Human Mesh Recovery (HMR) is an important yet chal-lenging problem with applications across various domains including motion capture, augmented reality, and biome-chanics. Accurately predicting human pose parameters from a single image remains a challenging 3D computer vision task. In this work, we introduce DeforHMR, a novel regression-based monocular HMR framework designed to enhance the prediction of human pose parameters using deformable attention transformers. DeforHMR leverages a novel query-agnostic deformable cross-attention mecha-nism within the transformer decoder to effectively regress the visual features extracted from a frozen pretrained vision transformer (ViT) encoder. The proposed deformable cross-attention mechanism allows the model to attend to rel-evant spatial features more flexibly and in a data-dependent manner. Equipped with a transformer decoder capable of spatially-nuanced attention, DeforHMR achieves state-of-the-art performance for single-frame regression-based methods on the widely used 3D HMR benchmarks 3DPW and RICH. By pushing the boundary on the field of 3D hu-man mesh recovery through deformable attention, we intro-duce an new, effective paradigm for decoding local spatial information from large pretrained vision encoders in computer vision.

Reconstructing 3D human movements from video sequences is an important task in the fields of computer vision, graphics, and biomechanics. Although much progress has been made to infer 3D human mesh based on visual contexts provided in video sequences, generalization to in-the-wild videos still remains challenging for existing human mesh recovery (HMR) methods. To overcome inaccurate prediction, they can perform a second step optimization that refines the inaccurate estimations continuously at test time. Most optimization methods seek fitting of the body joints in the image space with respect to pseudo ground truth predicted by an off-the-shelf key point detector. However, state-of-theart detectors still introduce errors, especially for challenging poses. In this work, we rethink the dependency on the 2D key point fitting paradigm and present NeuHMR, an optimization-based mesh recovery framework based on recent advances in neural rendering. Our method builds on Human Neural Radiance Fields that allow the refinement of human meshes through animatable$2 D$renderings. We evaluated our method on two common benchmarks and validated its effectiveness.

Scientific research demands sophisticated reasoning over multimodal data, a challenge especially prevalent in biology. Despite recent advances in multimodal large language models (MLLMs) for AI-assisted research, existing multimodal reasoning benchmarks only target up to college-level difficulty, while research-level benchmarks emphasize lower-level perception, falling short of the complex multimodal reasoning needed for scientific discovery. To bridge this gap, we introduce MicroVQA, a visual-question answering (VQA) benchmark designed to assess three reasoning capabilities vital in research workflows: expert image understanding, hypothesis generation, and experiment proposal. MicroVQA consists of 1,042 multiple-choice questions (MCQs) curated by biology experts across diverse microscopy modalities, ensuring VQA samples represent real scientific practice. In constructing the benchmark, we find that standard MCQ generation methods induce language shortcuts, motivating a new two-stage pipeline: an optimized LLM prompt structures question-answer pairs into MCQs; then, an agent-based 'RefineBot' updates them to remove shortcuts. Benchmarking on state-of-the-art MLLMs reveal a peak performance of 53%; models with smaller LLMs only slightly underperform top models, suggesting that language-based reasoning is less challenging than multimodal reasoning; and tuning with scientific articles enhances performance. Expert analysis of chain-of-thought responses shows that perception errors are the most frequent, followed by knowledge errors and then overgeneralization errors. These insights highlight the challenges in multimodal scientific reasoning, showing MicroVQA is a valuable resource advancing AI-driven biomedical research. MicroVQA is available here, project here.

The development of vision-language models (VLMs) is driven by large-scale and diverse multi-modal datasets. However, progress toward generalist biomedical VLMs is limited by the lack of annotated, publicly accessible datasets across biology and medicine. Existing efforts are limited to narrow domains, missing the full diversity of biomedical knowledge encoded in scientific literature. To address this gap, we introduce BIOMEDICA: a scalable, open-source framework to extract, annotate, and serialize the entirety of the PubMed Central Open Access subset into an easy-to-use, publicly accessible dataset. Our framework produces a comprehensive archive with over 24 million unique image-text pairs from over 6 million articles. Metadata and expert-guided annotations are additionally provided.We demonstrate the utility and accessibility of our resource by releasing BMC-CLIP, a suite of CLIP-style models continuously pre-trained on BIOMEDICA dataset via streaming (eliminating the need to download 27 TB of data locally). On average, our models achieve state-of-the-art performance across 40 tasks — spanning pathology, radiology, ophthalmology, dermatology, surgery, molecular biology, parasitology, and cell biology — excelling in zero-shot classification with 6.56% average improvement (as high as 29.8% and 17.5% in dermatology and ophthalmology, respectively) and stronger image-text retrieval while using 10x less compute. To foster reproducibility and collaboration, we release our codebase1,2and dataset3to the broader research community.

