While image captioning provides isolated descriptions for individual images, and video captioning offers one single narrative for an entire video clip, our work explores an important middle ground: progress-aware video captioning at the frame level. This novel task aims to generate temporally fine-grained captions that not only accurately describe each frame but also capture the subtle progression of actions throughout a video sequence. Despite the strong capabilities of existing leading vision language models, they often struggle to discern the nuances of frame-wise differences. To address this, we propose ProgressCaptioner, a captioning model designed to capture the fine-grained temporal dynamics within an action sequence. Alongside, we develop the FrameCap dataset to support training and the FrameCapEval benchmark to assess caption quality. The results demonstrate that ProgressCaptioner significantly surpasses leading captioning models, producing precise captions that accurately capture action progression and set a new standard for temporal precision in video captioning. Finally, we showcase practical applications of our approach, specifically in aiding keyframe selection and advancing video understanding, highlighting its broad utility.
论文检索
输入标题、作者或关键词，从 8,216 篇学术成果中精准定位
Video Frame Interpolation aims to recover realistic missing frames between observed frames, generating a high-frame-rate video from a low-frame-rate video. However, without additional guidance, large motion between frames makes this problem ill-posed. Event-based Video Frame Interpolation (EVFI) addresses this challenge by using sparse, high-temporal-resolution event measurements as motion guidance. This guidance allows EVFI methods to significantly outperform frame-only methods. However, to date, EVFI methods have relied upon a limited set of paired event-frame training data, severely limiting their performance and generalization capabilities. In this work, we overcome the limited data challenge by adapting pre-trained video diffusion models trained on internet-scale datasets to EVFI. We experimentally validate our approach on real-world EVFI datasets, including a new one we introduce. Our method outperforms existing methods and generalizes across cameras far better than existing approaches.
Generalist vision language models (VLMs) have made significant strides in computer vision, but they fall short in specialized fields like healthcare, where expert knowledge is essential. Current large multimodal models like Gemini and GPT-4o are insufficient for medical tasks due to their reliance on memorized internet knowledge rather than the nuanced expertise required in healthcare. Meanwhile, existing medical VLMs (e.g. Med-Gemini) often lack expert consultation as part of their design, and many rely on outdated, static datasets that were not created with modern, large deep learning models in mind. VLMs are usually trained in three stages: vision pre-training, vision-language pre-training, and instruction fine-tuning (IFT). IFT has been typically applied using a mixture of generic and healthcare data. In contrast, we propose that for medical VLMs, a fourth stage of specialized IFT is necessary, which focuses on medical data and includes information from domain expert models. Domain expert models developed for medical use are crucial because they are specifically trained for certain clinical tasks, e.g. to detect tumors and classify abnormalities through segmentation and classification, which learn fine-grained features of medical data-features that are often too intricate for a VLM to capture effectively. This paper introduces a new framework, VILA-M3, for medical VLMs that utilizes domain knowledge via expert models. We argue that generic VLM architectures alone are not viable for real-world clinical applications and on-demand usage of domain-specialized expert model knowledge is critical for advancing AI in healthcare. Through our experiments, we show an improved state-of-the-art (SOTA) performance with an average improvement of ~9% over the prior SOTA model Med-Gemini and ~6% over models trained on the specific tasks. Our approach emphasizes the importance of domain expertise in creating precise, reliable VLMs for medical applications.
Unlike modern native digital videos, the restoration of old films requires addressing specific degradations inherent to analog sources. However, existing specialized methods still fall short compared to general video restoration techniques. In this work, we propose a new baseline to re-examine the challenges in old film restoration. First, we develop an improved Mamba-based framework, dubbed MambaOFR, which can dynamically adjust the degradation removal patterns by generating degradation-aware prompts to tackle the complex and composite degradations present in old films. Second, we introduce a flow-guided mask deformable alignment module to mitigate the propagation of structured defect features in the temporal domain. Third, we introduce the first benchmark dataset that includes both synthetic and real-world old film clips. Extensive experiments show that the proposed method achieves state-of-the-art performance, outperforming existing advanced approaches in old film restoration. The implementation and model is available at https://github.com/MaoAYD/MambaOFR.
