We present Integrated Multimodal Perception (IMP), a simple and scalable multimodal multi-task training and modeling approach. IMP integrates multimodal inputs including image, video, text, and audio into a single Transformer encoder with minimal modality-specific components. IMP makes use of a novel design that combines Alternating Gradient Descent (AGD) and Mixture-of-Experts (MoE) for efficient model and task scaling. We conduct extensive empirical studies and reveal the following key insights: 1) Performing gradient descent updates by alternating on diverse modalities, loss functions, and tasks, with varying input resolutions, efficiently improves the model. 2) Sparsification with MoE on a single modality-agnostic encoder substantially improves the performance, outperforming dense models that use modality-specific encoders or additional fusion layers and greatly mitigates the conflicts between modalities. IMP achieves competitive performance on a wide range of downstream tasks including video classification, image classification, image-text, and video-text retrieval. Most notably, we train a sparse IMP-MoE-L variant focusing on video tasks that achieves new state-of-the-art in zero-shot video classification: 77.0% on Kinetics-400, 76.8% on Kinetics-600, and 68.3% on Kinetics-700, improving the previous state-of-the-art by +5%, +6.7%, and +5.8%, respectively, while using only 15% of their total training computational cost.

We introduce "PatchMorph," an new stochastic deep learning algorithm tailored for unsupervised 3D brain image registration. Unlike other methods, our method uses compact patches of a constant small size to derive solutions that can combine global transformations with local deformations. This approach minimizes the memory footprint of the GPU during training, but also enables us to operate on numerous amounts of randomly overlapping small patches during inference to mitigate image and patch boundary problems. PatchMorph adeptly handles world coordinate transformations between two input images, accommodating variances in attributes such as spacing, array sizes, and orientations. The spatial resolution of patches transitions from coarse to fine, addressing both global and local attributes essential for aligning the images. Each patch offers a unique perspective, together converging towards a comprehensive solution. Experiments on human T1 MRI brain images and marmoset brain images from serial 2-photon tomography affirm PatchMorph's superior performance.

Perception of offensiveness is inherently subjective, shaped by the lived experiences and socio-cultural values of the perceivers. Recent years have seen substantial efforts to build AI-based tools that can detect offensive language at scale, as a means to moderate social media platforms, and to ensure safety of conversational AI technologies such as ChatGPT and Bard. However, existing approaches treat this task as a technical endeavor, built on top of data annotated for offensiveness by a global crowd workforce without any attention to the crowd workers' provenance or the values their perceptions reflect. We argue that cultural and psychological factors play a vital role in the cognitive processing of offensiveness, which is critical to consider in this context. We re-frame the task of determining offensiveness as essentially a matter of moral judgment -- deciding the boundaries of ethically wrong vs. right language within an implied set of socio-cultural norms. Through a large-scale cross-cultural study based on 4309 participants from 21 countries across 8 cultural regions, we demonstrate substantial cross-cultural differences in perceptions of offensiveness. More importantly, we find that individual moral values play a crucial role in shaping these variations: moral concerns about Care and Purity are significant mediating factors driving cross-cultural differences. These insights are of crucial importance as we build AI models for the pluralistic world, where the values they espouse should aim to respect and account for moral values in diverse geo-cultural contexts.

We present W.A.L.T, a transformer-based approach for photorealistic video generation via diffusion modeling. Our approach has two key design decisions. First, we use a causal encoder to jointly compress images and videos within a unified latent space, enabling training and generation across modalities. Second, for memory and training efficiency, we use a window attention architecture tailored for joint spatial and spatiotemporal generative modeling. Taken together these design decisions enable us to achieve state-of-the-art performance on established video (UCF-101 and Kinetics-600) and image (ImageNet) generation benchmarks without using classifier free guidance. Finally, we also train a cascade of three models for the task of text-to-video generation consisting of a base latent video diffusion model, and two video super-resolution diffusion models to generate videos of $512 \times 896$ resolution at $8$ frames per second.

We present WildHands, a method for 3D hand pose estimation in egocentric images in the wild. This is challenging due to (a) lack of 3D hand pose annotations for images in the wild, and (b) a form of perspective distortion-induced shape ambiguity that arises in the analysis of crops around hands. For the former, we use auxiliary supervision on in-the-wild data in the form of segmentation masks & grasp labels in addition to 3D supervision available in lab datasets. For the latter, we provide spatial cues about the location of the hand crop in the camera's field of view. Our approach achieves the best 3D hand pose on the ARCTIC leaderboard and outperforms FrankMocap, a popular and robust approach for estimating hand pose in the wild, by 45.3% when evaluated on 2D hand pose on our EPIC-HandKps dataset.

