Medical Image De-Identification Benchmark Challenge

The de-identification (deID) of protected health information (PHI) and personally identifiable information (PII) is a fundamental requirement for sharing medical images, particularly through public repositories, to ensure compliance with patient privacy laws. In addition, preservation of non-PHI metadata to inform and enable downstream development of imaging artificial intelligence (AI) is an important consideration in biomedical research. The goal of MIDI-B was to provide a standardized platform for benchmarking of DICOM image deID tools based on a set of rules conformant to the HIPAA Safe Harbor regulation, the DICOM Attribute Confidentiality Profiles, and best practices in preservation of research-critical metadata, as defined by The Cancer Imaging Archive (TCIA). The challenge employed a large, diverse, multi-center, and multi-modality set of real de-identified radiology images with synthetic PHI/PII inserted. The MIDI-B Challenge consisted of three phases: training, validation, and test. Eighty individuals registered for the challenge. In the training phase, we encouraged participants to tune their algorithms using their in-house or public data. The validation and test phases utilized the DICOM images containing synthetic identifiers (of 216 and 322 subjects, respectively). Ten teams successfully completed the test phase of the challenge. To measure success of a rule-based approach to image deID, scores were computed as the percentage of correct actions from the total number of required actions. The scores ranged from 97.91% to 99.93%. Participants employed a variety of open-source and proprietary tools with customized configurations, large language models, and optical character recognition (OCR). In this paper we provide a comprehensive report on the MIDI-B Challenge's design, implementation, results, and lessons learned.

Face-LLaVA: Facial Expression and Attribute Understanding through Instruction Tuning

The human face plays a central role in social communication, necessitating the use of performant computer vision tools for human-centered applications. We propose Face-LLaVA, a multimodal large language model for face-centered, in-context learning, including facial expression and attribute recognition. Additionally, Face-LLaVA is able to generate natural language descriptions that can be used for reasoning. Leveraging existing visual databases, we first developed FaceInstruct-1M, a face-centered database for instruction tuning MLLMs for face processing. We then developed a novel face-specific visual encoder powered by Face-Region Guided Cross-Attention that integrates face geometry with local visual features. We evaluated the proposed method across nine different datasets and five different face processing tasks, including facial expression recognition, action unit detection, facial attribute detection, age estimation and deepfake detection. Face-LLaVA achieves superior results compared to existing open-source MLLMs and competitive performance compared to commercial solutions. Our model output also receives a higher reasoning rating by GPT under a zero-shot setting across all the tasks. Both our dataset and model wil be released at https://face-llava.github.io to support future advancements in social AI and foundational vision-language research.

ForcePose: A Deep Learning Approach for Force Calculation Based on Action Recognition Using MediaPipe Pose Estimation Combined with Object Detection

Force estimation in human-object interactions is crucial for various fields like ergonomics, physical therapy, and sports science. Traditional methods depend on specialized equipment such as force plates and sensors, which makes accurate assessments both expensive and restricted to laboratory settings. In this paper, we introduce ForcePose, a novel deep learning framework that estimates applied forces by combining human pose estimation with object detection. Our approach leverages MediaPipe for skeletal tracking and SSD MobileNet for object recognition to create a unified representation of human-object interaction. We've developed a specialized neural network that processes both spatial and temporal features to predict force magnitude and direction without needing any physical sensors. After training on our dataset of 850 annotated videos with corresponding force measurements, our model achieves a mean absolute error of 5.83 N in force magnitude and 7.4 degrees in force direction. When compared to existing computer vision approaches, our method performs 27.5% better while still offering real-time performance on standard computing hardware. ForcePose opens up new possibilities for force analysis in diverse real-world scenarios where traditional measurement tools are impractical or intrusive. This paper discusses our methodology, the dataset creation process, evaluation metrics, and potential applications across rehabilitation, ergonomics assessment, and athletic performance analysis.