The rapid development of vision language models (VLMs) demands rigorous and reliable evaluation. However, current visual question answering (VQA) benchmarks often depend on open-ended questions, making accurate evaluation difficult due to the variability in natural language responses. To address this, we introduce AutoConverter, an agentic framework that automatically converts these open-ended questions into multiple-choice format, enabling objective evaluation while reducing the costly multiple-choice question creation process. Our experiments demonstrate that AutoConverter can generate correct and challenging multiple-choice questions, with VLMs demonstrating consistently similar or lower accuracy on these questions compared to human-created ones. Using AutoConverter, we construct VMCBench, a benchmark created by transforming 20 existing VQA datasets into a unified multiple-choice format, totaling 9,018 questions. We comprehensively evaluate 33 state-of-the-art VLMs on VM-CBench, setting a new standard for scalable, consistent, and reproducible VLM evaluation.

Despite the rapid integration of video perception capabilities into Large Multimodal Models (LMMs), what drives their video perception remains poorly understood. Consequently, many design decisions in this domain are made without proper justification or analysis. The high computational cost of training and evaluating such models and limited open research hinder the development of video-LMMs. To address this, we present a comprehensive study that helps uncover what effectively drives video understanding in LMMs. We begin by critically examining the primary contributors to the high computational requirements associated with video-LMM research and discover Scaling Consistency, wherein design and training decisions made on smaller models and datasets (up to a critical size) effectively transfer to larger models. Leveraging these insights, we explored many video-specific aspects of video-LMMs, including video sampling, architectures, data composition, training schedules, and more. Guided by these findings, we introduce Apollo, a state-of-the-art family of LMMs that achieve superior performance across different model sizes. Our models process over 1-hour videos efficiently, with the 3B parameter variant outperforming most existing 7B models. Apollo-7B is state-of-the-art compared to 7B LMMs with a 70.9 on MLVU, and 63.3 on Video-MME.

Recent works on accelerating Vision-Language Models achieve strong performance across a variety of vision-language tasks despite highly compressing visual information. In this work, we examine the popular acceleration approach of early pruning of visual tokens inside the language model. Surprisingly, we find that while strong performance is maintained across many tasks, it exhibits drastically different behavior for a subset of vision-centric tasks such as localization. Upon further investigation, we uncover a core issue with the acceleration approach where most tokens towards the top of the image are pruned away. Yet, on many benchmarks aiming to evaluate vision-centric capabilities, strong performance persists with the flawed pruning strategy, highlighting these benchmarks' limited ability to assess fine-grained visual capabilities. Based on these findings, we propose FEATHER (Fast and Effective Acceleration wiTH Ensemble cRiteria), a straightforward approach that resolves the discovered early-layer pruning issue and further enhances the preservation of relevant tokens via multistage pruning with early uniform sampling to ensure broad image coverage. With comparable computational savings, we find that FEATHER achieves more than 5x performance improvement on the vision-centric localization benchmarks compared to the original acceleration approach.

How do two individuals differ when performing the same action? In this work, we introduce Video Action Differencing (VidDiff), the novel task of identifying subtle differences between videos of the same action, which has numerous applications, such as coaching and skill learning. To enable development on this new task, we first create VidDiffBench, a benchmark dataset containing 549 video pairs, with human annotations of 4,469 fine-grained action differences and 2,075 timestamps indicating where these differences occur. Our experiments demonstrate that VidDiffBench poses a significant challenge for state-of-the-art large multimodal models (LMMs), such as GPT-4o and Qwen2-VL. By analyzing the failure cases of LMMs on VidDiffBench, we highlight two key challenges for this task: localizing relevant sub-actions over two videos and fine-grained frame comparison. To overcome these, we propose the VidDiff method, an agentic workflow that breaks the task into three stages: action difference proposal, keyframe localization, and frame differencing, each stage utilizing specialized foundation models. To encourage future research in this new task, we release the benchmark and code.

Large pre-trained models, or foundation models, have shown impressive performance when adapted to a variety of downstream tasks, often out-performing specialized models. Hypernetworks, neural networks that generate some or all of the parameters of another neural network, have become an increasingly important technique for conditioning and generalizing implicit neural representations (INRs), which represent signals or objects such as audio or 3D shapes using a neural network. However, despite the potential benefits of incorporating foundation models in hypernetwork methods, this research direction has not been investigated, likely due to the dissimilarity of the weight generation task with other visual tasks. To address this gap, we (1) show how foundation models can improve hypernetworks with Transformer-based architectures, (2) provide an empirical analysis of the benefits of foundation models for hypernetworks through the lens of the generalizable INR task, showing that leveraging foundation models improves performance, generalizability, and data efficiency across a variety of algorithms and modalities. We also provide further analysis in examining the design space of foundation model-based hypernetworks, including examining the choice of foundation models, algorithms, and the effect of scaling foundation models.

