Philipp Slusallek

Anindita Ghosh, Rishabh Dabral, Vladislav Golyanik et al.

Can we make virtual characters in a scene interact with their surrounding objects through simple instructions? Is it possible to synthesize such motion plausibly with a diverse set of objects and instructions? Inspired by these questions, we present the first framework to synthesize the full-body motion of virtual human characters performing specified actions with 3D objects placed within their reach. Our system takes textual instructions specifying the objects and the associated intentions of the virtual characters as input and outputs diverse sequences of full-body motions. This contrasts existing works, where full-body action synthesis methods generally do not consider object interactions, and human-object interaction methods focus mainly on synthesizing hand or finger movements for grasping objects. We accomplish our objective by designing an intent-driven fullbody motion generator, which uses a pair of decoupled conditional variational auto-regressors to learn the motion of the body parts in an autoregressive manner. We also optimize the 6-DoF pose of the objects such that they plausibly fit within the hands of the synthesized characters. We compare our proposed method with the existing methods of motion synthesis and establish a new and stronger state-of-the-art for the task of intent-driven motion synthesis.

Anindita Ghosh, Rishabh Dabral, Vladislav Golyanik et al.

Current approaches for 3D human motion synthesis generate high quality animations of digital humans performing a wide variety of actions and gestures. However, a notable technological gap exists in addressing the complex dynamics of multi human interactions within this paradigm. In this work, we present ReMoS, a denoising diffusion based model that synthesizes full body reactive motion of a person in a two person interaction scenario. Given the motion of one person, we employ a combined spatio temporal cross attention mechanism to synthesize the reactive body and hand motion of the second person, thereby completing the interactions between the two. We demonstrate ReMoS across challenging two person scenarios such as pair dancing, Ninjutsu, kickboxing, and acrobatics, where one persons movements have complex and diverse influences on the other. We also contribute the ReMoCap dataset for two person interactions containing full body and finger motions. We evaluate ReMoS through multiple quantitative metrics, qualitative visualizations, and a user study, and also indicate usability in interactive motion editing applications.

Israel Abebe Azime, Jesujoba Oluwadara Alabi, Crystina Zhang et al.

Assessing the veracity of a claim made online is a complex and important task with real-world implications. When these claims are directed at communities with limited access to information and the content concerns issues such as healthcare and culture, the consequences intensify, especially in low-resource languages. In this work, we introduce AfrIFact, a dataset that covers the necessary steps for automatic fact-checking (i.e., information retrieval, evidence extraction, and fact checking), in ten African languages and English. Our evaluation results show that even the best embedding models lack cross-lingual retrieval capabilities, and that cultural and news documents are easier to retrieve than healthcare-domain documents, both in large corpora and in single documents. We show that LLMs lack robust multilingual fact-verification capabilities in African languages, while few-shot prompting improves performance by up to 43% in AfriqueQwen-14B, and task-specific fine-tuning further improves fact-checking accuracy by up to 26%. These findings, along with our release of the AfrIFact dataset, encourage work on low-resource information retrieval, evidence retrieval, and fact checking.

Manuela Schuler, Richard Membarth, Philipp Slusallek

Memory efficiency is crucial in training deep learning networks on resource-restricted devices. During backpropagation, forward tensors are used to calculate gradients. Despite the option of keeping those dependencies in memory until they are reused in backpropagation, some forward tensors can be discarded and recomputed later from saved tensors, so-called checkpoints. This allows, in particular, for resource-constrained heterogeneous environments to make use of all available compute devices. Unfortunately, the definition of these checkpoints is a non-trivial problem and poses a challenge to the programmer - improper or excessive recomputations negate the benefit of checkpointing. In this article, we present XEngine, an approach that schedules network operators to heterogeneous devices in low memory environments by determining checkpoints and recomputations of tensors. Our approach selects suitable resources per timestep and operator and optimizes the end-to-end time for neural networks taking the memory limitation of each device into account. For this, we formulate a mixed-integer quadratic program (MIQP) to schedule operators of deep learning networks on heterogeneous systems. We compare our MIQP solver XEngine against Checkmate, a mixed-integer linear programming (MILP) approach that solves recomputation on a single device. Our solver finds solutions that are up to 22.5 % faster than the fastest Checkmate schedule in which the network is computed exclusively on a single device. We also find valid schedules for networks making use of both central processing units and graphics processing units if memory limitations do not allow scheduling exclusively to the graphics processing unit.

Anindita Ghosh, Vladislav Golyanik, Taku Komura et al.