Surg-3M: A Dataset and Foundation Model for Perception in Surgical Settings

Advancements in computer-assisted surgical procedures heavily rely on accurate visual data interpretation from camera systems used during surgeries. Traditional open-access datasets focusing on surgical procedures are often limited by their small size, typically consisting of fewer than 100 videos with less than 100K images. To address these constraints, a new dataset called Surg-3M has been compiled using a novel aggregation pipeline that collects high-resolution videos from online sources. Featuring an extensive collection of over 4K surgical videos and more than 3 million high-quality images from multiple procedure types, Surg-3M offers a comprehensive resource surpassing existing alternatives in size and scope, including two novel tasks. To demonstrate the effectiveness of this dataset, we present SurgFM, a self-supervised foundation model pretrained on Surg-3M that achieves impressive results in downstream tasks such as surgical phase recognition, action recognition, and tool presence detection. Combining key components from ConvNeXt, DINO, and an innovative augmented distillation method, SurgFM exhibits exceptional performance compared to specialist architectures across various benchmarks. Our experimental results show that SurgFM outperforms state-of-the-art models in multiple downstream tasks, including significant gains in surgical phase recognition (+8.9pp, +4.7pp, and +3.9pp of Jaccard in AutoLaparo, M2CAI16, and Cholec80), action recognition (+3.1pp of mAP in CholecT50) and tool presence detection (+4.6pp of mAP in Cholec80). Moreover, even when using only half of the data, SurgFM outperforms state-of-the-art models in AutoLaparo and achieves state-of-the-art performance in Cholec80. Both Surg-3M and SurgFM have significant potential to accelerate progress towards developing autonomous robotic surgery systems.

JARVIS-VLA: Post-Training Large-Scale Vision Language Models to Play Visual Games with Keyboards and Mouse

Recently, action-based decision-making in open-world environments has gained significant attention. Visual Language Action (VLA) models, pretrained on large-scale web datasets, have shown promise in decision-making tasks. However, previous work has primarily focused on action post-training, often neglecting enhancements to the foundational model itself. In response, we introduce a novel approach, Act from Visual Language Post-Training, which refines Visual Language Models (VLMs) through visual and linguistic guidance in a self-supervised manner. This enhancement improves the models' capabilities in world knowledge, visual recognition, and spatial grounding in open-world environments. Following the above post-training paradigms, we obtain the first VLA models in Minecraft that can follow human instructions on over 1k different atomic tasks, including crafting, smelting, cooking, mining, and killing. Our experiments demonstrate that post-training on non-trajectory tasks leads to a significant 40% improvement over the best agent baseline on a diverse set of atomic tasks. Furthermore, we demonstrate that our approach surpasses traditional imitation learning-based policies in Minecraft, achieving state-of-the-art performance. We have open-sourced the code, models, and datasets to foster further research. The project page can be found in https://craftjarvis.github.io/JarvisVLA.

From Motion Signals to Insights: A Unified Framework for Student Behavior Analysis and Feedback in Physical Education Classes

Analyzing student behavior in educational scenarios is crucial for enhancing teaching quality and student engagement. Existing AI-based models often rely on classroom video footage to identify and analyze student behavior. While these video-based methods can partially capture and analyze student actions, they struggle to accurately track each student's actions in physical education classes, which take place in outdoor, open spaces with diverse activities, and are challenging to generalize to the specialized technical movements involved in these settings. Furthermore, current methods typically lack the ability to integrate specialized pedagogical knowledge, limiting their ability to provide in-depth insights into student behavior and offer feedback for optimizing instructional design. To address these limitations, we propose a unified end-to-end framework that leverages human activity recognition technologies based on motion signals, combined with advanced large language models, to conduct more detailed analyses and feedback of student behavior in physical education classes. Our framework begins with the teacher's instructional designs and the motion signals from students during physical education sessions, ultimately generating automated reports with teaching insights and suggestions for improving both learning and class instructions. This solution provides a motion signal-based approach for analyzing student behavior and optimizing instructional design tailored to physical education classes. Experimental results demonstrate that our framework can accurately identify student behaviors and produce meaningful pedagogical insights.

