Sarah Ostadabbas

Le Jiang, Shuangjun Liu, Xiangyu Bai et al.

Accurately annotated image datasets are essential components for studying animal behaviors from their poses. Compared to the number of species we know and may exist, the existing labeled pose datasets cover only a small portion of them, while building comprehensive large-scale datasets is prohibitively expensive. Here, we present a very data efficient strategy targeted for pose estimation in quadrupeds that requires only a small amount of real images from the target animal. It is confirmed that fine-tuning a backbone network with pretrained weights on generic image datasets such as ImageNet can mitigate the high demand for target animal pose data and shorten the training time by learning the the prior knowledge of object segmentation and keypoint estimation in advance. However, when faced with serious data scarcity (i.e., $<10^2$ real images), the model performance stays unsatisfactory, particularly for limbs with considerable flexibility and several comparable parts. We therefore introduce a prior-aware synthetic animal data generation pipeline called PASyn to augment the animal pose data essential for robust pose estimation. PASyn generates a probabilistically-valid synthetic pose dataset, SynAP, through training a variational generative model on several animated 3D animal models. In addition, a style transfer strategy is utilized to blend the synthetic animal image into the real backgrounds. We evaluate the improvement made by our approach with three popular backbone networks and test their pose estimation accuracy on publicly available animal pose images as well as collected from real animals in a zoo.

Shaotong Zhu, Michael Wan, Elaheh Hatamimajoumerd et al.

We present an end-to-end computer vision pipeline to detect non-nutritive sucking (NNS) -- an infant sucking pattern with no nutrition delivered -- as a potential biomarker for developmental delays, using off-the-shelf baby monitor video footage. One barrier to clinical (or algorithmic) assessment of NNS stems from its sparsity, requiring experts to wade through hours of footage to find minutes of relevant activity. Our NNS activity segmentation algorithm solves this problem by identifying periods of NNS with high certainty -- up to 94.0\% average precision and 84.9\% average recall across 30 heterogeneous 60 s clips, drawn from our manually annotated NNS clinical in-crib dataset of 183 hours of overnight baby monitor footage from 19 infants. Our method is based on an underlying NNS action recognition algorithm, which uses spatiotemporal deep learning networks and infant-specific pose estimation, achieving 94.9\% accuracy in binary classification of 960 2.5 s balanced NNS vs. non-NNS clips. Tested on our second, independent, and public NNS in-the-wild dataset, NNS recognition classification reaches 92.3\% accuracy, and NNS segmentation achieves 90.8\% precision and 84.2\% recall.

Sai Kumar Reddy Manne, Shaotong Zhu, Sarah Ostadabbas et al.

Respiration is a critical vital sign for infants, and continuous respiratory monitoring is particularly important for newborns. However, neonates are sensitive and contact-based sensors present challenges in comfort, hygiene, and skin health, especially for preterm babies. As a step toward fully automatic, continuous, and contactless respiratory monitoring, we develop a deep-learning method for estimating respiratory rate and waveform from plain video footage in natural settings. Our automated infant respiration flow-based network (AIRFlowNet) combines video-extracted optical flow input and spatiotemporal convolutional processing tuned to the infant domain. We support our model with the first public annotated infant respiration dataset with 125 videos (AIR-125), drawn from eight infant subjects, set varied pose, lighting, and camera conditions. We include manual respiration annotations and optimize AIRFlowNet training on them using a novel spectral bandpass loss function. When trained and tested on the AIR-125 infant data, our method significantly outperforms other state-of-the-art methods in respiratory rate estimation, achieving a mean absolute error of $\sim$2.9 breaths per minute, compared to $\sim$4.7--6.2 for other public models designed for adult subjects and more uniform environments.

Elaheh Hatamimajoumerd, Pooria Daneshvar Kakhaki, Xiaofei Huang et al.

Automated human action recognition, a burgeoning field within computer vision, boasts diverse applications spanning surveillance, security, human-computer interaction, tele-health, and sports analysis. Precise action recognition in infants serves a multitude of pivotal purposes, encompassing safety monitoring, developmental milestone tracking, early intervention for developmental delays, fostering parent-infant bonds, advancing computer-aided diagnostics, and contributing to the scientific comprehension of child development. This paper delves into the intricacies of infant action recognition, a domain that has remained relatively uncharted despite the accomplishments in adult action recognition. In this study, we introduce a groundbreaking dataset called ``InfActPrimitive'', encompassing five significant infant milestone action categories, and we incorporate specialized preprocessing for infant data. We conducted an extensive comparative analysis employing cutting-edge skeleton-based action recognition models using this dataset. Our findings reveal that, although the PoseC3D model achieves the highest accuracy at approximately 71%, the remaining models struggle to accurately capture the dynamics of infant actions. This highlights a substantial knowledge gap between infant and adult action recognition domains and the urgent need for data-efficient pipeline models.

Xiaofei Huang, Michael Wan, Lingfei Luan et al.

Bilateral postural symmetry plays a key role as a potential risk marker for autism spectrum disorder (ASD) and as a symptom of congenital muscular torticollis (CMT) in infants, but current methods of assessing symmetry require laborious clinical expert assessments. In this paper, we develop a computer vision based infant symmetry assessment system, leveraging 3D human pose estimation for infants. Evaluation and calibration of our system against ground truth assessments is complicated by our findings from a survey of human ratings of angle and symmetry, that such ratings exhibit low inter-rater reliability. To rectify this, we develop a Bayesian estimator of the ground truth derived from a probabilistic graphical model of fallible human raters. We show that the 3D infant pose estimation model can achieve 68% area under the receiver operating characteristic curve performance in predicting the Bayesian aggregate labels, compared to only 61% from a 2D infant pose estimation model and 60% from a 3D adult pose estimation model, highlighting the importance of 3D poses and infant domain knowledge in assessing infant body symmetry. Our survey analysis also suggests that human ratings are susceptible to higher levels of bias and inconsistency, and hence our final 3D pose-based symmetry assessment system is calibrated but not directly supervised by Bayesian aggregate human ratings, yielding higher levels of consistency and lower levels of inter-limb assessment bias.

Le Jiang, Xiangyu Bai, Bishoy Galoaa et al.

We present PanoWorld, a panoramic video world model that generates geometry-consistent 360$\degree$ video from a single image and a caption. Existing panoramic video methods optimize primarily for visual realism and do not explicitly constrain the underlying 3D scene state, producing outputs that appear plausible yet exhibit inconsistent depth, broken correspondences, and implausible motion across the spherical surface. We address this gap by framing panoramic video generation as a geometry- and dynamics-consistent latent state modeling problem rather than pure visual synthesis. Building on a pre-trained perspective video world model, we introduce two lightweight regularizers: a depth consistency loss against pseudo ground-truth panoramic depth, and a trajectory consistency loss that supervises the 3D world-frame positions of tracked points across time. We further apply spherical-geometry-aware adaptation to the conditioning and positional encoding. We additionally introduce PanoGeo, a unified geometry-aware panoramic video dataset with consistent depth, trajectory, and prompt annotations across diverse real and synthetic sources, used for both training and stratified evaluation. Experiments show that PanoWorld improves geometric consistency over prior panoramic generation methods while maintaining competitive visual realism, establishing that panoramic video generation must be treated as a geometric modeling problem to support the holistic spatial understanding requirements of embodied AI applications. Code is available at https://github.com/ostadabbas/PanoWorld.