Early-Bird Diffusion: Investigating and Leveraging Timestep-Aware Early-Bird Tickets in Diffusion Models for Efficient Training
PDF ↗Training diffusion models (DMs) requires substantial computational resources due to multiple forward and backward passes across numerous timesteps, motivating research into efficient training techniques. In this paper, we propose EB-Diff-Train, a new efficient DM training approach that is orthogonal to other methods of accelerating DM training, by investigating and leveraging Early-Bird (EB) tickets--sparse subnetworks that manifest early in the training process and maintain high generation quality. We first investigate the existence of traditional EB tickets in DMs, enabling competitive generation quality without fully training a dense model. Then, we delve into the concept of diffusion-dedicated EB tickets, drawing on insights from varying importance of different timestep regions. These tickets adapt their sparsity levels according to the importance of corresponding timestep regions, allowing for aggressive sparsity during non-critical regions while conserving computational resources for crucial timestep regions. Building on this, we develop an efficient DM training technique that derives timestep-aware EB tickets, trains them in parallel, and combines them during inference for image generation. Extensive experiments validate the existence of both traditional and timestep-aware EB tickets, as well as the effectiveness of our proposed EB-Diff-Train method. This approach can significantly reduce training time both spatially and temporally--achieving 2.9x 5.8x speedups over training unpruned dense models, and up to 10.3x faster training compared to standard train-prune-finetune pipelines--without compromising generative quality. Our code is available at https://github.com/GATECH-EIC/Early-Bird-Diffusion.
Text-to-image diffusion models have demonstrated remarkable capabilities in creating images highly aligned with user prompts, yet their proclivity for memorizing training set images has sparked concerns about the originality of the generated images and privacy issues, potentially leading to legal complications for both model owners and users, particularly when the memorized images contain proprietary content. Although methods to mitigate these issues have been suggested, enhancing privacy often results in a significant decrease in the utility of the outputs, as indicated by text-alignment scores. To bridge the research gap, we introduce a novel method, PRSS, which refines the classifier-free guidance approach in diffusion models by integrating prompt re-anchoring (PR) to improve privacy and incorporating semantic prompt search (SS) to enhance utility. Extensive experiments across various privacy levels demonstrate that our approach consistently improves the privacy-utility trade-off, establishing a new state-of-the-art.
CustomKD: Customizing Large Vision Foundation for Edge Model Improvement via Knowledge Distillation
PDF ↗We propose a novel knowledge distillation approach, CustomKD, that effectively leverages large vision foundation models (LVFMs) to enhance the performance of edge models (e.g., MobileNetV3). Despite recent advancements in LVFMs, such as DINOv2 and CLIP, their potential in knowledge distillation for enhancing edge models remains underexplored. While knowledge distillation is a promising approach for improving the performance of edge models, the discrepancy in model capacities and heterogeneous architectures between LVFMs and edge models poses a significant challenge. Our observation indicates that although utilizing larger backbones (e.g., ViT-S to ViT-L) in teacher models improves their downstream task performances, the knowledge distillation from the large teacher models fails to bring as much performance gain for student models as for teacher models due to the large model discrepancy. Our simple yet effective CustomKD customizes the well-generalized features inherent in LVFMs to a given student model in order to reduce model discrepancies. Specifically, beyond providing well-generalized original knowledge from teachers, CustomKD aligns the features of teachers to those of students, making it easy for students to understand and overcome the large model discrepancy overall. CustomKD significantly improves the performances of edge models in scenarios with unlabeled data such as unsupervised domain adaptation (e.g., OfficeHome and DomainNet) and semi-supervised learning (e.g., CIFAR-100 with 400 labeled samples and ImageNet with 1% labeled samples), achieving the new state-of-the-art performances.