The concept of digital twin (DT), which enables the creation of a programmable, digital representation of physical systems, is expected to revolutionize future industries and will lie at the heart of the vision of a future smart society, namely, Society 5.0, in which high integration between cyber (digital) and physical spaces is exploited to bring economic and societal advancements. However, the success of such a DT-driven Society 5.0 requires a synergistic convergence of artificial intelligence and networking technologies into an integrated, programmable system that can coordinate networks of DTs to effectively deliver diverse Society 5.0 services. Prior works remain restricted to either qualitative study, simple analysis or software implementations of a single DT, and thus, they cannot provide the highly synergistic integration of digital and physical spaces as required by Society 5.0. In contrast, this paper envisions a novel concept of an Internet of Federated Digital Twins (IoFDT) that holistically integrates heterogeneous and physically separated DTs representing different Society 5.0 services within a single framework and system. For this concept of IoFDT, we first introduce a hierarchical architecture that integrates federated DTs through horizontal and vertical interactions, bridging the cyber and physical spaces to unlock new possibilities. Then, we discuss the challenges of realizing IoFDT, highlighting the intricacies across communication, computing, and AI-native networks while also underscoring potential innovative solutions. Subsequently, we elaborate on the importance of the implementation of a unified IoFDT platform that integrates all technical components and orchestrates their interactions, emphasizing the necessity of practical experimental platforms with a focus on real-world applications in areas like smart mobility.

Robotic Process Automation (RPA) has gained widespread adoption in corporate organizations, streamlining work processes while also introducing additional maintenance tasks. Effective governance of RPA can be achieved through the reusability of RPA components. However, refactoring RPA processes poses challenges when dealing with larger development teams, outsourcing, and staff turnover. This research aims to explore the possibility of identifying similarities in RPA processes for refactoring. To address this issue, we have developed Similarity Discovering Techniques for RPA (SiDiTeR). SiDiTeR utilizes source code or process logs from RPAautomations to search for similar or identical parts within RPA processes. The techniques introduced are specifically tailored to the RPA domain. We have expanded the potential matches by introducing a dictionary feature which helps identify different activities that produce the same output, and this has led to improved results in the RPA domain. Through our analysis, we have discovered 655 matches across 156 processes, with the longest match spanning 163 occurrences in 15 processes. Process similarity within the RPA domain proves to be a viable solution for mitigating the maintenance burden associated with RPA. This underscores the significance of process similarity in the RPA domain.

Monocular 3D human pose estimation (3D-HPE) is an inherently ambiguous task, as a 2D pose in an image might originate from different possible 3D poses. Yet, most 3D-HPE methods rely on regression models, which assume a one-to-one mapping between inputs and outputs. In this work, we provide theoretical and empirical evidence that, because of this ambiguity, common regression models are bound to predict topologically inconsistent poses, and that traditional evaluation metrics, such as the MPJPE, P-MPJPE and PCK, are insufficient to assess this aspect. As a solution, we propose ManiPose, a novel manifold-constrained multi-hypothesis model capable of proposing multiple candidate 3D poses for each 2D input, together with their corresponding plausibility. Unlike previous multi-hypothesis approaches, our solution is completely supervised and does not rely on complex generative models, thus greatly facilitating its training and usage. Furthermore, by constraining our model to lie within the human pose manifold, we can guarantee the consistency of all hypothetical poses predicted with our approach, which was not possible in previous works. We illustrate the usefulness of ManiPose in a synthetic 1D-to-2D lifting setting and demonstrate on real-world datasets that it outperforms state-of-the-art models in pose consistency by a large margin, while still reaching competitive MPJPE performance.

Time series refer to a series of data points indexed in time order, which can be found in various fields, e.g., transportation, healthcare, and finance. Accurate time series forecasting can enhance optimization planning and decision-making support. Time series have multi-scale characteristics, i.e., different temporal patterns at different scales, which presents a challenge for time series forecasting. In this paper, we propose TPRNN, a Top-down Pyramidal Recurrent Neural Network for time series forecasting. We first construct subsequences of different scales from the input, forming a pyramid structure. Then by executing a multi-scale information interaction module from top to bottom, we model both the temporal dependencies of each scale and the influences of subsequences of different scales, resulting in a complete modeling of multi-scale temporal patterns in time series. Experiments on seven real-world datasets demonstrate that TPRNN has achieved the state-of-the-art performance with an average improvement of 8.13% in MSE compared to the best baseline.

This paper addresses the often overlooked issue of fairness in the autonomous driving domain, particularly in vision-based perception and prediction systems, which play a pivotal role in the overall functioning of Autonomous Vehicles (AVs). We focus our analysis on biases present in some of the most commonly used visual datasets for training person and vehicle detection systems. We introduce an annotation methodology and a specialised annotation tool, both designed to annotate protected attributes of agents in visual datasets. We validate our methodology through an inter-rater agreement analysis and provide the distribution of attributes across all datasets. These include annotations for the attributes age, sex, skin tone, group, and means of transport for more than 90K people, as well as vehicle type, colour, and car type for over 50K vehicles. Generally, diversity is very low for most attributes, with some groups, such as children, wheelchair users, or personal mobility vehicle users, being extremely underrepresented in the analysed datasets. The study contributes significantly to efforts to consider fairness in the evaluation of perception and prediction systems for AVs. This paper follows reproducibility principles. The annotation tool, scripts and the annotated attributes can be accessed publicly at https://github.com/ec-jrc/humaint_annotator.