Zhouping Wang, Sarah Ostadabbas

3D Human body pose and shape estimation within a temporal sequence can be quite critical for understanding human behavior. Despite the significant progress in human pose estimation in the recent years, which are often based on single images or videos, human motion estimation on live stream videos is still a rarely-touched area considering its special requirements for real-time output and temporal consistency. To address this problem, we present a temporally embedded 3D human body pose and shape estimation (TePose) method to improve the accuracy and temporal consistency of pose estimation in live stream videos. TePose uses previous predictions as a bridge to feedback the error for better estimation in the current frame and to learn the correspondence between data frames and predictions in the history. A multi-scale spatio-temporal graph convolutional network is presented as the motion discriminator for adversarial training using datasets without any 3D labeling. We propose a sequential data loading strategy to meet the special start-to-end data processing requirement of live stream. We demonstrate the importance of each proposed module with extensive experiments. The results show the effectiveness of TePose on widely-used human pose benchmarks with state-of-the-art performance.

Bishoy Galoaa, Xiangyu Bai, Shayda Moezzi et al.

This paper presents LAPA (Look Around and Pay Attention), a novel end-to-end transformer-based architecture for multi-camera point tracking that integrates appearance-based matching with geometric constraints. Traditional pipelines decouple detection, association, and tracking, leading to error propagation and temporal inconsistency in challenging scenarios. LAPA addresses these limitations by leveraging attention mechanisms to jointly reason across views and time, establishing soft correspondences through a cross-view attention mechanism enhanced with geometric priors. Instead of relying on classical triangulation, we construct 3D point representations via attention-weighted aggregation, inherently accommodating uncertainty and partial observations. Temporal consistency is further maintained through a transformer decoder that models long-range dependencies, preserving identities through extended occlusions. Extensive experiments on challenging datasets, including our newly created multi-camera (MC) versions of TAPVid-3D panoptic and PointOdyssey, demonstrate that our unified approach significantly outperforms existing methods, achieving 37.5% APD on TAPVid-3D-MC and 90.3% APD on PointOdyssey-MC, particularly excelling in scenarios with complex motions and occlusions. Code is available at https://github.com/ostadabbas/Look-Around-and-Pay-Attention-LAPA-

Michael Wan, Xiaofei Huang, Bethany Tunik et al.

We apply computer vision pose estimation techniques developed expressly for the data-scarce infant domain to the study of torticollis, a common condition in infants for which early identification and treatment is critical. Specifically, we use a combination of facial landmark and body joint estimation techniques designed for infants to estimate a range of geometric measures pertaining to face and upper body symmetry, drawn from an array of sources in the physical therapy and ophthalmology research literature in torticollis. We gauge performance with a range of metrics and show that the estimates of most these geometric measures are successful, yielding strong to very strong Spearman's $ρ$ correlation with ground truth values. Furthermore, we show that these estimates, derived from pose estimation neural networks designed for the infant domain, cleanly outperform estimates derived from more widely known networks designed for the adult domain

Shaotong Zhu, Michael Wan, Sai Kumar Reddy Manne et al.

Non-nutritive sucking (NNS), which refers to the act of sucking on a pacifier, finger, or similar object without nutrient intake, plays a crucial role in assessing healthy early development. In the case of preterm infants, NNS behavior is a key component in determining their readiness for feeding. In older infants, the characteristics of NNS behavior offer valuable insights into neural and motor development. Additionally, NNS activity has been proposed as a potential safeguard against sudden infant death syndrome (SIDS). However, the clinical application of NNS assessment is currently hindered by labor-intensive and subjective finger-in-mouth evaluations. Consequently, researchers often resort to expensive pressure transducers for objective NNS signal measurement. To enhance the accessibility and reliability of NNS signal monitoring for both clinicians and researchers, we introduce a vision-based algorithm designed for non-contact detection of NNS activity using baby monitor footage in natural settings. Our approach involves a comprehensive exploration of optical flow and temporal convolutional networks, enabling the detection and amplification of subtle infant-sucking signals. We successfully classify short video clips of uniform length into NNS and non-NNS periods. Furthermore, we investigate manual and learning-based techniques to piece together local classification results, facilitating the segmentation of longer mixed-activity videos into NNS and non-NNS segments of varying duration. Our research introduces two novel datasets of annotated infant videos, including one sourced from our clinical study featuring 19 infant subjects and 183 hours of overnight baby monitor footage.

Timothy Rupprecht, Pu Zhao, Amir Taherin et al.

This comprehensive report distinguishes prior works by the cognitive functions they innovate. Many works claim an almost "human-like" cognitive capability in their world models. To evaluate these claims requires a proper grounding in first principles in Cognitive Architecture Theory (CAT). We present a conceptual unified framework for world models that fully incorporates all the cognitive functions associated with CAT (i.e. memory, perception, language, reasoning, imagining, motivation, and meta-cognition) and identify gaps in the research as a guide for future states of the art. In particular, we find that motivation (especially intrinsic motivation) and meta-cognition remain drastically under-researched, and we propose concrete directions informed by active inference and global workspace theory to address them. We further introduce Epistemic World Models, a new category encompassing agent frameworks for scientific discovery that operate over structured knowledge. Our taxonomy, applied across video, embodied, and epistemic world models, suggests research directions where prior taxonomies have not.

Bishoy Galoaa, Shayda Moezzi, Xiangyu Bai et al.

Recent research has made substantial progress on video reasoning, with many models leveraging spatio-temporal evidence chains to strengthen their inference capabilities. At the same time, a growing set of datasets and benchmarks now provides structured annotations designed to support and evaluate such reasoning. However, little attention has been paid to reasoning about \emph{how} objects move between observations: no prior work has articulated the motion patterns by connecting successive observations, leaving trajectory understanding implicit and difficult to verify. We formalize this missing capability as Spatial-Temporal-Trajectory (STT) reasoning and introduce \textbf{Motion-o}, a motion-centric video understanding extension to visual language models that makes trajectories explicit and verifiable. To enable motion reasoning, we also introduce a trajectory-grounding dataset artifact that expands sparse keyframe supervision via augmentation to yield denser bounding box tracks and a stronger trajectory-level training signal. Finally, we introduce Motion Chain of Thought (MCoT), a structured reasoning pathway that makes object trajectories through discrete \texttt{<motion/>} tag summarizing per-object direction, speed, and scale (of velocity) change to explicitly connect grounded observations into trajectories. To train Motion-o, we design a reward function that compels the model to reason directly over visual evidence, all while requiring no architectural modifications. Empirical results demonstrate that Motion-o improves spatial-temporal grounding and trajectory prediction while remaining fully compatible with existing frameworks, establishing motion reasoning as a critical extension for evidence-based video understanding. Code is available at https://github.com/ostadabbas/Motion-o.

