Video Question Answering (VideoQA) aims to answer natural language questions based on the information observed in videos. Despite the recent success of Large Multimodal Models (LMMs) in image-language understanding and reasoning, they deal with VideoQA insufficiently by simply taking uniformly sampled frames as visual inputs, which ignores question-relevant visual clues. Moreover, there are no human annotations for question-critical timestamps in existing VideoQA datasets. In light of this, we propose a novel weakly supervised framework to enforce the LMMs to reason out the answers with question-critical moments as visual inputs. Specifically, we fuse the question and answer pairs as event descriptions to find multiple keyframes as target moments, which will be pseudo-labels. With these pseudo-labels as additionally weak supervision, we devise a lightweight Gaussian-based Contrastive Grounding (GCG) module. GCG learns multiple Gaussian functions to characterize the temporal structure of the video, and sample question-critical frames as positive moments to be the visual inputs of LMMs. Extensive experiments on several VideoQA benchmarks verify the effectiveness of our framework, and we achieve substantial improvements compared to previous state-of-the-art methods.
We introduce Lumiere -- a text-to-video diffusion model designed for synthesizing videos that portray realistic, diverse and coherent motion -- a pivotal challenge in video synthesis. To this end, we introduce a Space-Time U-Net architecture that generates the entire temporal duration of the video at once, through a single pass in the model. This is in contrast to existing video models which synthesize distant keyframes followed by temporal super-resolution -- an approach that inherently makes global temporal consistency difficult to achieve. By deploying both spatial and (importantly) temporal down- and up-sampling and leveraging a pre-trained text-to-image diffusion model, our model learns to directly generate a full-frame-rate, low-resolution video by processing it in multiple space-time scales. We demonstrate state-of-the-art text-to-video generation results, and show that our design easily facilitates a wide range of content creation tasks and video editing applications, including image-to-video, video inpainting, and stylized generation.
When training data is scarce, it is common to make use of a feature extractor that has been pre-trained on a large base dataset, either by fine-tuning its parameters on the ``target'' dataset or by directly adopting its representation as features for a simple classifier. Fine-tuning is ineffective for few-shot learning, since the target dataset contains only a handful of examples. However, directly adopting the features without fine-tuning relies on the base and target distributions being similar enough that these features achieve separability and generalization. This paper investigates whether better features for the target dataset can be obtained by training on fewer base classes, seeking to identify a more useful base dataset for a given task.We consider cross-domain few-shot image classification in eight different domains from Meta-Dataset and entertain multiple real-world settings (domain-informed, task-informed and uninformed) where progressively less detail is known about the target task. To our knowledge, this is the first demonstration that fine-tuning on a subset of carefully selected base classes can significantly improve few-shot learning. Our contributions are simple and intuitive methods that can be implemented in any few-shot solution. We also give insights into the conditions in which these solutions are likely to provide a boost in accuracy. We release the code to reproduce all experiments from this paper on GitHub. https://github.com/RafLaf/Few-and-Fewer.git
In high-end visual effects pipelines, a customized (and expensive) light stage system is (typically) used to scan an actor in order to acquire both geometry and texture for various expressions. Aiming towards democratization, we propose a novel pipeline for obtaining geometry and texture as well as enough expression information to build a customized person-specific animation rig without using a light stage or any other high-end hardware (or manual cleanup). A key novel idea consists of warping real-world images to align with the geometry of a template avatar and subsequently projecting the warped image into the template avatar's texture; importantly, this allows us to leverage baked-in real-world lighting/texture information in order to create surrogate facial features (and bridge the domain gap) for the sake of geometry reconstruction. Not only can our method be used to obtain a neutral expression geometry and de-lit texture, but it can also be used to improve avatars after they have been imported into an animation system (noting that such imports tend to be lossy, while also hallucinating various features). Since a default animation rig will contain template expressions that do not correctly correspond to those of a particular individual, we use a Simon Says approach to capture various expressions and build a person-specific animation rig (that moves like they do). Our aforementioned warping/projection method has high enough efficacy to reconstruct geometry corresponding to each expressions.
In this paper, we introduce Human-LRM, a single-stage feed-forward Large Reconstruction Model designed to predict human Neural Radiance Fields (NeRF) from a single image. Our approach demonstrates remarkable adaptability in training using extensive datasets containing 3D scans and multi-view capture. Furthermore, to enhance the model's applicability for in-the-wild scenarios especially with occlusions, we propose a novel strategy that distills multi-view reconstruction into single-view via a conditional triplane diffusion model. This generative extension addresses the inherent variations in human body shapes when observed from a single view, and makes it possible to reconstruct the full body human from an occluded image. Through extensive experiments, we show that Human-LRM surpasses previous methods by a significant margin on several benchmarks.