Diffusion Bridge: Leveraging Diffusion Model to Reduce the Modality Gap Between Text and Vision for Zero-Shot Image Captioning
PDF ↗The modality gap between vision and text embeddings in CLIP presents a significant challenge for zero-shot image captioning, limiting effective cross-modal representation. Traditional approaches, such as noise injection and memory-based similarity matching, attempt to address this gap, yet these methods either rely on indirect alignment or relatively naive solutions with heavy computation. Diffusion Bridge introduces a novel approach to directly reduce this modality gap by leveraging Denoising Diffusion Probabilistic Models (DDPM), trained exclusively on text embeddings to model their distribution. Our approach is motivated by the observation that, while paired vision and text embeddings are relatively close, a modality gap still exists due to stable regions created by the contrastive loss. This gap can be interpreted as noise in cross-modal mappings, which we approximate as Gaussian noise. To bridge this gap, we employ a reverse diffusion process, where image embeddings are strategically introduced at an intermediate step in the reverse process, allowing them to be refined progressively toward the text embedding distribution. This process transforms vision embeddings into text-like representations closely aligned with paired text embeddings, effectively minimizing discrepancies between modalities. Experimental results demonstrate that these text-like vision embeddings significantly enhance alignment with their paired text embeddings, leading to improved zero-shot captioning performance on MSCOCO and Flickr30K. Diffusion Bridge achieves competitive results without reliance on memory banks or entity-driven methods, offering a novel pathway for cross-modal alignment and opening new possibilities for the application of diffusion models in multi-modal tasks. The source code is available at: https://github.com/mongeoroo/diffusion-bridge
Thanks to the introduction of large-scale datasets, deep-learning has become the mainstream approach for appearance-based gaze estimation problems. However, current large-scale datasets contain annotation errors and provide only a single vector for gaze annotation, lacking key information such as 3D eyeball structures. Limitations in annotation accuracy and variety have constrained the progress in research and development of deep-learning methods for appearance-based gaze-related tasks. In this paper, we present GazeGene, a new large-scale synthetic gaze dataset with photo-realistic samples. More importantly, GazeGene not only provides accurate gaze annotations, but also offers 3D annotations of vital eye structures such as the pupil, iris, eyeball, optical and visual axes for the first time. Experiments show that GazeGene achieves comparable quality and generalization ability with real-world datasets, even outperforms most existing datasets on high-resolution images. Furthermore, its 3D eyeball annotations expand the application of deep-learning methods on various gaze-related tasks, offering new insights into this field. The dataset is available at: https://phiai.buaa.edu.cn/GazeGene/.
Photography during night or in dark conditions typically suffers from noise, low light and blurring issues due to the dim environment and the common use of long exposure. Although Deblurring and Low-light Image Enhancement (LLIE) are related under these conditions, most approaches in image restoration solve these tasks separately. In this paper, we present an efficient and robust neural network for multi-task low-light image restoration. Instead of following the current tendency of Transformer-based models, we propose new attention mechanisms to enhance the receptive field of efficient CNNs. Our method reduces the computational costs in terms of parameters and MAC operations compared to previous methods. Our model, DarkIR, achieves new state-of-the-art results on the popular LOLBlur, LOLv2 and Real-LOLBlur datasets, being able to generalize on real-world night images.
