arXiv subjects

Roger Zimmermann

Publications and source records attributed to Roger Zimmermann.

At least 37 records · Page 2Linked to original sources

arXiv2025

Uni3D-MoE: Scalable Multimodal 3D Scene Understanding via Mixture of Experts

Recent advancements in multimodal large language models (MLLMs) have demonstrated considerable potential for comprehensive 3D scene understanding. However, existing approaches typically utilize only one or a limited subset of 3D modalities, resulting in incomplete representations of 3D scenes and reduced interpretive accuracy. Furthermore, different types of queries inherently depend on distinct modalities, indicating that uniform processing of all modality tokens may fail to effectively capture query-specific context. To address these challenges, we propose Uni3D-MoE, a sparse Mixture-of-Experts (MoE)-based 3D MLLM designed to enable adaptive 3D multimodal fusion. Specifically, Uni3D-MoE integrates a comprehensive set of 3D modalities, including multi-view RGB and depth images, bird's-eye-view (BEV) maps, point clouds, and voxel representations. At its core, our framework employs a learnable routing mechanism within the sparse MoE-based large language model, dynamically selecting appropriate experts at the token level. Each expert specializes in processing multimodal tokens based on learned modality preferences, thus facilitating flexible collaboration tailored to diverse task-specific requirements. Extensive evaluations on standard 3D scene understanding benchmarks and specialized datasets demonstrate the efficacy of Uni3D-MoE.

cs.CV↗

arXiv2025

JointDistill: Adaptive Multi-Task Distillation for Joint Depth Estimation and Scene Segmentation

Depth estimation and scene segmentation are two important tasks in intelligent transportation systems. A joint modeling of these two tasks will reduce the requirement for both the storage and training efforts. This work explores how the multi-task distillation could be used to improve such unified modeling. While existing solutions transfer multiple teachers' knowledge in a static way, we propose a self-adaptive distillation method that can dynamically adjust the knowledge amount from each teacher according to the student's current learning ability. Furthermore, as multiple teachers exist, the student's gradient update direction in the distillation is more prone to be erroneous where knowledge forgetting may occur. To avoid this, we propose a knowledge trajectory to record the most essential information that a model has learnt in the past, based on which a trajectory-based distillation loss is designed to guide the student to follow the learning curve similarly in a cost-effective way. We evaluate our method on multiple benchmarking datasets including Cityscapes and NYU-v2. Compared to the state-of-the-art solutions, our method achieves a clearly improvement. The code is provided in the supplementary materials.

cs.LG↗

arXiv2025

Toward One-Second Latency: Evolution of Live Media Streaming

This survey presents the evolution of live media streaming and the technological developments behind today's IP-based low-latency live streaming systems. Live streaming primarily involves capturing, encoding, packaging and delivering real-time events such as live sports, live news, personal broadcasts and surveillance videos. Live streaming also involves concurrent streaming of linear TV programming off the satellite, cable, over-the-air or IPTV broadcast, where the programming is not necessarily a real-time event. The survey starts with a discussion on the latency and latency continuum in streaming applications. Then, it lays out the existing live streaming workflows and protocols, followed by an in-depth analysis of the latency sources in these workflows and protocols. The survey continues with the technology enablers, low-latency extensions for the popular HTTP adaptive streaming methods and enhancements for robust low-latency playback. An entire section is dedicated to the detailed summary and findings of Twitch's grand challenge on low-latency live streaming. The survey concludes with a discussion of ongoing research problems in this space. We expect this survey to be the one-stop reference for those who would like to learn how low-latency live streaming has evolved and works today, and what further developments could happen in the future.

cs.NI↗

arXiv2025

Through the Dual-Prism: A Spectral Perspective on Graph Data Augmentation for Graph Classification

