Multi-Modal Fusion of In-Situ Video Data and Process Parameters for Online Forecasting of Cookie Drying Readiness

Food drying is essential for food production, extending shelf life, and reducing transportation costs. Accurate real-time forecasting of drying readiness is crucial for minimizing energy consumption, improving productivity, and ensuring product quality. However, this remains challenging due to the dynamic nature of drying, limited data availability, and the lack of effective predictive analytical methods. To address this gap, we propose an end-to-end multi-modal data fusion framework that integrates in-situ video data with process parameters for real-time food drying readiness forecasting. Our approach leverages a new encoder-decoder architecture with modality-specific encoders and a transformer-based decoder to effectively extract features while preserving the unique structure of each modality. We apply our approach to sugar cookie drying, where time-to-ready is predicted at each timestamp. Experimental results demonstrate that our model achieves an average prediction error of only 15 seconds, outperforming state-of-the-art data fusion methods by 65.69% and a video-only model by 11.30%. Additionally, our model balances prediction accuracy, model size, and computational efficiency, making it well-suited for heterogenous industrial datasets. The proposed model is extensible to various other industrial modality fusion tasks for online decision-making.

ReSpec: Relevance and Specificity Grounded Online Filtering for Learning on Video-Text Data Streams

The rapid growth of video-text data presents challenges in storage and computation during training. Online learning, which processes streaming data in real-time, offers a promising solution to these issues while also allowing swift adaptations in scenarios demanding real-time responsiveness. One strategy to enhance the efficiency and effectiveness of learning involves identifying and prioritizing data that enhances performance on target downstream tasks. We propose Relevance and Specificity-based online filtering framework (ReSpec) that selects data based on four criteria: (i) modality alignment for clean data, (ii) task relevance for target focused data, (iii) specificity for informative and detailed data, and (iv) efficiency for low-latency processing. Relevance is determined by the probabilistic alignment of incoming data with downstream tasks, while specificity employs the distance to a root embedding representing the least specific data as an efficient proxy for informativeness. By establishing reference points from target task data, ReSpec filters incoming data in real-time, eliminating the need for extensive storage and compute. Evaluating on large-scale datasets WebVid2M and VideoCC3M, ReSpec attains state-of-the-art performance on five zeroshot video retrieval tasks, using as little as 5% of the data while incurring minimal compute. The source code is available at https://github.com/cdjkim/ReSpec.

UrbanVideo-Bench: Benchmarking Vision-Language Models on Embodied Intelligence with Video Data in Urban Spaces

Large multimodal models exhibit remarkable intelligence, yet their embodied cognitive abilities during motion in open-ended urban 3D space remain to be explored. We introduce a benchmark to evaluate whether video-large language models (Video-LLMs) can naturally process continuous first-person visual observations like humans, enabling recall, perception, reasoning, and navigation. We have manually control drones to collect 3D embodied motion video data from real-world cities and simulated environments, resulting in 1.5k video clips. Then we design a pipeline to generate 5.2k multiple-choice questions. Evaluations of 17 widely-used Video-LLMs reveal current limitations in urban embodied cognition. Correlation analysis provides insight into the relationships between different tasks, showing that causal reasoning has a strong correlation with recall, perception, and navigation, while the abilities for counterfactual and associative reasoning exhibit lower correlation with other tasks. We also validate the potential for Sim-to-Real transfer in urban embodiment through fine-tuning.