Unsigned distance fields (UDFs) provide a versatile framework for representing a diverse array of 3D shapes, encompassing both watertight and non-watertight geometries. Traditional UDF learning methods typically require extensive training on large 3D shape datasets, which is costly and necessitates re-training for new datasets. This paper presents a novel neural framework, *LoSF-UDF*, for reconstructing surfaces from 3D point clouds by leveraging local shape functions to learn UDFs. We observe that 3D shapes manifest simple patterns in localized regions, prompting us to develop a training dataset of point cloud patches characterized by mathematical functions that represent a continuum from smooth surfaces to sharp edges and corners. Our approach learns features within a specific radius around each query point and utilizes an attention mechanism to focus on the crucial features for UDF estimation. Despite being highly lightweight, with only 653 KB of trainable parameters and a modest-sized training dataset with 0.5 GB storage, our method enables efficient and robust surface reconstruction from point clouds without requiring for shape-specific training. Furthermore, our method exhibits enhanced resilience to noise and outliers in point clouds compared to existing methods. We conduct comprehensive experiments and comparisons across various datasets, including synthetic and real-scanned point clouds, to validate our method's efficacy. Notably, our lightweight framework offers rapid and reliable initialization for other unsupervised iterative approaches, improving both the efficiency and accuracy of their reconstructions.
Generalizable Neural Radiance Fields (GNeRF) are recognized as one of the most promising techniques for novel view synthesis and 3D model generation in real-world applications. However, like other generative models in computer vision, ensuring their adversarial robustness against various threat models is essential for practical use. The pioneering work in this area, NeRFool, introduced a state-of-the-art attack that targets GNeRFs by manipulating source views before feature extraction, successfully disrupting the color and density results of the constructed views. Building on this foundation, we propose IL2-NeRF (Iterative L2 NeRF Attack), a novel adversarial attack method that explores a new threat model (in the L2 domain) for attacking GNeRFs. We evaluated IL2-NeRF against two standard GNeRF models across three benchmark datasets, demonstrating similar performance compared to NeRFool, based on the same evaluation metrics proposed by NeRFool. Our results establish IL2-NeRF as the first adversarial method for GNeRFs under the L2 norm. We establish a foundational L2 threat model for future research, enabling direct performance comparisons while introducing a smoother, image-wide perturbation approach in Adversarial 3D Reconstruction. Our code is available at: https://github.com/The-NRC-SCAR-Group/IL2-NeRF
The goal of image cropping is to identify visually appealing crops in an image. Conventional methods are trained on specific datasets and fail to adapt to new requirements. Recent breakthroughs in large vision-language models (VLMs) enable visual in-context learning without explicit training. However, downstream tasks with VLMs remain under explored. In this paper, we propose an effective approach to leverage VLMs for image cropping. First, we propose an efficient prompt retrieval mechanism for image cropping to automate the selection of in-context examples. Second, we introduce an iterative refinement strategy to iteratively enhance the predicted crops. The proposed framework, we refer to as Cropper, is applicable to a wide range of cropping tasks, including free-form cropping, subject-aware cropping, and aspect ratio-aware cropping. Extensive experiments demonstrate that Cropper significantly outperforms state-of-the-art methods across several benchmarks.
This paper proposes ShapeShifter, a new 3D generative model that learns to synthesize shape variations based on a single reference model. While generative methods for 3D objects have recently attracted much attention, current techniques often lack geometric details and/or require long training times and large resources. Our approach remedies these issues by combining sparse voxel grids and multiscale point, normal, and color sampling within an encoder-free neural architecture that can be trained efficiently and in parallel. We show that our resulting variations better capture the fine details of their original input and can capture more general types of surfaces than previous SDF-based methods. Moreover, we offer interactive generation of 3D shape variants, allowing more human control in the design loop if needed.
Synthesizing diverse and physically plausible Human-Scene Interactions (HSI) is pivotal for both computer animation and embodied AI. Despite encouraging progress, current methods mainly focus on developing separate controllers, each specialized for a specific interaction task. This significantly hinders the ability to tackle a wide variety of challenging HSI tasks that require the integration of multiple skills, e.g., sitting down while carrying an object (see Fig. 1). To address this issue, we present TokenHSI, a single, unified transformer-based policy capable of multi-skill unification and flexible adaptation. The key insight is to model the humanoid proprioception as a separate shared token and combine it with distinct task tokens via a masking mechanism. Such a unified policy enables effective knowledge sharing across skills, thereby facilitating the multi-task training. Moreover, our policy architecture supports variable length inputs, enabling flexible adaptation of learned skills to new scenarios. By training additional task tokenizers, we can not only modify the geometries of interaction targets but also coordinate multiple skills to address complex tasks. The experiments demonstrate that our approach can significantly improve versatility, adaptability, and extensibility in various HSI tasks.