Synthesizing text-driven 3D human motion within realistic scenes requires learning both semantic intent ("walk to the couch") and physical feasibility (e.g., avoiding collisions). Current methods use generative frameworks that simultaneously learn high-level planning and low-level contact reasoning, and rely on computationally expensive 3D scene data such as point clouds or voxel occupancy grids. We propose SceMoS, a scene-aware motion synthesis framework that shows that structured 2D scene representations can serve as a powerful alternative to full 3D supervision in physically grounded motion synthesis. SceMoS disentangles global planning from local execution using lightweight 2D cues and relying on (1) a text-conditioned autoregressive global motion planner that operates on a bird's-eye-view (BEV) image rendered from an elevated corner of the scene, encoded with DINOv2 features, as the scene representation, and (2) a geometry-grounded motion tokenizer trained via a conditional VQ-VAE, that uses 2D local scene heightmap, thus embedding surface physics directly into a discrete vocabulary. This 2D factorization reaches an efficiency-fidelity trade-off: BEV semantics capture spatial layout and affordance for global reasoning, while local heightmaps enforce fine-grained physical adherence without full 3D volumetric reasoning. SceMoS achieves state-of-the-art motion realism and contact accuracy on the TRUMANS benchmark, reducing the number of trainable parameters for scene encoding by over 50%, showing that 2D scene cues can effectively ground 3D human-scene interaction.

Atnafu Lambebo Tonja, Israel Abebe Azime, Tadesse Destaw Belay et al.

Large language models (LLMs) have gained popularity recently due to their outstanding performance in various downstream Natural Language Processing (NLP) tasks. However, low-resource languages are still lagging behind current state-of-the-art (SOTA) developments in the field of NLP due to insufficient resources to train LLMs. Ethiopian languages exhibit remarkable linguistic diversity, encompassing a wide array of scripts, and are imbued with profound religious and cultural significance. This paper introduces EthioLLM -- multilingual large language models for five Ethiopian languages (Amharic, Ge'ez, Afan Oromo, Somali, and Tigrinya) and English, and Ethiobenchmark -- a new benchmark dataset for various downstream NLP tasks. We evaluate the performance of these models across five downstream NLP tasks. We open-source our multilingual language models, new benchmark datasets for various downstream tasks, and task-specific fine-tuned language models and discuss the performance of the models. Our dataset and models are available at the https://huggingface.co/EthioNLP repository.

Israel Abebe Azime, Atnafu Lambebo Tonja, Tadesse Destaw Belay et al.

With the rapid development of evaluation datasets to assess LLMs understanding across a wide range of subjects and domains, identifying a suitable language understanding benchmark has become increasingly challenging. In this work, we explore LLM evaluation challenges for low-resource language understanding and introduce \proverbeval, LLM evaluation benchmark for low-resource languages, focusing on low-resource language understanding in culture-specific scenarios. We benchmark various LLMs and explore factors that create variability in the benchmarking process. We observed performance variances of up to 50\%, depending on the order in which answer choices were presented in multiple-choice tasks. Native language proverb descriptions significantly improve tasks such as proverb generation, contributing to improved outcomes. Additionally, monolingual evaluations consistently outperformed their cross-lingual counterparts in generation tasks. We argue that special attention must be given to the order of choices, the choice of prompt language, task variability, and generation tasks when creating LLM evaluation benchmarks. Evaluation data available at https://huggingface.co/datasets/israel/ProverbEval, evaluation code https://github.com/EthioNLP/EthioProverbEval.

Tadesse Destaw Belay, Israel Abebe Azime, Abinew Ali Ayele et al.

Large Language Models (LLMs) show promising learning and reasoning abilities. Compared to other NLP tasks, multilingual and multi-label emotion evaluation tasks are under-explored in LLMs. In this paper, we present EthioEmo, a multi-label emotion classification dataset for four Ethiopian languages, namely, Amharic (amh), Afan Oromo (orm), Somali (som), and Tigrinya (tir). We perform extensive experiments with an additional English multi-label emotion dataset from SemEval 2018 Task 1. Our evaluation includes encoder-only, encoder-decoder, and decoder-only language models. We compare zero and few-shot approaches of LLMs to fine-tuning smaller language models. The results show that accurate multi-label emotion classification is still insufficient even for high-resource languages such as English, and there is a large gap between the performance of high-resource and low-resource languages. The results also show varying performance levels depending on the language and model type. EthioEmo is available publicly to further improve the understanding of emotions in language models and how people convey emotions through various languages.