Graph Neural Networks have become the preferred tool to process graph data, with their efficacy being boosted through graph data augmentation techniques. Despite the evolution of augmentation methods, issues like graph property distortions and restricted structural changes persist. This leads to the question: Is it possible to develop more property-conserving and structure-sensitive augmentation methods? Through a spectral lens, we investigate the interplay between graph properties, their augmentation, and their spectral behavior, and observe that keeping the low-frequency eigenvalues unchanged can preserve the critical properties at a large scale when generating augmented graphs. These observations inform our introduction of the Dual-Prism (DP) augmentation methods, including DP-Noise and DP-Mask, which retain essential graph properties while diversifying augmented graphs. Extensive experiments validate the efficiency of our approach, providing a new and promising direction for graph data augmentation.

cs.LG↗

arXiv2025

LaDe: The First Comprehensive Last-mile Delivery Dataset from Industry

Real-world last-mile delivery datasets are crucial for research in logistics, supply chain management, and spatio-temporal data mining. Despite a plethora of algorithms developed to date, no widely accepted, publicly available last-mile delivery dataset exists to support research in this field. In this paper, we introduce \texttt{LaDe}, the first publicly available last-mile delivery dataset with millions of packages from the industry. LaDe has three unique characteristics: (1) Large-scale. It involves 10,677k packages of 21k couriers over 6 months of real-world operation. (2) Comprehensive information. It offers original package information, such as its location and time requirements, as well as task-event information, which records when and where the courier is while events such as task-accept and task-finish events happen. (3) Diversity. The dataset includes data from various scenarios, including package pick-up and delivery, and from multiple cities, each with its unique spatio-temporal patterns due to their distinct characteristics such as populations. We verify LaDe on three tasks by running several classical baseline models per task. We believe that the large-scale, comprehensive, diverse feature of LaDe can offer unparalleled opportunities to researchers in the supply chain community, data mining community, and beyond. The dataset homepage is publicly available at https://huggingface.co/datasets/Cainiao-AI/LaDe.

cs.DB↗

arXiv2024

Improving Multimodal LLMs Ability In Geometry Problem Solving, Reasoning, And Multistep Scoring

This paper presents GPSM4K, a comprehensive geometry multimodal dataset tailored to augment the problem-solving capabilities of Large Vision Language Models (LVLMs). GPSM4K encompasses 2157 multimodal question-answer pairs manually extracted from mathematics textbooks spanning grades 7-12 and is further augmented to 5340 problems, consisting of both numerical and theorem-proving questions. In contrast to PGPS9k, Geometry3K, and Geo170K which feature only objective-type questions, GPSM4K offers detailed step-by-step solutions in a consistent format, facilitating a comprehensive evaluation of problem-solving approaches. This dataset serves as an excellent benchmark for assessing the geometric reasoning capabilities of LVLMs. Evaluation of our test set shows that there is scope for improvement needed in open-source language models in geometry problem-solving. Finetuning on our training set increases the geometry problem-solving capabilities of models. Further, We also evaluate the effectiveness of techniques such as image captioning and Retrieval Augmentation generation (RAG) on model performance. We leveraged LLM to automate the task of final answer evaluation by providing ground truth and predicted solutions. This research will help to assess and improve the geometric reasoning capabilities of LVLMs.

cs.AI↗

arXiv2024

Backpropagation-Free Multi-modal On-Device Model Adaptation via Cloud-Device Collaboration

In our increasingly interconnected world, where intelligent devices continually amass copious personalized multi-modal data, a pressing need arises to deliver high-quality, personalized device-aware services. However, this endeavor presents a multifaceted challenge to prevailing artificial intelligence (AI) systems primarily rooted in the cloud. As these systems grapple with shifting data distributions between the cloud and devices, the traditional approach of fine-tuning-based adaptation (FTA) exists the following issues: the costly and time-consuming data annotation required by FTA and the looming risk of model overfitting. To surmount these challenges, we introduce a Universal On-Device Multi-modal Model Adaptation Framework, revolutionizing on-device model adaptation by striking a balance between efficiency and effectiveness. The framework features the Fast Domain Adaptor (FDA) hosted in the cloud, providing tailored parameters for the Lightweight Multi-modal Model on devices. To enhance adaptability across multi-modal tasks, the AnchorFrame Distribution Reasoner (ADR) minimizes communication costs. Our contributions, encapsulated in the Cloud-Device Collaboration Multi-modal Parameter Generation (CDC-MMPG) framework, represent a pioneering solution for on-Device Multi-modal Model Adaptation (DMMA). Extensive experiments validate the efficiency and effectiveness of our method, particularly in video question answering and retrieval tasks, driving forward the integration of intelligent devices into our daily lives.