Xiangyu Bai, Bishoy Galoaa, Sarah Ostadabbas

Video question answering (VQA) with vision-language models (VLMs) depends critically on which frames are selected from the input video, yet most systems rely on uniform or heuristic sampling that cannot be optimized for downstream answering quality. We introduce \textbf{HORNet}, a lightweight frame selection policy trained with Group Relative Policy Optimization (GRPO) to learn which frames a frozen VLM needs to answer questions correctly. With fewer than 1M trainable parameters, HORNet reduces input frames by up to 99\% and VLM processing time by up to 93\%, while improving answer quality on short-form benchmarks (+1.7\% F1 on MSVD-QA) and achieving strong performance on temporal reasoning tasks (+7.3 points over uniform sampling on NExT-QA). We formalize this as Select Any Frames (SAF), a task that decouples visual input curation from VLM reasoning, and show that GRPO-trained selection generalizes better out-of-distribution than supervised and PPO alternatives. HORNet's policy further transfers across VLM answerers without retraining, yielding an additional 8.5\% relative gain when paired with a stronger model. Evaluated across six benchmarks spanning 341,877 QA pairs and 114.2 hours of video, our results demonstrate that optimizing \emph{what} a VLM sees is a practical and complementary alternative to optimizing what it generates while improving efficiency. Code is available at https://github.com/ostadabbas/HORNet.

Somaieh Amraee, Bishoy Galoaa, Matthew Goodwin et al.

Multiple toddler tracking (MTT) involves identifying and differentiating toddlers in video footage. While conventional multi-object tracking (MOT) algorithms are adept at tracking diverse objects, toddlers pose unique challenges due to their unpredictable movements, various poses, and similar appearance. Tracking toddlers in indoor environments introduces additional complexities such as occlusions and limited fields of view. In this paper, we address the challenges of MTT and propose MTTSort, a customized method built upon the DeepSort algorithm. MTTSort is designed to track multiple toddlers in indoor videos accurately. Our contributions include discussing the primary challenges in MTT, introducing a genetic algorithm to optimize hyperparameters, proposing an accurate tracking algorithm, and curating the MTTrack dataset using unbiased AI co-labeling techniques. We quantitatively compare MTTSort to state-of-the-art MOT methods on MTTrack, DanceTrack, and MOT15 datasets. In our evaluation, the proposed method outperformed other MOT methods, achieving 0.98, 0.68, and 0.98 in multiple object tracking accuracy (MOTA), higher order tracking accuracy (HOTA), and iterative and discriminative framework 1 (IDF1) metrics, respectively.

Liyang Song, Hardik Bishnoi, Sai Kumar Reddy Manne et al.

The development of contactless respiration monitoring for infants could enable advances in the early detection and treatment of breathing irregularities, which are associated with neurodevelopmental impairments and conditions like sudden infant death syndrome (SIDS). But while respiration estimation for adults is supported by a robust ecosystem of computer vision algorithms and video datasets, only one small public video dataset with annotated respiration data for infant subjects exists, and there are no reproducible algorithms which are effective for infants. We introduce the annotated infant respiration dataset of 400 videos (AIR-400), contributing 275 new, carefully annotated videos from 10 recruited subjects to the public corpus. We develop the first reproducible pipelines for infant respiration estimation, based on infant-specific region-of-interest detection and spatiotemporal neural processing enhanced by optical flow inputs. We establish, through comprehensive experiments, the first reproducible benchmarks for the state-of-the-art in vision-based infant respiration estimation. We make our dataset, code repository, and trained models available for public use.

Juyi Lin, Arash Akbari, Yumei He et al.

Generative world models are increasingly used for video generation, where learned simulators are expected to capture the physical rules that govern real-world dynamics. However, evaluating whether generated videos actually follow these rules remains challenging. Existing physics-focused video benchmarks have made important progress, but they still face three key challenges, including the coarse evaluation frameworks that hide law-specific failures, response biases and fatigue that undermine the validity of annotation judgments, and automated evaluators that are insufficiently physics-aware or difficult to audit. To address those challenges, we introduce PhyGround, a criteria-grounded benchmark for evaluating physical reasoning in video generation. The benchmark contains 250 curated prompts, each augmented with an expected physical outcome, and a taxonomy of 13 physical laws across solid-body mechanics, fluid dynamics, and optics. Each law is operationalized through observable sub-questions to enable per-law diagnostics. We evaluate eight modern video generation models through a large-scale, quality-controlled human study, grounded on social science lab experiment design. A total of 459 annotators provided 5,796 complete annotations and over 37.4K fine-grained labels; after quality control, the retained annotations exhibited high split-half model-ranking correlations (Spearman's rho > 0.90). To support reproducible automated evaluation, we release PhyJudge-9B, an open physics-specialized VLM judge. PhyJudge-9B achieves substantially lower aggregate relative bias than Gemini-3.1-Pro (3.3% vs. 16.6%). We release prompts, human annotations, model checkpoints, and evaluation code on the project page https://phyground.github.io/.

Wen Xie, Yanjun Zhu, Gijs Overgoor et al.

Advertisers commonly need multiple versions of the same advertisement (ad) at varying durations for a single campaign. The traditional approach involves manually selecting and re-editing shots from longer video ads to create shorter versions, which is labor-intensive and time-consuming. In this paper, we introduce a framework for automated video ad clipping using video summarization techniques. We are the first to frame video clipping as a shot selection problem, tailored specifically for advertising. Unlike existing general video summarization methods that primarily focus on visual content, our approach emphasizes the critical role of audio in advertising. To achieve this, we develop a two-stream audio-visual fusion model that predicts the importance of video frames, where importance is defined as the likelihood of a frame being selected in the firm-produced short ad. To address the lack of ad-specific datasets, we present AdSum204, a novel dataset comprising 102 pairs of 30-second and 15-second ads from real advertising campaigns. Extensive experiments demonstrate that our model outperforms state-of-the-art methods across various metrics, including Average Precision, Area Under Curve, Spearman, and Kendall.

Le Jiang, Shaotong Zhu, Yedi Luo et al.

In dynamic Neural Radiance Fields (NeRF) systems, state-of-the-art novel view synthesis methods often fail under significant viewpoint deviations, producing unstable and unrealistic renderings. To address this, we introduce Expanded Dynamic NeRF (ExpanDyNeRF), a monocular NeRF framework that leverages Gaussian splatting priors and a pseudo-ground-truth generation strategy to enable realistic synthesis under large-angle rotations. ExpanDyNeRF optimizes density and color features to improve scene reconstruction from challenging perspectives. We also present the Synthetic Dynamic Multiview (SynDM) dataset, the first synthetic multiview dataset for dynamic scenes with explicit side-view supervision-created using a custom GTA V-based rendering pipeline. Quantitative and qualitative results on SynDM and real-world datasets demonstrate that ExpanDyNeRF significantly outperforms existing dynamic NeRF methods in rendering fidelity under extreme viewpoint shifts. Further details are provided in the supplementary materials.

Adaeze Adigwe, Noé Tits, Kevin El Haddad et al.