The performance and reasoning capabilities of Large Multi-modal Models (LMMs) is dependent on the size and quality of their training datasets. However, collecting datasets that support chain-of-thought instruction tuning is highly challenging. Existing video instruction tuning datasets are often derived by prompting large language models with video captions to generate question-answer pairs, which makes them predominantly descriptive rather than reasoning-focused. Meanwhile, many labeled video datasets with diverse labels and supervision exist -- however, we find that their integration into LMMs is non-trivial. Herein, we present $\underline{\text{Video}}$ $\underline{\text{S}}\text{elf}$-$\underline{\text{T}}\text{raining}$ $\text{with}$ $\underline{\text{a}}\text{ugmented}$ $\underline{\text{R}}\text{easoning}$ (Video-STaR), the first self-training approach for video instruction tuning. Video-STaR allows the utilization of *any* labeled video dataset for video instruction tuning. In Video-STaR, an LMM cycles between instruction generation and finetuning, which we show (I) improves general video understanding and (II) adapts LMMs to novel downstream tasks with existing supervision. During instruction generation, an LMM is prompted to propose an answer. The answers are then filtered only to those that contain the original video labels, and the LMM is then re-trained on the generated dataset. By training exclusively on generated answers containing the correct video labels, Video-STaR leverages these existing labels as weak supervision for video instruction tuning. Our results demonstrate that Video-STaR-augmented LMMs achieve notable improvements in (I) general Video QA, where TempCompass performance improved by 6.1%, *and* (II) downstream tasks, with a 9.9% increase in Kinetics700-QA accuracy and a 4.0% improvement in action quality assessment on FineDiving, while also exhibiting better interpretability.

Building a virtual cell capable of accurately simulating cellular behaviors in silico has long been a dream in computational biology. We introduce CellFlux, an image-generative model that simulates cellular morphology changes induced by chemical and genetic perturbations using flow matching. Unlike prior methods, CellFlux models distribution-wise transformations from unperturbed to perturbed cell states, effectively distinguishing actual perturbation effects from experimental artifacts such as batch effects—a major challenge in biological data. Evaluated on chemical (BBBC021), genetic (RxRx1), and combined perturbation (JUMP) datasets, CellFlux generates biologically meaningful cell images that faithfully capture perturbation-specific morphological changes, achieving a 35% improvement in FID scores and a 12% increase in mode-of-action prediction accuracy over existing methods. Additionally, CellFlux enables continuous interpolation between cellular states, providing a potential tool for studying perturbation dynamics. These capabilities mark a significant step toward realizing virtual cell modeling for biomedical research. Project page: https://yuhui-zh15.github.io/CellFlux/.

Advancements in vision-language models (VLMs) have propelled the field of computer vision, particularly in the zero-shot learning setting. Despite their promise, the effectiveness of these models often diminishes due to domain shifts in test environments. To address this, we introduce the Test-Time Prototype Shifting (TPS) framework, a pio-neering approach designed to adapt VLMs to test datasets using unlabeled test inputs. Our method is based on the notion of modulating per-class prototypes in the shared embedding space. By pre-computing and caching prototypes generated with the pretrained text encoder, TPS not only facilitates optimization-free prototype reuse for subsequent predictions but also enables seamless integration with current advancements in prompt engineering. At test-time, TPS dynamically learns shift vectors for each prototype based solely on the given test sample, effectively bridging the domain gap and enhancing classification accuracy. A notable aspect of our framework is its significantly reduced memory and computational demands when compared to conventional text-prompt tuning methods. Extensive evaluations across 15 image classification datasets involving natural distribution shifts and cross-dataset generalization, as well as in context-dependent visual reasoning, demonstrate TPS's superior performance, achieving state-of-the-art results while reducing resource requirements. Code is available at https://github.com/elaine-sui/TPS.

Recent text-to-image generative models have exhibited remarkable abilities in generating high-fidelity and photorealistic images. However, despite the visually impressive results, these models often struggle to preserve plausible human structure in the generations. Due to this reason, while generative models have shown promising results in aiding downstream image recognition tasks by generating large volumes of synthetic data, they are not suitable for improving downstream human pose perception and understanding. In this work, we propose a Diffusion model with Human Pose Correction (Diffusion-HPC), a text-conditioned method that generates photo-realistic images with plausible posed humans by injecting prior knowledge about human body structure. Our generated images are accompanied by 3D meshes that serve as ground truths for improving Human Mesh Recovery tasks, where a short-age of 3D training data has long been an issue. Furthermore, we show that Diffusion-HPC effectively improves the realism of human generations under varying conditioning strategies.11Code: https://github.com/ZZWENG/Diffusion_HPC