cs.DC↗

arXiv2024

Grounding is All You Need? Dual Temporal Grounding for Video Dialog

In the realm of video dialog response generation, the understanding of video content and the temporal nuances of conversation history are paramount. While a segment of current research leans heavily on large-scale pretrained visual-language models and often overlooks temporal dynamics, another delves deep into spatial-temporal relationships within videos but demands intricate object trajectory pre-extractions and sidelines dialog temporal dynamics. This paper introduces the Dual Temporal Grounding-enhanced Video Dialog model (DTGVD), strategically designed to merge the strengths of both dominant approaches. It emphasizes dual temporal relationships by predicting dialog turn-specific temporal regions, filtering video content accordingly, and grounding responses in both video and dialog contexts. One standout feature of DTGVD is its heightened attention to chronological interplay. By recognizing and acting upon the dependencies between different dialog turns, it captures more nuanced conversational dynamics. To further bolster the alignment between video and dialog temporal dynamics, we've implemented a list-wise contrastive learning strategy. Within this framework, accurately grounded turn-clip pairings are designated as positive samples, while less precise pairings are categorized as negative. This refined classification is then funneled into our holistic end-to-end response generation mechanism. Evaluations using AVSD@DSTC-7 and AVSD@DSTC-8 datasets underscore the superiority of our methodology.

cs.CV↗

arXiv2024

Prompt-Based Spatio-Temporal Graph Transfer Learning

Spatio-temporal graph neural networks have proven efficacy in capturing complex dependencies for urban computing tasks such as forecasting and kriging. Yet, their performance is constrained by the reliance on extensive data for training on a specific task, thereby limiting their adaptability to new urban domains with varied task demands. Although transfer learning has been proposed to remedy this problem by leveraging knowledge across domains, the cross-task generalization still remains under-explored in spatio-temporal graph transfer learning due to the lack of a unified framework. To bridge the gap, we propose Spatio-Temporal Graph Prompting (STGP), a prompt-based framework capable of adapting to multi-diverse tasks in a data-scarce domain. Specifically, we first unify different tasks into a single template and introduce a task-agnostic network architecture that aligns with this template. This approach enables capturing dependencies shared across tasks. Furthermore, we employ learnable prompts to achieve domain and task transfer in a two-stage prompting pipeline, facilitating the prompts to effectively capture domain knowledge and task-specific properties. Our extensive experiments demonstrate that STGP outperforms state-of-the-art baselines in three tasks-forecasting, kriging, and extrapolation-achieving an improvement of up to 10.7%.

cs.LG↗

arXiv2024

Manifold-Aware Local Feature Modeling for Semi-Supervised Medical Image Segmentation