Farzad Nozarian, Shashank Agarwal, Farzaneh Rezaeianaran et al.

Semi-supervised 3D object detection can benefit from the promising pseudo-labeling technique when labeled data is limited. However, recent approaches have overlooked the impact of noisy pseudo-labels during training, despite efforts to enhance pseudo-label quality through confidence-based filtering. In this paper, we examine the impact of noisy pseudo-labels on IoU-based target assignment and propose the Reliable Student framework, which incorporates two complementary approaches to mitigate errors. First, it involves a class-aware target assignment strategy that reduces false negative assignments in difficult classes. Second, it includes a reliability weighting strategy that suppresses false positive assignment errors while also addressing remaining false negatives from the first step. The reliability weights are determined by querying the teacher network for confidence scores of the student-generated proposals. Our work surpasses the previous state-of-the-art on KITTI 3D object detection benchmark on point clouds in the semi-supervised setting. On 1% labeled data, our approach achieves a 6.2% AP improvement for the pedestrian class, despite having only 37 labeled samples available. The improvements become significant for the 2% setting, achieving 6.0% AP and 5.7% AP improvements for the pedestrian and cyclist classes, respectively.

Paloma García-de-Herreros, Vagrant Gautam, Philipp Slusallek et al.

ORCA (Shen et al., 2023) is a recent technique for cross-modal fine-tuning, i.e., applying pre-trained transformer models to modalities beyond their training data. The technique consists primarily of training an embedder and fine-tuning the embedder and model. Despite its high performance on a variety of downstream tasks, we do not understand precisely how each of these components contribute to ORCA's success. Therefore, we run a series of ablations and find that embedder training does not help 2D tasks at all, contrary to what the original paper posits. In 1D tasks, some amount of embedder training is necessary but more is not better. In 4 out of 6 datasets we experiment with, it is model fine-tuning that makes the biggest difference. Through our ablations and baselines, we contribute a better understanding of the individual components of ORCA.

Igor Vozniak, Philipp Mueller, Nils Lipp et al.

The object-based nature of human visual attention is well-known in cognitive science, but has only played a minor role in computational visual attention models so far. This is mainly due to a lack of suitable datasets and evaluation metrics for object-based attention. To address these limitations, we present \dataset~ -- a novel 120-participant dataset of spatial street-crossing navigation in virtual reality specifically geared to object-based attention evaluations. The uniqueness of the presented dataset lies in the ethical and safety affiliated challenges that make collecting comparable data in real-world environments highly difficult. \dataset~ not only features accurate gaze data and a complete state-space representation of objects in the virtual environment, but it also offers variable scenario complexities and rich annotations, including panoptic segmentation, depth information, and vehicle keypoints. We further propose object-based similarity (oSIM) as a novel metric to evaluate the performance of object-based visual attention models, a previously unexplored performance characteristic. Our evaluations show that explicitly optimising for object-based attention not only improves oSIM performance but also leads to an improved model performance on common metrics. In addition, we present SUMGraph, a Mamba U-Net-based model, which explicitly encodes critical scene objects (vehicles) in a graph representation, leading to further performance improvements over several state-of-the-art visual attention prediction methods. The dataset, code and models will be publicly released.

Israel Abebe Azime, Abenezer Kebede Angamo, Hana Mekonen Tamiru et al.

With the growing emphasis on multilingual and cultural evaluation benchmarks for large language models, language and culture are often treated as synonymous, and performance is commonly used as a proxy for a models understanding of a given language. In this work, we argue that such evaluations overlook meaningful cultural variation that exists within a single language. We address this gap by focusing on narratives from different regions of Ethiopia and demonstrate that, despite shared linguistic characteristics, region-specific and domain-specific content substantially influences language evaluation outcomes. To this end, we introduce \textbf{\textit{AmharicStoryQA}}, a long-sequence story question answering benchmark grounded in culturally diverse narratives from Amharic-speaking regions. Using this benchmark, we reveal a significant narrative understanding gap in existing LLMs, highlight pronounced regional differences in evaluation results, and show that supervised fine-tuning yields uneven improvements across regions and evaluation settings. Our findings emphasize the need for culturally grounded benchmarks that go beyond language-level evaluation to more accurately assess and improve narrative understanding in low-resource languages.

Mehran Jeelani, Sadbhawna, Noshaba Cheema et al.