AnomalousNet: A Hybrid Approach with Attention U-Nets and Change Point Detection for Accurate Characterization of Anomalous Diffusion in Video Data

Anomalous diffusion occurs in a wide range of systems, including protein transport within cells, animal movement in complex habitats, pollutant dispersion in groundwater, and nanoparticle motion in synthetic materials. Accurately estimating the anomalous diffusion exponent and the diffusion coefficient from the particle trajectories is essential to distinguish between sub-diffusive, super-diffusive, or normal diffusion regimes. These estimates provide a deeper insight into the underlying dynamics of the system, facilitating the identification of particle behaviors and the detection of changes in diffusion states. However, analyzing short and noisy video data, which often yield incomplete and heterogeneous trajectories, poses a significant challenge for traditional statistical approaches. We introduce a data-driven method that integrates particle tracking, an attention U-Net architecture, and a change-point detection algorithm to address these issues. This approach not only infers the anomalous diffusion parameters with high accuracy but also identifies temporal transitions between different states, even in the presence of noise and limited temporal resolution. Our methodology demonstrated strong performance in the 2nd Anomalous Diffusion (AnDi) Challenge benchmark within the top submissions for video tasks.

How good are deep learning methods for automated road safety analysis using video data? An experimental study

Image-based multi-object detection (MOD) and multi-object tracking (MOT) are advancing at a fast pace. A variety of 2D and 3D MOD and MOT methods have been developed for monocular and stereo cameras. Road safety analysis can benefit from those advancements. As crashes are rare events, surrogate measures of safety (SMoS) have been developed for safety analyses. (Semi-)Automated safety analysis methods extract road user trajectories to compute safety indicators, for example, Time-to-Collision (TTC) and Post-encroachment Time (PET). Inspired by the success of deep learning in MOD and MOT, we investigate three MOT methods, including one based on a stereo-camera, using the annotated KITTI traffic video dataset. Two post-processing steps, IDsplit and SS, are developed to improve the tracking results and investigate the factors influencing the TTC. The experimental results show that, despite some advantages in terms of the numbers of interactions or similarity to the TTC distributions, all the tested methods systematically over-estimate the number of interactions and under-estimate the TTC: they report more interactions and more severe interactions, making the road user interactions appear less safe than they are. Further efforts will be directed towards testing more methods and more data, in particular from roadside sensors, to verify the results and improve the performance.

Mamba-3D as Masked Autoencoders for Accurate and Data-Efficient Analysis of Medical Ultrasound Videos

Ultrasound videos are an important form of clinical imaging data, and deep learning-based automated analysis can improve diagnostic accuracy and clinical efficiency. However, the scarcity of labeled data and the inherent challenges of video analysis have impeded the advancement of related methods. In this work, we introduce E-ViM$^3$, a data-efficient Vision Mamba network that preserves the 3D structure of video data, enhancing long-range dependencies and inductive biases to better model space-time correlations. With our design of Enclosure Global Tokens (EGT), the model captures and aggregates global features more effectively than competing methods. To further improve data efficiency, we employ masked video modeling for self-supervised pre-training, with the proposed Spatial-Temporal Chained (STC) masking strategy designed to adapt to various video scenarios. Experiments demonstrate that E-ViM$^3$ performs as the state-of-the-art in two high-level semantic analysis tasks across four datasets of varying sizes: EchoNet-Dynamic, CAMUS, MICCAI-BUV, and WHBUS. Furthermore, our model achieves competitive performance with limited labels, highlighting its potential impact on real-world clinical applications.

Validation of Human Pose Estimation and Human Mesh Recovery for Extracting Clinically Relevant Motion Data from Videos

This work aims to discuss the current landscape of kinematic analysis tools, ranging from the state-of-the-art in sports biomechanics such as inertial measurement units (IMUs) and retroreflective marker-based optical motion capture (MoCap) to more novel approaches from the field of computing such as human pose estimation and human mesh recovery. Primarily, this comparative analysis aims to validate the use of marker-less MoCap techniques in a clinical setting by showing that these marker-less techniques are within a reasonable range for kinematics analysis compared to the more cumbersome and less portable state-of-the-art tools. Not only does marker-less motion capture using human pose estimation produce results in-line with the results of both the IMU and MoCap kinematics but also benefits from a reduced set-up time and reduced practical knowledge and expertise to set up. Overall, while there is still room for improvement when it comes to the quality of the data produced, we believe that this compromise is within the room of error that these low-speed actions that are used in small clinical tests.