Achieving precise medical image segmentation is vital for effective treatment planning and accurate disease diagnosis. Traditional fully-supervised deep learning methods, though highly precise, are heavily reliant on large volumes of labeled data, which are often difficult to obtain due to the expertise required for medical annotations. This has led to the rise of semi-supervised learning approaches that utilize both labeled and unlabeled data to mitigate the label scarcity issue. In this paper, we introduce the Manifold-Aware Local Feature Modeling Network (MANet), which enhances the U-Net architecture by incorporating manifold supervision signals. This approach focuses on improving boundary accuracy, which is crucial for reliable medical diagnosis. To further extend the versatility of our method, we propose two variants: MA-Sobel and MA-Canny. The MA-Sobel variant employs the Sobel operator, which is effective for both 2D and 3D data, while the MA-Canny variant utilizes the Canny operator, specifically designed for 2D images, to refine boundary detection. These variants allow our method to adapt to various medical image modalities and dimensionalities, ensuring broader applicability. Our extensive experiments on datasets such as ACDC, LA, and Pancreas-NIH demonstrate that MANet consistently surpasses state-of-the-art methods in performance metrics like Dice and Jaccard scores. The proposed method also shows improved generalization across various semi-supervised segmentation networks, highlighting its robustness and effectiveness. Visual analysis of segmentation results confirms that MANet offers clearer and more accurate class boundaries, underscoring the value of manifold information in medical image segmentation.

cs.CV↗

arXiv2024

Moirai-MoE: Empowering Time Series Foundation Models with Sparse Mixture of Experts

Time series foundation models have demonstrated impressive performance as zero-shot forecasters. However, achieving effectively unified training on time series remains an open challenge. Existing approaches introduce some level of model specialization to account for the highly heterogeneous nature of time series data. For instance, Moirai pursues unified training by employing multiple input/output projection layers, each tailored to handle time series at a specific frequency. Similarly, TimesFM maintains a frequency embedding dictionary for this purpose. We identify two major drawbacks to this human-imposed frequency-level model specialization: (1) Frequency is not a reliable indicator of the underlying patterns in time series. For example, time series with different frequencies can display similar patterns, while those with the same frequency may exhibit varied patterns. (2) Non-stationarity is an inherent property of real-world time series, leading to varied distributions even within a short context window of a single time series. Frequency-level specialization is too coarse-grained to capture this level of diversity. To address these limitations, this paper introduces Moirai-MoE, using a single input/output projection layer while delegating the modeling of diverse time series patterns to the sparse mixture of experts (MoE) within Transformers. With these designs, Moirai-MoE reduces reliance on human-defined heuristics and enables automatic token-level specialization. Extensive experiments on 39 datasets demonstrate the superiority of Moirai-MoE over existing foundation models in both in-distribution and zero-shot scenarios. Furthermore, this study conducts comprehensive model analyses to explore the inner workings of time series MoE foundation models and provides valuable insights for future research.

cs.LG↗

arXiv2024

Towards Unifying Diffusion Models for Probabilistic Spatio-Temporal Graph Learning

Spatio-temporal graph learning is a fundamental problem in modern urban systems. Existing approaches tackle different tasks independently, tailoring their models to unique task characteristics. These methods, however, fall short of modeling intrinsic uncertainties in the spatio-temporal data. Meanwhile, their specialized designs misalign with the current research efforts toward unifying spatio-temporal graph learning solutions. In this paper, we propose to model these tasks in a unified probabilistic perspective, viewing them as predictions based on conditional information with shared dependencies. Based on this proposal, we introduce Unified Spatio-Temporal Diffusion Models (USTD) to address the tasks uniformly under the uncertainty-aware diffusion framework. USTD is holistically designed, comprising a shared spatio-temporal encoder and attention-based denoising decoders that are task-specific. The encoder, optimized by pre-training strategies, effectively captures conditional spatio-temporal patterns. The decoders, utilizing attention mechanisms, generate predictions by leveraging learned patterns. Opting for forecasting and kriging, the decoders are designed as Spatial Gated Attention (SGA) and Temporal Gated Attention (TGA) for each task, with different emphases on the spatial and temporal dimensions. Combining the advantages of deterministic encoders and probabilistic decoders, USTD achieves state-of-the-art performances compared to both deterministic and probabilistic baselines, while also providing valuable uncertainty estimates.