Video super-resolution (VSR) techniques, especially deep-learning-based algorithms, have drastically improved over the last few years and shown impressive performance on synthetic data. However, their performance on real-world video data suffers because of the complexity of real-world degradations and misaligned video frames. Since obtaining a synthetic dataset consisting of low-resolution (LR) and high-resolution (HR) frames are easier than obtaining real-world LR and HR images, in this paper, we propose synthesizing real-world degradations on synthetic training datasets. The proposed synthetic real-world degradations (SRWD) include a combination of the blur, noise, downsampling, pixel binning, and image and video compression artifacts. We then propose using a random shuffling-based strategy to simulate these degradations on the training datasets and train a single end-to-end deep neural network (DNN) on the proposed larger variation of realistic synthesized training data. Our quantitative and qualitative comparative analysis shows that the proposed training strategy using diverse realistic degradations improves the performance by 7.1 % in terms of NRQM compared to RealBasicVSR and by 3.34 % compared to BSRGAN on the VideoLQ dataset. We also introduce a new dataset that contains high-resolution real-world videos that can serve as a common ground for bench-marking.

Elena Kosheleva, Sunil Jaiswal, Faranak Shamsafar et al.

Video depth estimation is crucial in various applications, such as scene reconstruction and augmented reality. In contrast to the naive method of estimating depths from images, a more sophisticated approach uses temporal information, thereby eliminating flickering and geometrical inconsistencies. We propose a consistent method for dense video depth estimation; however, unlike the existing monocular methods, ours relates to stereo videos. This technique overcomes the limitations arising from the monocular input. As a benefit of using stereo inputs, a left-right consistency loss is introduced to improve the performance. Besides, we use SLAM-based camera pose estimation in the process. To address the problem of depth blurriness during test-time training (TTT), we present an edge-preserving loss function that improves the visibility of fine details while preserving geometrical consistency. We show that our edge-aware stereo video model can accurately estimate the dense depth maps.

Aakash Rajpal, Noshaba Cheema, Klaus Illgner-Fehns et al.

Accurate depth maps are essential in various applications, such as autonomous driving, scene reconstruction, point-cloud creation, etc. However, monocular-depth estimation (MDE) algorithms often fail to provide enough texture & sharpness, and also are inconsistent for homogeneous scenes. These algorithms mostly use CNN or vision transformer-based architectures requiring large datasets for supervised training. But, MDE algorithms trained on available depth datasets do not generalize well and hence fail to perform accurately in diverse real-world scenes. Moreover, the ground-truth depth maps are either lower resolution or sparse leading to relatively inconsistent depth maps. In general, acquiring a high-resolution ground truth dataset with pixel-level precision for accurate depth prediction is an expensive, and time-consuming challenge. In this paper, we generate a high-resolution synthetic depth dataset (HRSD) of dimension 1920 X 1080 from Grand Theft Auto (GTA-V), which contains 100,000 color images and corresponding dense ground truth depth maps. The generated datasets are diverse and have scenes from indoors to outdoors, from homogeneous surfaces to textures. For experiments and analysis, we train the DPT algorithm, a state-of-the-art transformer-based MDE algorithm on the proposed synthetic dataset, which significantly increases the accuracy of depth maps on different scenes by 9 %. Since the synthetic datasets are of higher resolution, we propose adding a feature extraction module in the transformer encoder and incorporating an attention-based loss, further improving the accuracy by 15 %.

Anindita Ghosh, Noshaba Cheema, Cennet Oguz et al.

"How can we animate 3D-characters from a movie script or move robots by simply telling them what we would like them to do?" "How unstructured and complex can we make a sentence and still generate plausible movements from it?" These are questions that need to be answered in the long-run, as the field is still in its infancy. Inspired by these problems, we present a new technique for generating compositional actions, which handles complex input sentences. Our output is a 3D pose sequence depicting the actions in the input sentence. We propose a hierarchical two-stream sequential model to explore a finer joint-level mapping between natural language sentences and 3D pose sequences corresponding to the given motion. We learn two manifold representations of the motion -- one each for the upper body and the lower body movements. Our model can generate plausible pose sequences for short sentences describing single actions as well as long compositional sentences describing multiple sequential and superimposed actions. We evaluate our proposed model on the publicly available KIT Motion-Language Dataset containing 3D pose data with human-annotated sentences. Experimental results show that our model advances the state-of-the-art on text-based motion synthesis in objective evaluations by a margin of 50%. Qualitative evaluations based on a user study indicate that our synthesized motions are perceived to be the closest to the ground-truth motion captures for both short and compositional sentences.

Eduardo Sánchez Morales, Richard Membarth, Andreas Gaull et al.