Recognize Any Surgical Object: Unleashing the Power of Weakly-Supervised Data

We present RASO, a foundation model designed to Recognize Any Surgical Object, offering robust open-set recognition capabilities across a broad range of surgical procedures and object classes, in both surgical images and videos. RASO leverages a novel weakly-supervised learning framework that generates tag-image-text pairs automatically from large-scale unannotated surgical lecture videos, significantly reducing the need for manual annotations. Our scalable data generation pipeline gatherers to 2,200 surgical procedures and produces 3.6 million tag annotations across 2,066 unique surgical tags. Our experiments show that RASO achieves improvements of 2.9 mAP, 4.5 mAP, 10.6 mAP, and 7.2 mAP on four standard surgical benchmarks respectively in zero-shot settings, and surpasses state-of-the-art models in supervised surgical action recognition tasks. We will open-source our code, model, and dataset to facilitate further research.

Robustness-enhanced Myoelectric Control with GAN-based Open-set Recognition

Electromyography (EMG) signals are widely used in human motion recognition and medical rehabilitation, yet their variability and susceptibility to noise significantly limit the reliability of myoelectric control systems. Existing recognition algorithms often fail to handle unfamiliar actions effectively, leading to system instability and errors. This paper proposes a novel framework based on Generative Adversarial Networks (GANs) to enhance the robustness and usability of myoelectric control systems by enabling open-set recognition. The method incorporates a GAN-based discriminator to identify and reject unknown actions, maintaining system stability by preventing misclassifications. Experimental evaluations on publicly available and self-collected datasets demonstrate a recognition accuracy of 97.6\% for known actions and a 23.6\% improvement in Active Error Rate (AER) after rejecting unknown actions. The proposed approach is computationally efficient and suitable for deployment on edge devices, making it practical for real-world applications.

TACO: Learning Multi-modal Action Models with Synthetic Chains-of-Thought-and-Action

While open-source multi-modal language models perform well on simple question answering tasks, they often fail on complex questions that require multiple capabilities, such as fine-grained recognition, visual grounding, and reasoning, and that demand multi-step solutions. We present TACO, a family of multi-modal large action models designed to improve performance on such complex, multi-step, and multi-modal tasks. During inference, TACO produces chains-of-thought-and-action (CoTA), executes intermediate steps by invoking external tools such as OCR, depth estimation and calculator, then integrates both the thoughts and action outputs to produce coherent responses. To train TACO, we create a large dataset of over 1M synthetic CoTA traces generated with GPT-4o and Python programs. We then experiment with various data filtering and mixing techniques and obtain a final subset of 293K high-quality CoTA examples. This dataset enables TACO to learn complex reasoning and action paths, surpassing existing models trained on instruction tuning data with only direct answers. Our model TACO outperforms the instruction-tuned baseline across 8 benchmarks, achieving a 3.6% improvement on average, with gains of up to 15% in MMVet tasks involving OCR, mathematical reasoning, and spatial reasoning. Training on high-quality CoTA traces sets a new standard for complex multi-modal reasoning, highlighting the need for structured, multi-step instruction tuning in advancing open-source mutli-modal models' capabilities.

Temporally Consistent Dynamic Scene Graphs: An End-to-End Approach for Action Tracklet Generation

Understanding video content is pivotal for advancing real-world applications like activity recognition, autonomous systems, and human-computer interaction. While scene graphs are adept at capturing spatial relationships between objects in individual frames, extending these representations to capture dynamic interactions across video sequences remains a significant challenge. To address this, we present TCDSG, Temporally Consistent Dynamic Scene Graphs, an innovative end-to-end framework that detects, tracks, and links subject-object relationships across time, generating action tracklets, temporally consistent sequences of entities and their interactions. Our approach leverages a novel bipartite matching mechanism, enhanced by adaptive decoder queries and feedback loops, ensuring temporal coherence and robust tracking over extended sequences. This method not only establishes a new benchmark by achieving over 60% improvement in temporal recall@k on the Action Genome, OpenPVSG, and MEVA datasets but also pioneers the augmentation of MEVA with persistent object ID annotations for comprehensive tracklet generation. By seamlessly integrating spatial and temporal dynamics, our work sets a new standard in multi-frame video analysis, opening new avenues for high-impact applications in surveillance, autonomous navigation, and beyond.