In this paper, we present a database of emotional speech intended to be open-sourced and used for synthesis and generation purpose. It contains data for male and female actors in English and a male actor in French. The database covers 5 emotion classes so it could be suitable to build synthesis and voice transformation systems with the potential to control the emotional dimension in a continuous way. We show the data's efficiency by building a simple MLP system converting neutral to angry speech style and evaluate it via a CMOS perception test. Even though the system is a very simple one, the test show the efficiency of the data which is promising for future work.

Bishoy Galoaa, Xiangyu Bai, Sarah Ostadabbas

Vision-language models (VLMs) demonstrate impressive performance on standard video understanding benchmarks yet fail systematically on simple reasoning tasks that preschool children can solve, including counting, spatial reasoning, and compositional understanding. We hypothesize that the pedagogically-structured content of educational videos provides an ideal training signal for improving these capabilities. We introduce DoraVQA, a dataset of 5,344 question-answer pairs automatically extracted from 8 seasons of Dora the Explorer with precise timestamp alignment. Each episode follows a consistent \textit{context-question-pause-answer} structure that creates a self-contained learning environment analogous to interactive tutoring. We fine-tune both Qwen2 and Qwen3 using Group Relative Policy Optimization (GRPO), leveraging the clear correctness signals and structured reasoning traces inherent in educational content. Despite training exclusively on 38 hours of children's educational videos, our approach achieves improvements of 8-14 points on DoraVQA and state-of-the-art 86.16\% on CVBench, with strong transfer to Video-MME and NExT-QA, demonstrating effective generalization from narrow pedagogical content to broad multimodal understanding. Through cross-domain benchmarks, we show that VLMs can perform tasks that require robust reasoning learned from structured educational content, suggesting that content structure matters as much as content scale.

Bishoy Galoaa, Xiangyu Bai, Sarah Ostadabbas

We present Lang2Motion, a framework for language-guided point trajectory generation by aligning motion manifolds with joint embedding spaces. Unlike prior work focusing on human motion or video synthesis, we generate explicit trajectories for arbitrary objects using motion extracted from real-world videos via point tracking. Our transformer-based auto-encoder learns trajectory representations through dual supervision: textual motion descriptions and rendered trajectory visualizations, both mapped through CLIP's frozen encoders. Lang2Motion achieves 34.2% Recall@1 on text-to-trajectory retrieval, outperforming video-based methods by 12.5 points, and improves motion accuracy by 33-52% (12.4 ADE vs 18.3-25.3) compared to video generation baselines. We demonstrate 88.3% Top-1 accuracy on human action recognition despite training only on diverse object motions, showing effective transfer across motion domains. Lang2Motion supports style transfer, semantic interpolation, and latent-space editing through CLIP-aligned trajectory representations.

Xiangyu Bai, He Liang, Bishoy Galoaa et al.

While text-to-video (T2V) generation has achieved remarkable progress in photorealism, generating intent-aligned videos that faithfully obey physics principles remains a core challenge. In this work, we systematically study Newtonian motion-controlled text-to-video generation and evaluation, emphasizing physical precision and motion coherence. We introduce MoReGen, a motion-aware, physics-grounded T2V framework that integrates multi-agent LLMs, physics simulators, and renderers to generate reproducible, physically accurate videos from text prompts in the code domain. To quantitatively assess physical validity, we propose object-trajectory correspondence as a direct evaluation metric and present MoReSet, a benchmark of 1,275 human-annotated videos spanning nine classes of Newtonian phenomena with scene descriptions, spatiotemporal relations, and ground-truth trajectories. Using MoReSet, we conduct experiments on existing T2V models, evaluating their physical validity through both our MoRe metrics and existing physics-based evaluators. Our results reveal that state-of-the-art models struggle to maintain physical validity, while MoReGen establishes a principled direction toward physically coherent video synthesis.

Bishoy Galoaa, Pau Closas, Sarah Ostadabbas

Point tracking in video sequences is a foundational capability for real-world computer vision applications, including robotics, autonomous systems, augmented reality, and video analysis. While recent deep learning-based trackers achieve state-of-the-art accuracy on challenging benchmarks, their reliance on per-frame GPU inference poses a major barrier to deployment on resource-constrained edge devices, where compute, power, and connectivity are limited. We introduce K-Track (Kalman-enhanced Tracking), a general-purpose, tracker-agnostic acceleration framework designed to bridge this deployment gap. K-Track reduces inference cost by combining sparse deep learning keyframe updates with lightweight Kalman filtering for intermediate frame prediction, using principled Bayesian uncertainty propagation to maintain temporal coherence. This hybrid strategy enables 5-10X speedup while retaining over 85% of the original trackers' accuracy. We evaluate K-Track across multiple state-of-the-art point trackers and demonstrate real-time performance on edge platforms such as the NVIDIA Jetson Nano and RTX Titan. By preserving accuracy while dramatically lowering computational requirements, K-Track provides a practical path toward deploying high-quality point tracking in real-world, resource-limited settings, closing the gap between modern tracking algorithms and deployable vision systems.

Bishoy Galoaa, Sarah Ostadabbas

We propose Track and Caption Any Motion (TCAM), a motion-centric framework for automatic video understanding that discovers and describes motion patterns without user queries. Understanding videos in challenging conditions like occlusion, camouflage, or rapid movement often depends more on motion dynamics than static appearance. TCAM autonomously observes a video, identifies multiple motion activities, and spatially grounds each natural language description to its corresponding trajectory through a motion-field attention mechanism. Our key insight is that motion patterns, when aligned with contrastive vision-language representations, provide powerful semantic signals for recognizing and describing actions. Through unified training that combines global video-text alignment with fine-grained spatial correspondence, TCAM enables query-free discovery of multiple motion expressions via multi-head cross-attention. On the MeViS benchmark, TCAM achieves 58.4% video-to-text retrieval, 64.9 JF for spatial grounding, and discovers 4.8 relevant expressions per video with 84.7% precision, demonstrating strong cross-task generalization.

Bishoy Galoaa, Xiangyu Bai, Utsav Nandi et al.

We present UniTrack, a plug-and-play graph-theoretic loss function designed to significantly enhance multi-object tracking (MOT) performance by directly optimizing tracking-specific objectives through unified differentiable learning. Unlike prior graph-based MOT methods that redesign tracking architectures, UniTrack provides a universal training objective that integrates detection accuracy, identity preservation, and spatiotemporal consistency into a single end-to-end trainable loss function, enabling seamless integration with existing MOT systems without architectural modifications. Through differentiable graph representation learning, UniTrack enables networks to learn holistic representations of motion continuity and identity relationships across frames. We validate UniTrack across diverse tracking models and multiple challenging benchmarks, demonstrating consistent improvements across all tested architectures and datasets including Trackformer, MOTR, FairMOT, ByteTrack, GTR, and MOTE. Extensive evaluations show up to 53\% reduction in identity switches and 12\% IDF1 improvements across challenging benchmarks, with GTR achieving peak performance gains of 9.7\% MOTA on SportsMOT.