How do two sets of images differ? Discerning set-level differences is crucial for understanding model behaviors and analyzing datasets, yet manually sifting through thousands of images is impractical. To aid in this discovery process, we explore the task of automatically describing the differences between two sets of images, which we term Set Difference Captioning. This task takes in image sets$\mathcal{D}_{A}$and$\mathcal{D}_{B}$, and outputs a description that is more often true on$\mathcal{D}_{A}$than$\mathcal{D}_{B}$. We outline a two-stage approach that first proposes candidate difference descriptions from image sets and then re-ranks the candidates by checking how well they can differentiate the two sets. We introduce VisDiff, which first captions the images and prompts a language model to propose candidate descriptions, then re-ranks these descriptions using CLIP. To evaluate VisDiff, we collect VisDiffBench, a dataset with 187 paired image sets with ground truth difference descriptions. We apply VisDiff to various domains, such as comparing datasets (e.g., ImageNet vs. ImageNetV2), comparing classification models (e.g., zero-shot CLIP vs. supervised ResNet), characterizing differences between generative models (e.g., StableDiffusionV1 and V2), and discovering what makes images memorable. Using VisDiff, we are able to find interesting and previously unknown differences in datasets and models, demonstrating its utility in revealing nuanced insights.11Project page available at https:/understanding-visual-datasets.github.io/VisDiff-website/.

Building cross-modal applications is challenging due to limited paired multi-modal data. Recent works have shown that leveraging a pre-trained multi-modal contrastive representation space enables cross-modal tasks to be learned from uni-modal data. This is based on the assumption that contrastive optimization makes embeddings from different modalities interchangeable. However, this assumption is under-explored due to the poorly understood geometry of the multi-modal contrastive space, where a modality gap exists. In our study, we provide a theoretical explanation of this space's geometry and introduce a three-step method, $C^3$ (Connect, Collapse, Corrupt), to bridge the modality gap, enhancing the interchangeability of embeddings. Our $C^3$ method significantly improves cross-modal learning from uni-modal data, achieving state-of-the-art results on zero-shot image / audio / video captioning and text-to-image generation.

Recent advances in microscopy have enabled the rapid generation of terabytes of image data in cell biology and biomedical research. Vision-language models (VLMs) offer a promising solution for large-scale biological image analysis, enhancing researchers’ efficiency, identifying new image biomarkers, and accelerating hypothesis generation and scientific discovery. However, there is a lack of standardized, diverse, and large-scale vision-language benchmarks to evaluate VLMs’ perception and cognition capabilities in biological image understanding. To address this gap, we introduce Micro-Bench, an expert-curated benchmark encompassing 24 biomedical tasks across various scientific disciplines (biology, pathology), microscopy modalities (electron, fluorescence, light), scales (subcellular, cellular, tissue), and organisms in both normal and abnormal states. We evaluate state-of-the-art biomedical, pathology, and general VLMs on Micro-Bench and find that: i) current models struggle on all categories, even for basic tasks such as distinguishing microscopy modalities; ii) current specialist models fine-tuned on biomedical data often perform worse than generalist models; iii) fine-tuning in specific microscopy domains can cause catastrophic forgetting, eroding prior biomedical knowledge encoded in their base model. iv) weight interpolation between fine-tuned and pre-trained models offers one solution to forgetting and improves general performance across biomedical tasks. We release Micro-Bench under a permissive license to accelerate the research and development of microscopy foundation models.

Image classification is one of the most fundamental capabilities of machine vision intelligence. In this work, we revisit the image classification task using visually-grounded language models (VLMs) such as GPT-4V and LLaVA. We find that existing proprietary and public VLMs, despite often using CLIP as a vision encoder and having many more parameters, significantly underperform CLIP on standard image classification benchmarks like ImageNet. To understand the reason, we explore several hypotheses concerning the inference algorithms, training objectives, and data processing in VLMs. Our analysis reveals that the primary cause is data-related: critical information for image classification is encoded in the VLM's latent space but can only be effectively decoded with enough training data. Specifically, there is a strong correlation between the frequency of class exposure during VLM training and instruction-tuning and the VLM's performance in those classes; when trained with sufficient data, VLMs can match the accuracy of state-of-the-art classification models. Based on these findings, we enhance a VLM by integrating classification-focused datasets into its training, and demonstrate that the enhanced classification performance of the VLM transfers to its general capabilities, resulting in an improvement of 11.8% on the newly collected ImageWikiQA dataset.

Abstract Deep representation learning is a ubiquitous part of modern computer vision. While Euclidean space has been the de facto standard manifold for learning visual representations, hyperbolic space has recently gained rapid traction for learning in computer vision. Specifically, hyperbolic learning has shown a strong potential to embed hierarchical structures, learn from limited samples, quantify uncertainty, add robustness, limit error severity, and more. In this paper, we provide a categorization and in-depth overview of current literature on hyperbolic learning for computer vision. We research both supervised and unsupervised literature and identify three main research themes in each direction. We outline how hyperbolic learning is performed in all themes and discuss the main research problems that benefit from current advances in hyperbolic learning for computer vision. Moreover, we provide a high-level intuition behind hyperbolic geometry and outline open research questions to further advance research in this direction.