Quality Over Quantity? LLM-Based Curation for a Data-Efficient Audio-Video Foundation Model

Integrating audio and visual data for training multimodal foundational models remains challenging. We present Audio-Video Vector Alignment (AVVA), which aligns audiovisual (AV) scene content beyond mere temporal synchronization via a Large Language Model (LLM)-based data curation pipeline. Specifically, AVVA scores and selects high-quality training clips using Whisper (speech-based audio foundation model) for audio and DINOv2 for video within a dual-encoder contrastive learning framework. Evaluations on AudioCaps, VALOR, and VGGSound demonstrate that this approach can achieve significant accuracy gains with substantially less curated data. For instance, AVVA yields a 7.6% improvement in top-1 accuracy for audio-to-video retrieval on VGGSound compared to ImageBind, despite training on only 192 hours of carefully filtered data (vs. 5800+ hours). Moreover, an ablation study highlights that trading data quantity for data quality improves performance, yielding respective top-3 accuracy increases of 47.8, 48.4, and 58.0 percentage points on AudioCaps, VALOR, and VGGSound over uncurated baselines. While these results underscore AVVA's data efficiency, we also discuss the overhead of LLM-driven curation and how it may be scaled or approximated in larger domains. Overall, AVVA provides a viable path toward more robust, text-free audiovisual learning with improved retrieval accuracy.

Video-R1: Reinforcing Video Reasoning in MLLMs

Inspired by DeepSeek-R1's success in eliciting reasoning abilities through rule-based reinforcement learning (RL), we introduce Video-R1 as the first attempt to systematically explore the R1 paradigm for eliciting video reasoning within multimodal large language models (MLLMs). However, directly applying RL training with the GRPO algorithm to video reasoning presents two primary challenges: (i) a lack of temporal modeling for video reasoning, and (ii) the scarcity of high-quality video-reasoning data. To address these issues, we first propose the T-GRPO algorithm, which encourages models to utilize temporal information in videos for reasoning. Additionally, instead of relying solely on video data, we incorporate high-quality image-reasoning data into the training process. We have constructed two datasets: Video-R1-COT-165k for SFT cold start and Video-R1-260k for RL training, both comprising image and video data. Experimental results demonstrate that Video-R1 achieves significant improvements on video reasoning benchmarks such as VideoMMMU and VSI-Bench, as well as on general video benchmarks including MVBench and TempCompass, etc. Notably, Video-R1-7B attains a 35.8% accuracy on video spatial reasoning benchmark VSI-bench, surpassing the commercial proprietary model GPT-4o. All codes, models, data are released.

VEGGIE: Instructional Editing and Reasoning of Video Concepts with Grounded Generation

Recent video diffusion models have enhanced video editing, but it remains challenging to handle instructional editing and diverse tasks (e.g., adding, removing, changing) within a unified framework. In this paper, we introduce VEGGIE, a Video Editor with Grounded Generation from Instructions, a simple end-to-end framework that unifies video concept editing, grounding, and reasoning based on diverse user instructions. Specifically, given a video and text query, VEGGIE first utilizes an MLLM to interpret user intentions in instructions and ground them to the video contexts, generating frame-specific grounded task queries for pixel-space responses. A diffusion model then renders these plans and generates edited videos that align with user intent. To support diverse tasks and complex instructions, we employ a curriculum learning strategy: first aligning the MLLM and video diffusion model with large-scale instructional image editing data, followed by end-to-end fine-tuning on high-quality multitask video data. Additionally, we introduce a novel data synthesis pipeline to generate paired instructional video editing data for model training. It transforms static image data into diverse, high-quality video editing samples by leveraging Image-to-Video models to inject dynamics. VEGGIE shows strong performance in instructional video editing with different editing skills, outperforming the best instructional baseline as a versatile model, while other models struggle with multi-tasking. VEGGIE also excels in video object grounding and reasoning segmentation, where other baselines fail. We further reveal how the multiple tasks help each other and highlight promising applications like zero-shot multimodal instructional and in-context video editing.