Le Jiang, Sarah Ostadabbas

Animal pose estimation has become a crucial area of research, but the scarcity of annotated data is a significant challenge in developing accurate models. Synthetic data has emerged as a promising alternative, but it frequently exhibits domain discrepancies with real data. Style transfer algorithms have been proposed to address this issue, but they suffer from insufficient spatial correspondence, leading to the loss of label information. In this work, we present a new approach called Synthetic Pose-aware Animal ControlNet (SPAC-Net), which incorporates ControlNet into the previously proposed Prior-Aware Synthetic animal data generation (PASyn) pipeline. We leverage the plausible pose data generated by the Variational Auto-Encoder (VAE)-based data generation pipeline as input for the ControlNet Holistically-nested Edge Detection (HED) boundary task model to generate synthetic data with pose labels that are closer to real data, making it possible to train a high-precision pose estimation network without the need for real data. In addition, we propose the Bi-ControlNet structure to separately detect the HED boundary of animals and backgrounds, improving the precision and stability of the generated data. Using the SPAC-Net pipeline, we generate synthetic zebra and rhino images and test them on the AP10K real dataset, demonstrating superior performance compared to using only real images or synthetic data generated by other methods. Our work demonstrates the potential for synthetic data to overcome the challenge of limited annotated data in animal pose estimation.

Shuangjun Liu, Sarah Ostadabbas

Computer vision has achieved great success in interpreting semantic meanings from images, yet estimating underlying (non-visual) physical properties of an object is often limited to their bulk values rather than reconstructing a dense map. In this work, we present our pressure eye (PEye) approach to estimate contact pressure between a human body and the surface she is lying on with high resolution from vision signals directly. PEye approach could ultimately enable the prediction and early detection of pressure ulcers in bed-bound patients, that currently depends on the use of expensive pressure mats. Our PEye network is configured in a dual encoding shared decoding form to fuse visual cues and some relevant physical parameters in order to reconstruct high resolution pressure maps (PMs). We also present a pixel-wise resampling approach based on Naive Bayes assumption to further enhance the PM regression performance. A percentage of correct sensing (PCS) tailored for sensing estimation accuracy evaluation is also proposed which provides another perspective for performance evaluation under varying error tolerances. We tested our approach via a series of extensive experiments using multimodal sensing technologies to collect data from 102 subjects while lying on a bed. The individual's high resolution contact pressure data could be estimated from their RGB or long wavelength infrared (LWIR) images with 91.8% and 91.2% estimation accuracies in $PCS_{efs0.1}$ criteria, superior to state-of-the-art methods in the related image regression/translation tasks.

Michael Wan, Shaotong Zhu, Lingfei Luan et al.

We lay the groundwork for research in the algorithmic comprehension of infant faces, in anticipation of applications from healthcare to psychology, especially in the early prediction of developmental disorders. Specifically, we introduce the first-ever dataset of infant faces annotated with facial landmark coordinates and pose attributes, demonstrate the inadequacies of existing facial landmark estimation algorithms in the infant domain, and train new state-of-the-art models that significantly improve upon those algorithms using domain adaptation techniques. We touch on the closely related task of facial detection for infants, and also on a challenging case study of infrared baby monitor images gathered by our lab as part of in-field research into the aforementioned developmental issues.

Rohit Josyula, Sarah Ostadabbas

The phenomenon of Human Pose Estimation (HPE) is a problem that has been explored over the years, particularly in computer vision. But what exactly is it? To answer this, the concept of a pose must first be understood. Pose can be defined as the arrangement of human joints in a specific manner. Therefore, we can define the problem of Human Pose Estimation as the localization of human joints or predefined landmarks in images and videos. There are several types of pose estimation, including body, face, and hand, as well as many aspects to it. This paper will cover them, starting with the classical approaches to HPE to the Deep Learning based models.

Divyang Teotia, Agata Lapedriza, Sarah Ostadabbas

This paper presents Hierarchical Network Dissection, a general pipeline to interpret the internal representation of face-centric inference models. Using a probabilistic formulation, our pipeline pairs units of the model with concepts in our "Face Dictionary", a collection of facial concepts with corresponding sample images. Our pipeline is inspired by Network Dissection, a popular interpretability model for object-centric and scene-centric models. However, our formulation allows to deal with two important challenges of face-centric models that Network Dissection cannot address: (1) spacial overlap of concepts: there are different facial concepts that simultaneously occur in the same region of the image, like "nose" (facial part) and "pointy nose" (facial attribute); and (2) global concepts: there are units with affinity to concepts that do not refer to specific locations of the face (e.g. apparent age). We use Hierarchical Network Dissection to dissect different face-centric inference models trained on widely-used facial datasets. The results show models trained for different tasks learned different internal representations. Furthermore, the interpretability results can reveal some biases in the training data and some interesting characteristics of the face-centric inference tasks. Finally, we conduct controlled experiments on biased data to showcase the potential of Hierarchical Network Dissection for bias discovery. The results illustrate how Hierarchical Network Dissection can be used to discover and quantify bias in the training data that is also encoded in the model.

Amirreza Farnoosh, Sarah Ostadabbas

In this paper, we propose a Bayesian switching dynamical model for segmentation of 3D pose data over time that uncovers interpretable patterns in the data and is generative. Our model decomposes highly correlated skeleton data into a set of few spatial basis of switching temporal processes in a low-dimensional latent framework. We parameterize these temporal processes with regard to a switching deep vector autoregressive prior in order to accommodate both multimodal and higher-order nonlinear inter-dependencies. This results in a dynamical deep generative latent model that parses the meaningful intrinsic states in the dynamics of 3D pose data using approximate variational inference, and enables a realistic low-level dynamical generation and segmentation of complex skeleton movements. Our experiments on four biological motion data containing bat flight, salsa dance, walking, and golf datasets substantiate superior performance of our model in comparison with the state-of-the-art methods.

Shuangjun Liu, Michael Wan, Sarah Ostadabbas

Monocular 3D human pose estimation from RGB images has attracted significant attention in recent years. However, recent models depend on supervised training with 3D pose ground truth data or known pose priors for their target domains. 3D pose data is typically collected with motion capture devices, severely limiting their applicability. In this paper, we present a heuristic weakly supervised 3D human pose (HW-HuP) solution to estimate 3D poses in when no ground truth 3D pose data is available. HW-HuP learns partial pose priors from 3D human pose datasets and uses easy-to-access observations from the target domain to estimate 3D human pose and shape in an optimization and regression cycle. We employ depth data for weak supervision during training, but not inference. We show that HW-HuP meaningfully improves upon state-of-the-art models in two practical settings where 3D pose data can hardly be obtained: human poses in bed, and infant poses in the wild. Furthermore, we show that HW-HuP retains comparable performance to cutting-edge models on public benchmarks, even when such models train on 3D pose data.