The task of reconstructing 3D human motion has wide-ranging applications. The gold standard Motion capture (MoCap) systems are accurate but inaccessible to the general public due to their cost, hardware, and space constraints. In contrast, monocular human mesh recovery (HMR) methods are much more accessible than MoCap as they take single-view videos as inputs. Replacing the multi-view MoCap systems with a monocular HMR method would break the current barriers to collecting accurate 3D motion thus making exciting applications like motion analysis and motion-driven animation accessible to the general public. However, the performance of existing HMR methods degrades when the video contains challenging and dynamic motion that is not in existing MoCap datasets used for training. This reduces its appeal as dynamic motion is frequently the target in 3D motion recovery in the aforementioned applications. Our study aims to bridge the gap between monocular HMR and multi-view MoCap systems by leveraging information shared across multiple video instances of the same action. We introduce the Neural Motion (NeMo) field. It is optimized to represent the underlying 3D motions across a set of videos of the same action. Empirically, we show that NeMo can recover 3D motion in sports using videos from the Penn Action dataset, where NeMo outperforms existing HMR methods in terms of 2D keypoint detection. To further validate NeMo using 3D metrics, we collected a small MoCap dataset mimicking actions in Penn Action, and show that NeMo achieves better 3D reconstruction compared to various baselines.

Open World Object Detection (OWOD) is a new and challenging computer vision task that bridges the gap between classic object detection (OD) benchmarks and object detection in the real world. In addition to detecting and classifying seen/labeled objects, OWOD algorithms are expected to detect novel/unknown objects - which can be classified and incrementally learned. In standard OD, object proposals not overlapping with a labeled object are automatically classified as background. Therefore, simply applying OD methods to OWOD fails as unknown objects would be predicted as background. The challenge of detecting unknown objects stems from the lack of supervision in distinguishing unknown objects and background object proposals. Previous OWOD methods have attempted to overcome this issue by generating supervision using pseudo-labeling - however, unknown object detection has remained low. Probabilistic/generative models may provide a solution for this challenge. Herein, we introduce a novel probabilistic framework for objectness estimation, where we alternate between probability distribution estimation and objectness likelihood maximization of known objects in the embedded feature space - ultimately allowing us to estimate the objectness probability of different proposals. The resulting Probabilistic Objectness transformer-based open-world detector, PROB, integrates our framework into traditional object detection models, adapting them for the open-world setting. Comprehensive experiments on OWOD benchmarks show that PROB outperforms all existing OWOD methods in both unknown object detection (~ 2 × unknown recall) and known object detection (~ 10% mAP). Our code is available at https://github.com/orrzohar/PROB.

Neural fields, which represent signals as a function parameterized by a neural network, are a promising alternative to traditional discrete vector or grid-based representations. Compared to discrete representations, neural representations both scale well with increasing resolution, are continuous, and can be many-times differentiable. However, given a dataset of signals that we would like to represent, having to optimize a separate neural field for each signal is inefficient, and cannot capitalize on shared information or structures among signals. Existing generalization methods view this as a meta-learning problem and employ gradient-based meta-learning to learn an initialization which is then fine-tuned with test-time optimization, or learn hypernetworks to produce the weights of a neural field. We instead propose a new paradigm that views the large-scale training of neural representations as a part of a partially-observed neural process framework, and leverage neural process algorithms to solve this task. We demonstrate that this approach outperforms both state-of-the-art gradient-based meta-learning approaches and hypernetwork approaches.

Synthesizing information from various data sources plays a crucial role in the practice of modern medicine. Current applications of artificial intelligence in medicine often focus on single-modality data due to a lack of publicly available, multimodal medical datasets. To address this limitation, we introduce INSPECT, which contains de-identified longitudinal records from a large cohort of pulmonary embolism (PE) patients, along with ground truth labels for multiple outcomes. INSPECT contains data from 19,402 patients, including CT images, sections of radiology reports, and structured electronic health record (EHR) data (including demographics, diagnoses, procedures, and vitals). Using our provided dataset, we develop and release a benchmark for evaluating several baseline modeling approaches on a variety of important PE related tasks. We evaluate image-only, EHR-only, and fused models. Trained models and the de-identified dataset are made available for non-commercial use under a data use agreement. To the best our knowledge, INSPECT is the largest multimodal dataset for enabling reproducible research on strategies for integrating 3D medical imaging and EHR data.