Due to the current developments towards autonomous driving and vehicle active safety, there is an increasing necessity for algorithms that are able to perform complex criticality predictions in real-time. Being able to process multi-object traffic scenarios aids the implementation of a variety of automotive applications such as driver assistance systems for collision prevention and mitigation as well as fall-back systems for autonomous vehicles. We present a fully model-based algorithm with a parallelizable architecture. The proposed algorithm can evaluate the criticality of complex, multi-modal (vehicles and pedestrians) traffic scenarios by simulating millions of trajectory combinations and detecting collisions between objects. The algorithm is able to estimate upcoming criticality at very early stages, demonstrating its potential for vehicle safety-systems and autonomous driving applications. An implementation on an embedded system in a test vehicle proves in a prototypical manner the compatibility of the algorithm with the hardware possibilities of modern cars. For a complex traffic scenario with 11 dynamic objects, more than 86 million pose combinations are evaluated in 21 ms on the GPU of a Drive PX~2.

Georg Rehm, Katrin Marheinecke, Stefanie Hegele et al.

Multilingualism is a cultural cornerstone of Europe and firmly anchored in the European treaties including full language equality. However, language barriers impacting business, cross-lingual and cross-cultural communication are still omnipresent. Language Technologies (LTs) are a powerful means to break down these barriers. While the last decade has seen various initiatives that created a multitude of approaches and technologies tailored to Europe's specific needs, there is still an immense level of fragmentation. At the same time, AI has become an increasingly important concept in the European Information and Communication Technology area. For a few years now, AI, including many opportunities, synergies but also misconceptions, has been overshadowing every other topic. We present an overview of the European LT landscape, describing funding programmes, activities, actions and challenges in the different countries with regard to LT, including the current state of play in industry and the LT market. We present a brief overview of the main LT-related activities on the EU level in the last ten years and develop strategic guidance with regard to four key dimensions.

Noshaba Cheema, Somayeh Hosseini, Janis Sprenger et al.

Human motion capture data has been widely used in data-driven character animation. In order to generate realistic, natural-looking motions, most data-driven approaches require considerable efforts of pre-processing, including motion segmentation and annotation. Existing (semi-) automatic solutions either require hand-crafted features for motion segmentation or do not produce the semantic annotations required for motion synthesis and building large-scale motion databases. In addition, human labeled annotation data suffers from inter- and intra-labeler inconsistencies by design. We propose a semi-automatic framework for semantic segmentation of motion capture data based on supervised machine learning techniques. It first transforms a motion capture sequence into a ``motion image'' and applies a convolutional neural network for image segmentation. Dilated temporal convolutions enable the extraction of temporal information from a large receptive field. Our model outperforms two state-of-the-art models for action segmentation, as well as a popular network for sequence modeling. Most of all, our method is very robust under noisy and inaccurate training labels and thus can handle human errors during the labeling process.

Noshaba Cheema, Somayeh Hosseini, Janis Sprenger et al.

Semantic segmentation of motion capture sequences plays a key part in many data-driven motion synthesis frameworks. It is a preprocessing step in which long recordings of motion capture sequences are partitioned into smaller segments. Afterwards, additional methods like statistical modeling can be applied to each group of structurally-similar segments to learn an abstract motion manifold. The segmentation task however often remains a manual task, which increases the effort and cost of generating large-scale motion databases. We therefore propose an automatic framework for semantic segmentation of motion capture data using a dilated temporal fully-convolutional network. Our model outperforms a state-of-the-art model in action segmentation, as well as three networks for sequence modeling. We further show our model is robust against high noisy training labels.

Patrick Trampert, Faysal Bourghorbel, Pavel Potocek et al.

In scanning electron microscopy, the achievable image quality is often limited by a maximum feasible acquisition time per dataset. Particularly with regard to three-dimensional or large field-of-view imaging, a compromise must be found between a high amount of shot noise, which leads to a low signal-to-noise ratio, and excessive acquisition times. Assuming a fixed acquisition time per frame, we compared three different strategies for algorithm-assisted image acquisition in scanning electron microscopy. We evaluated (1) raster scanning with a reduced dwell time per pixel followed by a state-of-the-art Denoising algorithm, (2) raster scanning with a decreased resolution in conjunction with a state-of-the-art Super Resolution algorithm, and (3) a sparse scanning approach where a fixed percentage of pixels is visited by the beam in combination with state-of-the-art inpainting algorithms. Additionally, we considered increased beam currents for each of the strategies. The experiments showed that sparse scanning using an appropriate reconstruction technique was superior to the other strategies.