Shuangjun Liu, Naveen Sehgal, Sarah Ostadabbas

The ultimate goal for an inference model is to be robust and functional in real life applications. However, training vs. test data domain gaps often negatively affect model performance. This issue is especially critical for the monocular 3D human pose estimation problem, in which 3D human data is often collected in a controlled lab setting. In this paper, we focus on alleviating the negative effect of domain shift in both appearance and pose space for 3D human pose estimation by presenting our adapted human pose (AHuP) approach. AHuP is built upon two key components: (1) semantically aware adaptation (SAA) for the cross-domain feature space adaptation, and (2) skeletal pose adaptation (SPA) for the pose space adaptation which takes only limited information from the target domain. By using zero real 3D human pose data, one of our adapted synthetic models shows comparable performance with the SOTA pose estimation models trained with large scale real 3D human datasets. The proposed SPA can be also employed independently as a light-weighted head to improve existing SOTA models in a novel context. A new 3D scan-based synthetic human dataset called ScanAva+ is also going to be publicly released with this work.

Xiaofei Huang, Nihang Fu, Shuangjun Liu et al.

Infant motion analysis is a topic with critical importance in early childhood development studies. However, while the applications of human pose estimation have become more and more broad, models trained on large-scale adult pose datasets are barely successful in estimating infant poses due to the significant differences in their body ratio and the versatility of their poses. Moreover, the privacy and security considerations hinder the availability of adequate infant pose data required for training of a robust model from scratch. To address this problem, this paper presents (1) building and publicly releasing a hybrid synthetic and real infant pose (SyRIP) dataset with small yet diverse real infant images as well as generated synthetic infant poses and (2) a multi-stage invariant representation learning strategy that could transfer the knowledge from the adjacent domains of adult poses and synthetic infant images into our fine-tuned domain-adapted infant pose (FiDIP) estimation model. In our ablation study, with identical network structure, models trained on SyRIP dataset show noticeable improvement over the ones trained on the only other public infant pose datasets. Integrated with pose estimation backbone networks with varying complexity, FiDIP performs consistently better than the fine-tuned versions of those models. One of our best infant pose estimation performers on the state-of-the-art DarkPose model shows mean average precision (mAP) of 93.6.

Amirreza Farnoosh, Bahar Azari, Sarah Ostadabbas

We introduce deep switching auto-regressive factorization (DSARF), a deep generative model for spatio-temporal data with the capability to unravel recurring patterns in the data and perform robust short- and long-term predictions. Similar to other factor analysis methods, DSARF approximates high dimensional data by a product between time dependent weights and spatially dependent factors. These weights and factors are in turn represented in terms of lower dimensional latent variables that are inferred using stochastic variational inference. DSARF is different from the state-of-the-art techniques in that it parameterizes the weights in terms of a deep switching vector auto-regressive likelihood governed with a Markovian prior, which is able to capture the non-linear inter-dependencies among weights to characterize multimodal temporal dynamics. This results in a flexible hierarchical deep generative factor analysis model that can be extended to (i) provide a collection of potentially interpretable states abstracted from the process dynamics, and (ii) perform short- and long-term vector time series prediction in a complex multi-relational setting. Our extensive experiments, which include simulated data and real data from a wide range of applications such as climate change, weather forecasting, traffic, infectious disease spread and nonlinear physical systems attest the superior performance of DSARF in terms of long- and short-term prediction error, when compared with the state-of-the-art methods.

Shuangjun Liu, Xiaofei Huang, Nihang Fu et al.

Computer vision (CV) has achieved great success in interpreting semantic meanings from images, yet CV algorithms can be brittle for tasks with adverse vision conditions and the ones suffering from data/label pair limitation. One of this tasks is in-bed human pose estimation, which has significant values in many healthcare applications. In-bed pose monitoring in natural settings could involve complete darkness or full occlusion. Furthermore, the lack of publicly available in-bed pose datasets hinders the use of many successful pose estimation algorithms for this task. In this paper, we introduce our Simultaneously-collected multimodal Lying Pose (SLP) dataset, which includes in-bed pose images from 109 participants captured using multiple imaging modalities including RGB, long wave infrared, depth, and pressure map. We also present a physical hyper parameter tuning strategy for ground truth pose label generation under extreme conditions such as lights off and being fully covered by a sheet/blanket. SLP design is compatible with the mainstream human pose datasets, therefore, the state-of-the-art 2D pose estimation models can be trained effectively with SLP data with promising performance as high as 95% at PCKh@0.5 on a single modality. The pose estimation performance can be further improved by including additional modalities through collaboration.

Amirreza Farnoosh, Behnaz Rezaei, Eli Zachary Sennesh et al.

We introduce deep Markov spatio-temporal factorization (DMSTF), a generative model for dynamical analysis of spatio-temporal data. Like other factor analysis methods, DMSTF approximates high dimensional data by a product between time dependent weights and spatially dependent factors. These weights and factors are in turn represented in terms of lower dimensional latents inferred using stochastic variational inference. The innovation in DMSTF is that we parameterize weights in terms of a deep Markovian prior extendable with a discrete latent, which is able to characterize nonlinear multimodal temporal dynamics, and perform multidimensional time series forecasting. DMSTF learns a low dimensional spatial latent to generatively parameterize spatial factors or their functional forms in order to accommodate high spatial dimensionality. We parameterize the corresponding variational distribution using a bidirectional recurrent network in the low-level latent representations. This results in a flexible family of hierarchical deep generative factor analysis models that can be extended to perform time series clustering or perform factor analysis in the presence of a control signal. Our experiments, which include simulated and real-world data, demonstrate that DMSTF outperforms related methodologies in terms of predictive performance for unseen data, reveals meaningful clusters in the data, and performs forecasting in a variety of domains with potentially nonlinear temporal transitions.

Behnaz Rezaei, Amirreza Farnoosh, Sarah Ostadabbas

In this paper, we propose a computationally tractable and theoretically supported non-linear low-dimensional generative model to represent real-world data in the presence of noise and sparse outliers. The non-linear low-dimensional manifold discovery of data is done through describing a joint distribution over observations, and their low-dimensional representations (i.e. manifold coordinates). Our model, called generative low-dimensional background model (G-LBM) admits variational operations on the distribution of the manifold coordinates and simultaneously generates a low-rank structure of the latent manifold given the data. Therefore, our probabilistic model contains the intuition of the non-probabilistic low-dimensional manifold learning. G-LBM selects the intrinsic dimensionality of the underling manifold of the observations, and its probabilistic nature models the noise in the observation data. G-LBM has direct application in the background scenes model estimation from video sequences and we have evaluated its performance on SBMnet-2016 and BMC2012 datasets, where it achieved a performance higher or comparable to other state-of-the-art methods while being agnostic to the background scenes in videos. Besides, in challenges such as camera jitter and background motion, G-LBM is able to robustly estimate the background by effectively modeling the uncertainties in video observations in these scenarios.

Davoud Hejazi, Shuangjun Liu, Amirreza Farnoosh et al.