Machine learning research has long focused on models rather than datasets, and prominent datasets are used for common ML tasks without regard to the breadth, difficulty, and faithfulness of the underlying problems. Neglecting the fundamental importance of data has given rise to inaccuracy, bias, and fragility in real-world applications, and research is hindered by saturation across existing dataset benchmarks. In response, we present DataPerf, a community-led benchmark suite for evaluating ML datasets and data-centric algorithms. We aim to foster innovation in data-centric AI through competition, comparability, and reproducibility. We enable the ML community to iterate on datasets, instead of just architectures, and we provide an open, online platform with multiple rounds of challenges to support this iterative development. The first iteration of DataPerf contains five benchmarks covering a wide spectrum of data-centric techniques, tasks, and modalities in vision, speech, acquisition, debugging, and diffusion prompting, and we support hosting new contributed benchmarks from the community. The benchmarks, online evaluation platform, and baseline implementations are open source, and the MLCommons Association will maintain DataPerf to ensure long-term benefits to academia and industry.

Pre-trained multi-modal vision-language models (VLMs) are becoming increasingly popular due to their exceptional performance on downstream vision applications, particularly in the few- and zero-shot settings. However, selecting the best-performing VLM for some downstream applications is non-trivial, as it is dataset and task-dependent. Meanwhile, the exhaustive evaluation of all available VLMs on a novel application is not only time and computationally demanding but also necessitates the collection of a labeled dataset for evaluation. As the number of open-source VLM variants increases, there is a need for an efficient model selection strategy that does not require access to a curated evaluation dataset. This paper proposes a novel task and benchmark for efficiently evaluating VLMs' zero-shot performance on downstream applications without access to the downstream task dataset. Specifically, we introduce a new task LOVM: Language-Only Vision Model Selection , where methods are expected to perform both model selection and performance prediction based solely on a text description of the desired downstream application. We then introduced an extensive LOVM benchmark consisting of ground-truth evaluations of 35 pre-trained VLMs and 23 datasets, where methods are expected to rank the pre-trained VLMs and predict their zero-shot performance.

The ability to perceive 3D human bodies from a single image has a multitude of applications ranging from entertainment and robotics to neuroscience and healthcare. A fundamental challenge in human mesh recovery is in collecting the ground truth 3D mesh targets required for training, which requires burdensome motion capturing systems and is often limited to indoor laboratories. As a result, while progress is made on benchmark datasets collected in these restrictive settings, models fail to generalize to real-world "in-the-wild" scenarios due to distribution shifts. We propose Domain Adaptive 3D Pose Augmentation (DAPA), a data augmentation method that enhances the model's generalization ability in in-the-wild scenarios. DAPA combines the strength of methods based on synthetic datasets by getting direct supervision from the synthesized meshes, and domain adaptation methods by using ground truth 2D keypoints from the target dataset. We show quantitatively that finetuning with DAPA effectively improves results on benchmarks 3DPW [38]and AGORA[32]. We further demonstrate the utility of DAPA on a challenging dataset curated from videos of real-world parent-child interaction.

We present modality gap, an intriguing geometric phenomenon of the representation space of multi-modal models. Specifically, we show that different data modalities (e.g. images and text) are embedded at arm's length in their shared representation in multi-modal models such as CLIP. Our systematic analysis demonstrates that this gap is caused by a combination of model initialization and contrastive learning optimization. In model initialization, we show empirically and theoretically that the representation of a common deep neural network is restricted to a narrow cone. As a consequence, in a multi-modal model with two encoders, the representations of the two modalities are clearly apart when the model is initialized. During optimization, contrastive learning keeps the different modalities separate by a certain distance, which is influenced by the temperature parameter in the loss function. Our experiments further demonstrate that varying the modality gap distance has a significant impact in improving the model's downstream zero-shot classification performance and fairness.

In the biomedical domain, there is an abundance of dense, complex data where objects of interest may be challenging to detect or constrained by limits of human knowledge. Labelled domain specific datasets for supervised tasks are often expensive to obtain, and furthermore discovery of novel distinct objects may be desirable for unbiased scientific discovery. Therefore, we propose leveraging the wealth of annotations in benchmark computer vision datasets to conduct unsupervised instance segmentation for diverse biomedical datasets. The key obstacle is thus overcoming the large domain shift from common to biomedical images. We propose a Domain Adaptive Region-based Convolutional Neural Network (DARCNN), that adapts knowledge of object definition from COCO, a large labelled vision dataset, to multiple biomedical datasets. We introduce a domain separation module, a self-supervised representation consistency loss, and an augmented pseudo-labelling stage within DARCNN to effectively perform domain adaptation across such large domain shifts. We showcase DARCNN’s performance for unsupervised instance segmentation on numerous biomedical datasets.