cs.LG↗

arXiv2024

DriveDiTFit: Fine-tuning Diffusion Transformers for Autonomous Driving

In autonomous driving, deep models have shown remarkable performance across various visual perception tasks with the demand of high-quality and huge-diversity training datasets. Such datasets are expected to cover various driving scenarios with adverse weather, lighting conditions and diverse moving objects. However, manually collecting these data presents huge challenges and expensive cost. With the rapid development of large generative models, we propose DriveDiTFit, a novel method for efficiently generating autonomous Driving data by Fine-tuning pre-trained Diffusion Transformers (DiTs). Specifically, DriveDiTFit utilizes a gap-driven modulation technique to carefully select and efficiently fine-tune a few parameters in DiTs according to the discrepancy between the pre-trained source data and the target driving data. Additionally, DriveDiTFit develops an effective weather and lighting condition embedding module to ensure diversity in the generated data, which is initialized by a nearest-semantic-similarity initialization approach. Through progressive tuning scheme to refined the process of detail generation in early diffusion process and enlarging the weights corresponding to small objects in training loss, DriveDiTFit ensures high-quality generation of small moving objects in the generated data. Extensive experiments conducted on driving datasets confirm that our method could efficiently produce diverse real driving data. The source codes will be available at https://github.com/TtuHamg/DriveDiTFit.

cs.CV↗

arXiv2024

Described Spatial-Temporal Video Detection

Detecting visual content on language expression has become an emerging topic in the community. However, in the video domain, the existing setting, i.e., spatial-temporal video grounding (STVG), is formulated to only detect one pre-existing object in each frame, ignoring the fact that language descriptions can involve none or multiple entities within a video. In this work, we advance the STVG to a more practical setting called described spatial-temporal video detection (DSTVD) by overcoming the above limitation. To facilitate the exploration of DSTVD, we first introduce a new benchmark, namely DVD-ST. Notably, DVD-ST supports grounding from none to many objects onto the video in response to queries and encompasses a diverse range of over 150 entities, including appearance, actions, locations, and interactions. The extensive breadth and diversity of the DVD-ST dataset make it an exemplary testbed for the investigation of DSTVD. In addition to the new benchmark, we further present two baseline methods for our proposed DSTVD task by extending two representative STVG models, i.e., TubeDETR, and STCAT. These extended models capitalize on tubelet queries to localize and track referred objects across the video sequence. Besides, we adjust the training objectives of these models to optimize spatial and temporal localization accuracy and multi-class classification capabilities. Furthermore, we benchmark the baselines on the introduced DVD-ST dataset and conduct extensive experimental analysis to guide future investigation. Our code and benchmark will be publicly available.

cs.CV↗

arXiv2024

Do As I Do: Pose Guided Human Motion Copy

Human motion copy is an intriguing yet challenging task in artificial intelligence and computer vision, which strives to generate a fake video of a target person performing the motion of a source person. The problem is inherently challenging due to the subtle human-body texture details to be generated and the temporal consistency to be considered. Existing approaches typically adopt a conventional GAN with an L1 or L2 loss to produce the target fake video, which intrinsically necessitates a large number of training samples that are challenging to acquire. Meanwhile, current methods still have difficulties in attaining realistic image details and temporal consistency, which unfortunately can be easily perceived by human observers. Motivated by this, we try to tackle the issues from three aspects: (1) We constrain pose-to-appearance generation with a perceptual loss and a theoretically motivated Gromov-Wasserstein loss to bridge the gap between pose and appearance. (2) We present an episodic memory module in the pose-to-appearance generation to propel continuous learning that helps the model learn from its past poor generations. We also utilize geometrical cues of the face to optimize facial details and refine each key body part with a dedicated local GAN. (3) We advocate generating the foreground in a sequence-to-sequence manner rather than a single-frame manner, explicitly enforcing temporal inconsistency. Empirical results on five datasets, iPER, ComplexMotion, SoloDance, Fish, and Mouse datasets, demonstrate that our method is capable of generating realistic target videos while precisely copying motion from a source video. Our method significantly outperforms state-of-the-art approaches and gains 7.2% and 12.4% improvements in PSNR and FID respectively.