Due to their inherent variabilities,nanomaterial-based sensors are challenging to translate into real-world applications,where reliability/reproducibility is key.Recently we showed Bayesian inference can be employed on engineered variability in layered nanomaterial-based optical transmission filters to determine optical wavelengths with high accuracy/precision.In many practical applications the sensing cost/speed and long-term reliability can be equal or more important considerations.Though various machine learning tools are frequently used on sensor/detector networks to address these,nonetheless their effectiveness on nanomaterial-based sensors has not been explored.Here we show the best choice of ML algorithm in a cyber-nanomaterial detector is mainly determined by specific use considerations,e.g.,accuracy, computational cost,speed, and resilience against drifts/ageing effects.When sufficient data/computing resources are provided,highest sensing accuracy can be achieved by the kNN and Bayesian inference algorithms,but but can be computationally expensive for real-time applications.In contrast,artificial neural networks are computationally expensive to train,but provide the fastest result under testing conditions and remain reasonably accurate.When data is limited,SVMs perform well even with small training sets,while other algorithms show considerable reduction in accuracy if data is scarce,hence,setting a lower limit on the size of required training data.We show by tracking/modeling the long-term drifts of the detector performance over large (1year) period,it is possible to improve the predictive accuracy with no need for recalibration.Our research shows for the first time if the ML algorithm is chosen specific to use-case,low-cost solution-processed cyber-nanomaterial detectors can be practically implemented under diverse operational requirements,despite their inherent variabilities.

Behnaz Rezaei, Yiorgos Christakis, Bryan Ho et al.

Objective monitoring and assessment of human motor behavior can improve the diagnosis and management of several medical conditions. Over the past decade, significant advances have been made in the use of wearable technology for continuously monitoring human motor behavior in free-living conditions. However, wearable technology remains ill-suited for applications which require monitoring and interpretation of complex motor behaviors (e.g. involving interactions with the environment). Recent advances in computer vision and deep learning have opened up new possibilities for extracting information from video recordings. In this paper, we present a hierarchical vision-based behavior phenotyping method for classification of basic human actions in video recordings performed using a single RGB camera. Our method addresses challenges associated with tracking multiple human actors and classification of actions in videos recorded in changing environments with different fields of view. We implement a cascaded pose tracker that uses temporal relationships between detections for short-term tracking and appearance-based tracklet fusion for long-term tracking. Furthermore, for action classification, we use pose evolution maps derived from the cascaded pose tracker as low-dimensional and interpretable representations of the movement sequences for training a convolutional neural network. The cascaded pose tracker achieves an average accuracy of 88\% in tracking the target human actor in our video recordings, and overall system achieves average test accuracy of 84\% for target-specific action classification in untrimmed video recordings.

Shuangjun Liu, Sarah Ostadabbas

Human in-bed pose estimation has huge practical values in medical and healthcare applications yet still mainly relies on expensive pressure mapping (PM) solutions. In this paper, we introduce our novel physics inspired vision-based approach that addresses the challenging issues associated with the in-bed pose estimation problem including monitoring a fully covered person in complete darkness. We reformulated this problem using our proposed Under the Cover Imaging via Thermal Diffusion (UCITD) method to capture the high resolution pose information of the body even when it is fully covered by using a long wavelength IR technique. We proposed a physical hyperparameter concept through which we achieved high quality groundtruth pose labels in different modalities. A fully annotated in-bed pose dataset called Simultaneously-collected multimodal Lying Pose (SLP) is also formed/released with the same order of magnitude as most existing large-scale human pose datasets to support complex models' training and evaluation. A network trained from scratch on it and tested on two diverse settings, one in a living room and the other in a hospital room showed pose estimation performance of 99.5% and 95.7% in PCK0.2 standard, respectively. Moreover, in a multi-factor comparison with a state-of-the art in-bed pose monitoring solution based on PM, our solution showed significant superiority in all practical aspects by being 60 times cheaper, 300 times smaller, while having higher pose recognition granularity and accuracy.

Xiaofei Huang, Alaina Martens, Emily Zimmerman et al.

Non-nutritive sucking (NNS) is defined as the sucking action that occurs when a finger, pacifier, or other object is placed in the baby's mouth, but there is no nutrient delivered. In addition to providing a sense of safety, NNS even can be regarded as an indicator of infant's central nervous system development. The rich data, such as sucking frequency, the number of cycles, and their amplitude during baby's non-nutritive sucking is important clue for judging the brain development of infants or preterm infants. Nowadays most researchers are collecting NNS data by using some contact devices such as pressure transducers. However, such invasive contact will have a direct impact on the baby's natural sucking behavior, resulting in significant distortion in the collected data. Therefore, we propose a novel contact-less NNS data acquisition and quantification scheme, which leverages the facial landmarks tracking technology to extract the movement signals of baby's jaw from recorded baby's sucking video. Since completion of the sucking action requires a large amount of synchronous coordination and neural integration of the facial muscles and the cranial nerves, the facial muscle movement signals accompanying baby's sucking pacifier can indirectly replace the NNS signal. We have evaluated our method on videos collected from several infants during their NNS behaviors and we have achieved the quantified NNS patterns closely comparable to results from visual inspection as well as contact-based sensor readings.

Amirreza Farnoosh, Behnaz Rezaei, Sarah Ostadabbas

This paper presents a novel unsupervised probabilistic model estimation of visual background in video sequences using a variational autoencoder framework. Due to the redundant nature of the backgrounds in surveillance videos, visual information of the background can be compressed into a low-dimensional subspace in the encoder part of the variational autoencoder, while the highly variant information of its moving foreground gets filtered throughout its encoding-decoding process. Our deep probabilistic background model (DeepPBM) estimation approach is enabled by the power of deep neural networks in learning compressed representations of video frames and reconstructing them back to the original domain. We evaluated the performance of our DeepPBM in background subtraction on 9 surveillance videos from the background model challenge (BMC2012) dataset, and compared that with a standard subspace learning technique, robust principle component analysis (RPCA), which similarly estimates a deterministic low dimensional representation of the background in videos and is widely used for this application. Our method outperforms RPCA on BMC2012 dataset with 23% in average in F-measure score, emphasizing that background subtraction using the trained model can be done in more than 10 times faster.

Amirreza Farnoosh, Sarah Ostadabbas

Humans naturally perceive a 3D scene in front of them through accumulation of information obtained from multiple interconnected projections of the scene and by interpreting their correspondence. This phenomenon has inspired artificial intelligence models to extract the depth and view angle of the observed scene by modeling the correspondence between different views of that scene. Our paper is built upon previous works in the field of unsupervised depth and relative camera pose estimation from temporal consecutive video frames using deep learning (DL) models. Our approach uses a hybrid learning framework introduced in a recent work called GeoNet, which leverages geometric constraints in the 3D scenes to synthesize a novel view from intermediate DL-based predicted depth and relative pose. However, the state-of-the-art unsupervised depth and pose estimation DL models are exclusively trained/tested on a few available outdoor scene datasets and we have shown they are hardly transferable to new scenes, especially from indoor environments, in which estimation requires higher precision and dealing with probable occlusions. This paper introduces "Indoor GeoNet", a weakly supervised depth and camera pose estimation model targeted for indoor scenes. In Indoor GeoNet, we take advantage of the availability of indoor RGBD datasets collected by human or robot navigators, and added partial (i.e. weak) supervision in depth training into the model. Experimental results showed that our model effectively generalizes to new scenes from different buildings. Indoor GeoNet demonstrated significant depth and pose estimation error reduction when compared to the original GeoNet, while showing 3 times more reconstruction accuracy in synthesizing novel views in indoor environments.

