical images and clinical-related concepts semantically at multiple strata, encompassing the image level, token level, and concept level. Moreover, our method allows for model intervention and offers both textual and visual explanations in terms of human-interpretable concepts. Experimental results on three skin image datasets demonstrate that our method, while preserving model interpretability, attains high performance and label efficiency for concept detection and disease diagnosis.