Automating Visual Recognition of Leprosy in Wild Chimpanzees

Leprosy (Mycobacterium leprae) has been confirmed in wild western chimpanzees (Pan troglodytes verus) in West Africa, presenting as clear and progressive visual symptoms. Manual review of camera-trap footage at landscape scale is infeasible, motivating the need for automated screening. We present the first deep learning pipeline for wildlife leprosy detection and contribute the PanLep300 dataset of 125,670 annotated bounding-box crops across 953 tracks from 303 camera-trap videos with ecologically-motivated splits that withhold whole individuals and camera installations. We benchmark spatial (2D), temporally aggregated (2.5D), and video-based (3D) classification approaches to investigate which approach is best suited to automated leprosy detection in wild apes. We find that simple aggregation of crop-level predictions consistently matches or outperforms both learned temporal models and end-to-end video architectures -- consistent with leprosy's static cutaneous presentation. We further find that performance is suppressed when tracklets contain frames of partially visible individuals -- as commonly occurs at the start and end of a track -- and demonstrate that this can be addressed through targeted construction and aggregation strategies.

The PanAf-SBR Dataset: Social Behaviour Recognition for Wild Great Apes

Behavioural shifts in wild great ape populations, particularly the breakdown of social structures, can serve as an early indicator of population decline. Automating the detection of behaviours indicative of these shifts is therefore a critical task for conservation. Several valuable datasets have recently been introduced for the automated recognition of great ape behaviour, yet few include fine-grained social behaviour annotations, and those that do are captured either in captive settings or via aerial platforms such as UAVs. We address this gap by introducing PanAf-SBR, the first wild great ape camera trap dataset annotated with social behaviours. PanAf-SBR extends PanAf500 with 100 additional videos covering 36,063 frames. These come with 81,096 annotations including bounding boxes, segmentation masks, intra-video identities, and seven social behaviour classes defined under the action giver and receiver convention of ChimpACT. We use this data together with the AlphaChimp architecture to establish the first benchmarks for fine-grained social behaviour recognition in wild great apes from camera trap footage. We further conduct bidirectional transfer learning experiments between PanAf-SBR and the captive ChimpACT dataset, finding that cross-dataset pre-training is highly beneficial for specific classes rather than of uniform benefit. Finally, we examine the role of background context by inverting the segmentation masks to suppress non-ape pixels.

Every Step of the Way: Video-based Parkinsonian Turning Step Counting

As a prominent symptom of Parkinson's disease (PD), turning impairment is evaluated through parameters such as turning angle, duration, and particularly, the number of steps required to complete a turn, which directly reflects motor dysfunction. Accurate step counting is challenging due to variability in real-world turning movements and atypical shuffling patterns in parkinsonian gait. Existing methods are predominantly wearable-based, requiring users to wear and manage dedicated devices, which can be inconvenient for continuous daily use. To address this, we propose a passive, video-based framework that estimates step count in a coarse-to-fine manner using diverse motion representations. Specifically, an initial step count is estimated from foot movement signals derived from 3D human mesh recovery, providing high-level motion structures. To incorporate fine-grained motion details, a motion encoder learns complementary gait dynamics from mesh and optical flow to refine the initial estimate. In this process, coarse foot movement signals query the pixel-level motion cues via cross attention to capture subtle parkinsonian gait dynamics. To handle varying video lengths, we partition each video into clips and integrate clip-wise motion embeddings via multiple instance learning (MIL) for step count residual prediction. Extensive experiments show our method consistently outperforms existing step counting methods on real-world PD turning datasets.

TraMP-LLaMA: Generative Interpretability with Decoupled Instruction Tuning for Facial Expression Quality Assessment

Existing facial expression quality assessment (FEQA) methods typically produce only a severity score, without explicitly communicating the observable facial motion evidence that supports the prediction. This limits interpretability and makes it difficult to inspect the basis of model outputs in Parkinson's disease assessment. To address this gap, we propose TraMP-LLaMA, a unified multimodal framework that jointly predicts severity scores and generates structured textual reports from facial motion cues. The framework integrates RGB appearance and landmark trajectory cues, and adopts a decoupled instruction-tuning strategy to reduce task interference between severity prediction and language generation. To support this task, we further extend the PFED5 dataset with expert-guided textual motion descriptions and construct PFED5-plus. Experiments on PFED5-plus show that TraMP-LLaMA outperforms competitive video-language baselines in report generation and achieves the best severity prediction performance among the compared methods under joint multi-expression training, improving Spearman's rank correlation by at least 4.39 percent over all competing methods. The text annotations and code are available at https://github.com/shuchaoduan/TraMP-LLaMA.