cs.CV↗

arXiv2024

PetalView: Fine-grained Location and Orientation Extraction of Street-view Images via Cross-view Local Search with Supplementary Materials

Satellite-based street-view information extraction by cross-view matching refers to a task that extracts the location and orientation information of a given street-view image query by using one or multiple geo-referenced satellite images. Recent work has initiated a new research direction to find accurate information within a local area covered by one satellite image centered at a location prior (e.g., from GPS). It can be used as a standalone solution or complementary step following a large-scale search with multiple satellite candidates. However, these existing works require an accurate initial orientation (angle) prior (e.g., from IMU) and/or do not efficiently search through all possible poses. To allow efficient search and to give accurate prediction regardless of the existence or the accuracy of the angle prior, we present PetalView extractors with multi-scale search. The PetalView extractors give semantically meaningful features that are equivalent across two drastically different views, and the multi-scale search strategy efficiently inspects the satellite image from coarse to fine granularity to provide sub-meter and sub-degree precision extraction. Moreover, when an angle prior is given, we propose a learnable prior angle mixer to utilize this information. Our method obtains the best performance on the VIGOR dataset and successfully improves the performance on KITTI dataset test 1 set with the recall within 1 meter (r@1m) for location estimation to 68.88% and recall within 1 degree (r@1d) 21.10% when no angle prior is available, and with angle prior achieves stable estimations at r@1m and r@1d above 70% and 21%, up to a 40-degree noise level.

cs.CV↗

arXiv2024

Predicting Parking Availability in Singapore with Cross-Domain Data: A New Dataset and A Data-Driven Approach

The increasing number of vehicles highlights the need for efficient parking space management. Predicting real-time Parking Availability (PA) can help mitigate traffic congestion and the corresponding social problems, which is a pressing issue in densely populated cities like Singapore. In this study, we aim to collectively predict future PA across Singapore with complex factors from various domains. The contributions in this paper are listed as follows: (1) A New Dataset: We introduce the \texttt{SINPA} dataset, containing a year's worth of PA data from 1,687 parking lots in Singapore, enriched with various spatial and temporal factors. (2) A Data-Driven Approach: We present DeepPA, a novel deep-learning framework, to collectively and efficiently predict future PA across thousands of parking lots. (3) Extensive Experiments and Deployment: DeepPA demonstrates a 9.2% reduction in prediction error for up to 3-hour forecasts compared to existing advanced models. Furthermore, we implement DeepPA in a practical web-based platform to provide real-time PA predictions to aid drivers and inform urban planning for the governors in Singapore. We release the dataset and source code at https://github.com/yoshall/SINPA.

cs.AI↗

arXiv2024

Decoupling Long- and Short-Term Patterns in Spatiotemporal Inference

Sensors are the key to environmental monitoring, which impart benefits to smart cities in many aspects, such as providing real-time air quality information to assist human decision-making. However, it is impractical to deploy massive sensors due to the expensive costs, resulting in sparse data collection. Therefore, how to get fine-grained data measurement has long been a pressing issue. In this paper, we aim to infer values at non-sensor locations based on observations from available sensors (termed spatiotemporal inference), where capturing spatiotemporal relationships among the data plays a critical role. Our investigations reveal two significant insights that have not been explored by previous works. Firstly, data exhibits distinct patterns at both long- and short-term temporal scales, which should be analyzed separately. Secondly, short-term patterns contain more delicate relations including those across spatial and temporal dimensions simultaneously, while long-term patterns involve high-level temporal trends. Based on these observations, we propose to decouple the modeling of short-term and long-term patterns. Specifically, we introduce a joint spatiotemporal graph attention network to learn the relations across space and time for short-term patterns. Furthermore, we propose a graph recurrent network with a time skip strategy to alleviate the gradient vanishing problem and model the long-term dependencies. Experimental results on four public real-world datasets demonstrate that our method effectively captures both long- and short-term relations, achieving state-of-the-art performance against existing methods.

cs.LG↗