Instance segmentation is an active topic in computer vision that is usually solved by using supervised learning approaches over very large datasets composed of object level masks. Obtaining such a dataset for any new domain can be very expensive and time-consuming. In addition, models trained on certain annotated categories do not generalize well to unseen objects. The goal of this paper is to propose a method that can perform unsupervised discovery of long-tail categories in instance segmentation, through learning instance embeddings of masked regions. Leveraging rich relationship and hierarchical structure between objects in the images, we propose self-supervised losses for learning mask embeddings. Trained on COCO [34] dataset without additional annotations of the long-tail objects, our model is able to discover novel and more fine-grained objects than the common categories in COCO. We show that the model achieves competitive quantitative results on LVIS [17] as compared to the supervised and partially supervised methods.

The 3D world limits the human body pose and the human body pose conveys information about the surrounding objects. Indeed, from a single image of a person placed in an indoor scene, we as humans are adept at resolving ambiguities of the human pose and room layout through our knowledge of the physical laws and prior perception of the plausible object and human poses. However, few computer vision models fully leverage this fact. In this work, we pro-pose a holistically trainable model that perceives the 3D scene from a single RGB image, estimates the camera pose and the room layout, and reconstructs both human body and object meshes. By imposing a set of comprehensive and sophisticated losses on all aspects of the estimations, we show that our model outperforms existing human body mesh methods and indoor scene reconstruction methods. To the best of our knowledge, this is the first model that outputs both object and human predictions at the mesh level, and performs joint optimization on the scene and human poses.

In recent years, the growing utilization of medical imaging is placing an increasing burden on radiologists. Deep learning provides a promising solution for automatic medical image analysis and clinical decision support. However, large-scale manually labeled datasets required for training deep neural networks are difficult and expensive to obtain for medical images. The purpose of this work is to develop label-efficient multimodal medical imaging representations by leveraging radiology reports. We propose an attention-based framework for learning global and local representations by contrasting image sub-regions and words in the paired report. In addition, we propose methods to leverage the learned representations for various downstream medical image recognition tasks with limited labels. Our results demonstrate high-performance and label-efficiency for image-text retrieval, classification (finetuning and zerosshot settings), and segmentation on different datasets.

We consider the task of representation learning for unsupervised segmentation of 3D voxel-grid biomedical images. We show that models that capture implicit hierarchical relationships between subvolumes are better suited for this task. To that end, we consider encoder-decoder architectures with a hyperbolic latent space, to explicitly capture hierarchical relationships present in subvolumes of the data. We propose utilizing a 3D hyperbolic variational autoencoder with a novel gyroplane convolutional layer to map from the embedding space back to 3D images. To capture these relationships, we introduce an essential self-supervised loss---in addition to the standard VAE loss---which infers approximate hierarchies and encourages implicitly related subvolumes to be mapped closer in the embedding space. We present experiments on synthetic datasets along with a dataset from the medical domain to validate our hypothesis.

Creating representations of shapes that are invariant to isometric or almost-isometric transformations has long been an area of interest in shape analysis, since enforcing invariance allows the learning of more effective and robust shape representations. Most existing invariant shape representations are handcrafted, and previous work on learning shape representations do not focus on producing invariant representations. To solve the problem of learning unsupervised invariant shape representations, we use contrastive learning, which produces discriminative representations through learning invariance to user-specified data augmentations. To produce representations that are specifically isometry and almost-isometry invariant, we propose new data augmentations that randomly sample these transformations. We show experimentally that our method outperforms previous unsupervised learning approaches in both effectiveness and robustness.

OBJECTIVE: Hand hygiene is essential for preventing hospital-acquired infections but is difficult to accurately track. The gold-standard (human auditors) is insufficient for assessing true overall compliance. Computer vision technology has the ability to perform more accurate appraisals. Our primary objective was to evaluate if a computer vision algorithm could accurately observe hand hygiene dispenser use in images captured by depth sensors. MATERIALS AND METHODS: Sixteen depth sensors were installed on one hospital unit. Images were collected continuously from March to August 2017. Utilizing a convolutional neural network, a machine learning algorithm was trained to detect hand hygiene dispenser use in the images. The algorithm's accuracy was then compared with simultaneous in-person observations of hand hygiene dispenser usage. Concordance rate between human observation and algorithm's assessment was calculated. Ground truth was established by blinded annotation of the entire image set. Sensitivity and specificity were calculated for both human and machine-level observation. RESULTS: A concordance rate of 96.8% was observed between human and algorithm (kappa = 0.85). Concordance among the 3 independent auditors to establish ground truth was 95.4% (Fleiss's kappa = 0.87). Sensitivity and specificity of the machine learning algorithm were 92.1% and 98.3%, respectively. Human observations showed sensitivity and specificity of 85.2% and 99.4%, respectively. CONCLUSIONS: A computer vision algorithm was equivalent to human observation in detecting hand hygiene dispenser use. Computer vision monitoring has the potential to provide a more complete appraisal of hand hygiene activity in hospitals than the current gold-standard given its ability for continuous coverage of a unit in space and time.