Evaluation Protocols and Validation for Cameras in Indoor Healthcare Monitoring

Camera-based monitoring systems are increasingly adopted in healthcare settings for the continuous assessment of patient movement and activities. However, their technical performance under real-world indoor conditions remains insufficiently characterised, preventing appropriate camera selection for clinical or home adoption and reproducibility. Existing validation studies typically assess either device metrological performance or algorithm accuracy in isolation, and often do not systematically account for practical deployment factors, such as lighting variability, occlusions, and camera positioning. We present two technical validation protocols: the first evaluates the metrological performance of RGB and RGB-D cameras, and the second assesses their use in supporting human pose estimation, validated using state-of-the-art pose estimators. The proposed protocols systematically assess five cameras, four RGB-D and one RGB, under controlled variations in lighting, camera height, viewing angle, and occlusion level within representative indoor scenarios. The experimental results show that metrological performance varies substantially across cameras, with depth bias at 5 m ranging from 50 mm to over 1400 mm depending on the device. For 2D pose estimation, all cameras achieve broadly comparable accuracy, with mean mAP between approximately 78% and 90% across cameras and estimators, whereas 3D reconstruction error differs markedly across devices, with MPJPE ranging from 104 mm to 365 mm, closely reflecting underlying depth-sensing quality. Environmental factors have a camera- and estimator-dependent effect on 3D performance, while camera mounting height has minimal influence within the evaluated range. This work provides evidence-based guidance for the selection and deployment of cameras in healthcare monitoring applications, addressing an important gap in current technical validation practice.

The Invisible Hand of Physics: When Video Diffusion Models Know More Than They Show

Modern video diffusion models generate increasingly realistic and temporally coherent videos, motivating their use as candidate world simulators. Yet it remains unclear whether these models internally encode physical structure, or merely reproduce motion patterns seen during training. We study this question by probing video diffusion models along latent trajectories corresponding to real videos with known physical plausibility. To obtain such trajectories, we approximately invert the deterministic sampling process by integrating the learned velocity field backward from a clean video latent to noise, giving access to the model's intermediate states and attention maps. Using these recovered trajectories, we show that physical plausibility is linearly decodable from diffusion transformer states across IntPhys and InfLevel, reaching around 81.27% average accuracy and outperforming dedicated representation-learning baselines such as V-JEPA and VideoMAE. Surprisingly, this signal is absent from the VAE latent input and emerges inside the denoising transformer itself, despite the model not being trained with a self-supervised predictive objective. These findings suggest that physically meaningful representations can arise as a byproduct of generative denoising.

Probability-Conserving Flow Guidance

Diffusion and flow-based generative models dominate visual synthesis, with guidance aligning samples to user input and improving perceptual quality. However, Classifier-Free Guidance (CFG) and extrapolation-based methods are heuristic linear combinations of velocities/scores that ignore the generative manifold geometry, breaking probability conservation and driving samples off the learned manifold under strong guidance. We analyse guidance through the continuity equation and show its effect decomposes into a divergence term and a score-parallel term defined invariantly across parameterisations. We prove the divergence term blows up structurally as sampling approaches the data manifold, motivating a time-dependent schedule alongside score-parallel attenuation. The resulting plug-and-play rule, Adaptive Manifold Guidance (AdaMaG), bounds both terms at no additional inference cost. Finally, we show that most empirical heuristics for reducing saturation or improving generation quality correspond directly to the two terms in our decomposition. Across image generation benchmarks, AdaMaG improves realism, reduces hallucinations, and induces controlled desaturation in high-guidance regimes.

DiffGraph: An Automated Agent-driven Model Merging Framework for In-the-Wild Text-to-Image Generation

The rapid growth of the text-to-image (T2I) community has fostered a thriving online ecosystem of expert models, which are variants of pretrained diffusion models specialized for diverse generative abilities. Yet, existing model merging methods remain limited in fully leveraging abundant online expert resources and still struggle to meet diverse in-the-wild user needs. We present DiffGraph, a novel agent-driven graph-based model merging framework, which automatically harnesses online experts and flexibly merges them for diverse user needs. Our DiffGraph constructs a scalable graph and organizes ever-expanding online experts within it through node registration and calibration. Then, DiffGraph dynamically activates specific subgraphs based on user needs, enabling flexible combinations of different experts to achieve user-desired generation. Extensive experiments show the efficacy of our method.

When Visual Privacy Protection Meets Multimodal Large Language Models

The emergence of Multimodal Large Language Models (MLLMs) and the widespread usage of MLLM cloud services such as GPT-4V raised great concerns about privacy leakage in visual data. As these models are typically deployed in cloud services, users are required to submit their images and videos, posing serious privacy risks. However, how to tackle such privacy concerns is an under-explored problem. Thus, in this paper, we aim to conduct a new investigation to protect visual privacy when enjoying the convenience brought by MLLM services. We address the practical case where the MLLM is a "black box", i.e., we only have access to its input and output without knowing its internal model information. To tackle such a challenging yet demanding problem, we propose a novel framework, in which we carefully design the learning objective with Pareto optimality to seek a better trade-off between visual privacy and MLLM's performance, and propose critical-history enhanced optimization to effectively optimize the framework with the black-box MLLM. Our experiments show that our method is effective on different benchmarks.

LEMON: Local Explanations via Modality-aware OptimizatioN

Multimodal models are ubiquitous, yet existing explainability methods are often single-modal, architecture-dependent, or too computationally expensive to run at scale. We introduce LEMON (Local Explanations via Modality-aware OptimizatioN), a model-agnostic framework for local explanations of multimodal predictions. LEMON fits a single modality-aware surrogate with group-structured sparsity to produce unified explanations that disentangle modality-level contributions and feature-level attributions. The approach treats the predictor as a black box and is computationally efficient, requiring relatively few forward passes while remaining faithful under repeated perturbations. We evaluate LEMON on vision-language question answering and a clinical prediction task with image, text, and tabular inputs, comparing against representative multimodal baselines. Across backbones, LEMON achieves competitive deletion-based faithfulness while reducing black-box evaluations by 35-67 times and runtime by 2-8 times compared to strong multimodal baselines.