Image-guided robotic interventions represent a transformative frontier in surgery, blending advanced imaging and robotics for improved precision and outcomes. This paper addresses the critical need for integrating open-source platforms to enhance situational awareness in image-guided robotic research. We present an open-source toolset that seamlessly combines a physics-based constraint formulation framework, AMBF, with a state-of-the-art imaging platform application, 3D Slicer. Our toolset facilitates the creation of highly customizable interactive digital twins, that incorporates processing and visualization of medical imaging, robot kinematics, and scene dynamics for real-time robot control. Through a feasibility study, we showcase real-time synchronization of a physical robotic interventional environment in both 3D Slicer and AMBF, highlighting low-latency updates and improved visualization.
Histopathological image classification is an important task in medical image analysis. Recent approaches generally rely on weakly supervised learning due to the ease of acquiring case-level labels from pathology reports. However, patch-level classification is preferable in applications where only a limited number of cases are available or when local prediction accuracy is critical. On the other hand, acquiring extensive datasets with localized labels for training is not feasible. In this paper, we propose a semi-supervised patch-level histopathological image classification model, named CLASS-M, that does not require extensively labeled datasets. CLASS-M is formed by two main parts: a contrastive learning module that uses separated Hematoxylin and Eosin images generated through an adaptive stain separation process, and a module with pseudo-labels using MixUp. We compare our model with other state-of-the-art models on two clear cell renal cell carcinoma datasets. We demonstrate that our CLASS-M model has the best performance on both datasets. Our code is available at github.com/BzhangURU/Paper_CLASS-M/tree/main
Recent studies have highlighted the issue of stereotypical depictions for people of different identity groups in Text-to-Image (T2I) model generations. However, these existing approaches have several key limitations, including a noticeable lack of coverage of global identity groups in their evaluation, and the range of their associated stereotypes. Additionally, they often lack a critical distinction between inherently visual stereotypes, such as `underweight' or `sombrero', and culturally dependent stereotypes like `attractive' or `terrorist'. In this work, we address these limitations with a multifaceted approach that leverages existing textual resources to ground our evaluation of geo-cultural stereotypes in the generated images from T2I models. We employ existing stereotype benchmarks to identify and evaluate visual stereotypes at a global scale, spanning 135 nationality-based identity groups. We demonstrate that stereotypical attributes are thrice as likely to be present in images of these identities as compared to other attributes. We further investigate how disparately offensive the depictions of generated images are for different nationalities. Finally, through a detailed case study, we reveal how the 'default' representations of all identity groups have a stereotypical appearance. Moreover, for the Global South, images across different attributes are visually similar, even when explicitly prompted otherwise. CONTENT WARNING: Some examples may contain offensive stereotypes.
In this paper, we address a significant gap in the field of neuroimaging by introducing the largest-to-date public benchmark, BvEM, designed specifically for cortical blood vessel segmentation in Volume Electron Microscopy (VEM) images. The intricate relationship between cerebral blood vessels and neural function underscores the vital role of vascular analysis in understanding brain health. While imaging techniques at macro and mesoscales have garnered substantial attention and resources, the microscale VEM imaging, capable of revealing intricate vascular details, has lacked the necessary benchmarking infrastructure. As researchers delve deeper into the microscale intricacies of cerebral vasculature, our BvEM benchmark represents a critical step toward unraveling the mysteries of neurovascular coupling and its impact on brain function and pathology. The BvEM dataset is based on VEM image volumes from three mammal species: adult mouse, macaque, and human. We standardized the resolution, addressed imaging variations, and meticulously annotated blood vessels through semi-automatic, manual, and quality control processes, ensuring high-quality 3D segmentation. Furthermore, we developed a zero-shot cortical blood vessel segmentation method named TriSAM, which leverages the powerful segmentation model SAM for 3D segmentation. To lift SAM from 2D segmentation to 3D volume segmentation, TriSAM employs a multi-seed tracking framework, leveraging the reliability of certain image planes for tracking while using others to identify potential turning points. This approach, consisting of Tri-Plane selection, SAM-based tracking, and recursive redirection, effectively achieves long-term 3D blood vessel segmentation without model training or fine-tuning. Experimental results show that TriSAM achieved superior performances on the BvEM benchmark across three species.
Semantic Change Detection (SCD) is recognized as both a crucial and challenging task in the field of image analysis. Traditional methods for SCD have predominantly relied on the comparison of image pairs. However, this approach is significantly hindered by substantial imaging differences, which arise due to variations in shooting times, atmospheric conditions, and angles. Such discrepancies lead to two primary issues: the under-detection of minor yet significant changes, and the generation of false alarms due to temporal variances. These factors often result in unchanged objects appearing markedly different in multi-temporal images. In response to these challenges, the MapChange framework has been developed. This framework introduces a novel paradigm that synergizes temporal-invariant historical map data with contemporary high-resolution images. By employing this combination, the temporal variance inherent in conventional image pair comparisons is effectively mitigated. The efficacy of the MapChange framework has been empirically validated through comprehensive testing on two public datasets. These tests have demonstrated the framework's marked superiority over existing state-of-the-art SCD methods.