Five billion people in the world lack access to quality surgical care. Surgeon skill varies dramatically, and many surgical patients suffer complications and avoidable harm. Improving surgical training and feedback would help to reduce the rate of complications-half of which have been shown to be preventable. To do this, it is essential to assess operative skill, a process that currently requires experts and is manual, time consuming, and subjective. In this work, we introduce an approach to automatically assess surgeon performance by tracking and analyzing tool movements in surgical videos, leveraging region-based convolutional neural networks. In order to study this problem, we also introduce a new dataset, m2cai16-tool-locations, which extends the m2cai16-tool dataset with spatial bounds of tools. While previous methods have addressed tool presence detection, ours is the first to not only detect presence but also spatially localize surgical tools in real-world laparoscopic surgical videos. We show that our method both effectively detects the spatial bounds of tools as well as significantly outperforms existing methods on tool presence detection. We further demonstrate the ability of our method to assess surgical quality through analysis of tool usage patterns, movement range, and economy of motion.

Recognizing human object interactions (HOI) is an important part of distinguishing the rich variety of human action in the visual world. While recent progress has been made in improving HOI recognition in the fully supervised setting, the space of possible human-object interactions is large and it is impractical to obtain labeled training data for all interactions of interest. In this work, we tackle the challenge of scaling HOI recognition to the long tail of categories through a zero-shot learning approach. We introduce a factorized model for HOI detection that disentangles reasoning on verbs and objects, and at test-time can therefore produce detections for novel verb-object pairs. We present experiments on the recently introduced large-scale HICODET dataset, and show that our model is able to both perform comparably to state-of-the-art in fully-supervised HOI detection, while simultaneously achieving effective zeroshot detection of new HOI categories.

Physiological signals such as heart rate can provide valuable information about an individuals state and activity. However, existing work on computer vision has not yet explored leveraging these signals to enhance egocentric video understanding. In this work, we propose a model for reasoning on multimodal data to jointly predict activities and energy expenditures. We use heart rate signals as privileged self-supervision to derive energy expenditure in a training stage. A multitask objective is used to jointly optimize the two tasks. Additionally, we introduce a dataset that contains 31 hours of egocentric video augmented with heart rate and acceleration signals. This study can lead to new applications such as a visual calorie counter.

Understanding the simultaneously very diverse and intricately fine-grained set of possible human actions is a critical open problem in computer vision. Manually labeling training videos is feasible for some action classes but doesnt scale to the full long-tailed distribution of actions. A promising way to address this is to leverage noisy data from web queries to learn new actions, using semi-supervised or webly-supervised approaches. However, these methods typically do not learn domain-specific knowledge, or rely on iterative hand-tuned data labeling policies. In this work, we instead propose a reinforcement learning-based formulation for selecting the right examples for training a classifier from noisy web search results. Our method uses Q-learning to learn a data labeling policy on a small labeled training dataset, and then uses this to automatically label noisy web data for new visual concepts. Experiments on the challenging Sports-1M action recognition benchmark as well as on additional fine-grained and newly emerging action classes demonstrate that our method is able to learn good labeling policies for noisy data and use this to learn accurate visual concept classifiers.

In this work we introduce a fully end-to-end approach for action detection in videos that learns to directly predict the temporal bounds of actions. Our intuition is that the process of detecting actions is naturally one of observation and refinement: observing moments in video, and refining hypotheses about when an action is occurring. Based on this insight, we formulate our model as a recurrent neural network-based agent that interacts with a video over time. The agent observes video frames and decides both where to look next and when to emit a prediction. Since backpropagation is not adequate in this non-differentiable setting, we use REINFORCE to learn the agent's decision policy. Our model achieves state-of-the-art results on the THUMOS'14 and ActivityNet datasets while observing only a fraction (2% or less) of the video frames.

Previous work on action recognition has focused on adapting hand-designed local features, such as SIFT or HOG, from static images to the video domain. In this paper, we propose using unsupervised feature learning as a way to learn features directly from video data. More specifically, we present an extension of the Independent Subspace Analysis algorithm to learn invariant spatio-temporal features from unlabeled video data. We discovered that, despite its simplicity, this method performs surprisingly well when combined with deep learning techniques such as stacking and convolution to learn hierarchical representations. By replacing hand-designed features with our learned features, we achieve classification results superior to all previous published results on the Hollywood2, UCF, KTH and YouTube action recognition datasets. On the challenging Hollywood2 and YouTube action datasets we obtain 53.3% and 75.8% respectively, which are approximately 5% better than the current best published results. Further benefits of this method, such as the ease of training and the efficiency of training and prediction, will also be discussed. You can download our code and learned spatio-temporal features here: http://ai.stanford.edu/~wzou/.