Yu Yin, Mohsen Nabian, Miolin Fan et al.

In this paper, we present a multimodal approach to simultaneously analyze facial movements and several peripheral physiological signals to decode individualized affective experiences under positive and negative emotional contexts, while considering their personalized resting dynamics. We propose a person-specific recurrence network to quantify the dynamics present in the person's facial movements and physiological data. Facial movement is represented using a robust head vs. 3D face landmark localization and tracking approach, and physiological data are processed by extracting known attributes related to the underlying affective experience. The dynamical coupling between different input modalities is then assessed through the extraction of several complex recurrent network metrics. Inference models are then trained using these metrics as features to predict individual's affective experience in a given context, after their resting dynamics are excluded from their response. We validated our approach using a multimodal dataset consists of (i) facial videos and (ii) several peripheral physiological signals, synchronously recorded from 12 participants while watching 4 emotion-eliciting video-based stimuli. The affective experience prediction results signified that our multimodal fusion method improves the prediction accuracy up to 19% when compared to the prediction using only one or a subset of the input modalities. Furthermore, we gained prediction improvement for affective experience by considering the effect of individualized resting dynamics.

Shuangjun Liu, Sarah Ostadabbas

Deep learning approaches have been rapidly adopted across a wide range of fields because of their accuracy and flexibility, but require large labeled training datasets. This presents a fundamental problem for applications with limited, expensive, or private data (i.e. small data), such as human pose and behavior estimation/tracking which could be highly personalized. In this paper, we present a semi-supervised data augmentation approach that can synthesize large scale labeled training datasets using 3D graphical engines based on a physically-valid low dimensional pose descriptor. To evaluate the performance of our synthesized datasets in training deep learning-based models, we generated a large synthetic human pose dataset, called ScanAva using 3D scans of only 7 individuals based on our proposed augmentation approach. A state-of-the-art human pose estimation deep learning model then was trained from scratch using our ScanAva dataset and could achieve the pose estimation accuracy of 91.2% at PCK0.5 criteria after applying an efficient domain adaptation on the synthetic images, in which its pose estimation accuracy was comparable to the same model trained on large scale pose data from real humans such as MPII dataset and much higher than the model trained on other synthetic human dataset such as SURREAL.

Shuangjun Liu, Sarah Ostadabbas

Image-based generative methods, such as generative adversarial networks (GANs) have already been able to generate realistic images with much context control, specially when they are conditioned. However, most successful frameworks share a common procedure which performs an image-to-image translation with pose of figures in the image untouched. When the objective is reposing a figure in an image while preserving the rest of the image, the state-of-the-art mainly assumes a single rigid body with simple background and limited pose shift, which can hardly be extended to the images under normal settings. In this paper, we introduce an image "inner space" preserving model that assigns an interpretable low-dimensional pose descriptor (LDPD) to an articulated figure in the image. Figure reposing is then generated by passing the LDPD and the original image through multi-stage augmented hourglass networks in a conditional GAN structure, called inner space preserving generative pose machine (ISP-GPM). We evaluated ISP-GPM on reposing human figures, which are highly articulated with versatile variations. Test of a state-of-the-art pose estimator on our reposed dataset gave an accuracy over 80% on PCK0.5 metric. The results also elucidated that our ISP-GPM is able to preserve the background with high accuracy while reasonably recovering the area blocked by the figure to be reposed.

Behnaz Rezaei, Sarah Ostadabbas

Background subtraction is the primary task of the majority of video inspection systems. The most important part of the background subtraction which is common among different algorithms is background modeling. In this regard, our paper addresses the problem of background modeling in a computationally efficient way, which is important for current eruption of "big data" processing coming from high resolution multi-channel videos. Our model is based on the assumption that background in natural images lies on a low-dimensional subspace. We formulated and solved this problem in a low-rank matrix completion framework. In modeling the background, we benefited from the in-face extended Frank-Wolfe algorithm for solving a defined convex optimization problem. We evaluated our fast robust matrix completion (fRMC) method on both background models challenge (BMC) and Stuttgart artificial background subtraction (SABS) datasets. The results were compared with the robust principle component analysis (RPCA) and low-rank robust matrix completion (RMC) methods, both solved by inexact augmented Lagrangian multiplier (IALM). The results showed faster computation, at least twice as when IALM solver is used, while having a comparable accuracy even better in some challenges, in subtracting the backgrounds in order to detect moving objects in the scene.

Shuangjun Liu, Yu Yin, Sarah Ostadabbas

Although human pose estimation for various computer vision (CV) applications has been studied extensively in the last few decades, yet in-bed pose estimation using camera-based vision methods has been ignored by the CV community because it is assumed to be identical to the general purpose pose estimation methods. However, in-bed pose estimation has its own specialized aspects and comes with specific challenges including the notable differences in lighting conditions throughout a day and also having different pose distribution from the common human surveillance viewpoint. In this paper, we demonstrate that these challenges significantly lessen the effectiveness of existing general purpose pose estimation models. In order to address the lighting variation challenge, infrared selective (IRS) image acquisition technique is proposed to provide uniform quality data under various lighting conditions. In addition, to deal with unconventional pose perspective, a 2-end histogram of oriented gradient (HOG) rectification method is presented. In this work, we explored the idea of employing a pre-trained convolutional neural network (CNN) model trained on large public datasets of general human poses and fine-tuning the model using our own shallow in-bed IRS dataset. We developed an IRS imaging system and collected IRS image data from several realistic life-size mannequins in a simulated hospital room environment. A pre-trained CNN called convolutional pose machine (CPM) was repurposed for in-bed pose estimation by fine-tuning its specific intermediate layers. Using the HOG rectification method, the pose estimation performance of CPM significantly improved by 26.4% in PCK0.1 criteria compared to the model without such rectification.

Katie Hoemann, Behnaz Rezaei, Stacy C. Marsella et al.

Human interactions are characterized by explicit as well as implicit channels of communication. While the explicit channel transmits overt messages, the implicit ones transmit hidden messages about the communicator (e.g., his/her intentions and attitudes). There is a growing consensus that providing a computer with the ability to manipulate implicit affective cues should allow for a more meaningful and natural way of studying particular non-verbal signals of human-human communications by human-computer interactions. In this pilot study, we created a non-dynamic human-computer interaction while manipulating three specific non-verbal channels of communication: gaze pattern, facial expression, and gesture. Participants rated the virtual agent on affective dimensional scales (pleasure, arousal, and dominance) while their physiological signal (electrodermal activity, EDA) was captured during the interaction. Assessment of the behavioral data revealed a significant and complex three-way interaction between gaze, gesture, and facial configuration on the dimension of pleasure, as well as a main effect of gesture on the dimension of dominance. These results suggest a complex relationship between different non-verbal cues and the social context in which they are interpreted. Qualifying considerations as well as possible next steps are further discussed in light of these exploratory findings.