QuCOOP: A Versatile Framework for Solving Composite and Binary-Parametrised Problems on Quantum Annealers
PDF ↗There is growing interest in solving computer vision problems such as mesh or point set alignment using Adiabatic Quantum Computing (AQC). Unfortunately, modern experimental AQC devices such as D-Wave only support Quadratic Unconstrained Binary Optimisation (QUBO) problems, which severely limits their applicability. This paper proposes a new way to overcome this limitation and introduces QuCOOP, an optimisation framework extending the scope of AQC to composite and binary-parametrised, possibly non-quadratic problems. The key idea of QuCOOP is to iteratively approximate the original objective function by a sequel of local (intermediate) QUBO forms, whose binary parameters can be sampled on AQC devices. We experiment with quadratic assignment problems, shape matching and point set registration without knowing the correspondences in advance. Our approach achieves state-of-the-art results across multiple instances of tested problems.
Anticipating the multimodality of future events lays the foundation for safe autonomous driving. However, multimodal motion prediction for traffic agents has been clouded by the lack of multimodal ground truth. Existing works predominantly adopt the winner-take-all training strategy to tackle this challenge, yet still suffer from limited trajectory diversity and uncalibrated mode confidence. While some approaches address these limitations by generating excessive trajectory candidates, they necessitate a post-processing stage to identify the most representative modes, a process lacking universal principles and compromising trajectory accuracy. We are thus motivated to introduce ModeSeq, a new multimodal prediction paradigm that models modes as sequences. Unlike the common practice of decoding multiple plausible trajectories in one shot, ModeSeq requires motion decoders to infer the next mode step by step, thereby more explicitly capturing the correlation between modes and significantly enhancing the ability to reason about multimodality. Leveraging the inductive bias of sequential mode prediction, we also propose the Early-Match-Take-All (EMTA) training strategy to diversify the trajectories further. Without relying on dense mode prediction or heuristic post-processing, ModeSeq considerably improves the diversity of multimodal output while attaining satisfactory trajectory accuracy, resulting in balanced performance on motion prediction benchmarks. Moreover, ModeSeq naturally emerges with the capability of mode extrapolation, which supports forecasting more behavior modes when the future is highly uncertain.
Image restoration (IR), a key area in computer vision, has entered a new era with deep learning. Recent research has shifted toward Selective State Space Models (Mamba) to overcome CNNs' limited receptive fields and Transformers' computational inefficiency. However, due to Mamba's inherent one-dimensional scanning limitations, recent approaches have introduced multi-directional scanning to bolster inter-sequence correlations. Despite these enhancements, these methods still struggle with managing local pixel correlations across various directions. Moreover, the recursive computation in Mamba's SSM leads to reduced efficiency. To resolve these issues, we exploit the mathematical congruences between linear attention and SSM within Mamba to propose a novel model, ACL, which leverages news designs to Activate the Capability of Linear attention for IR. ACL integrates linear attention blocks instead of SSM within Mamba, serving as the core component of encoders/decoders, and aims to preserve a global perspective while boosting computational efficiency. Furthermore, we have designed a simple yet robust local enhancement module with multi-scale dilated convolutions to extract both coarse and fine features to improve local detail recovery. Experimental results confirm that our ACL model excels in classical IR tasks such as de-raining and de-blurring, while maintaining relatively low parameter counts and FLOPs.
Improved Monocular Depth Prediction Using Distance Transform Over Pre-semantic Contours with Self-supervised Neural Networks
PDF ↗Monocular depth estimation (MDE) with self-supervised training approaches struggles in low-texture areas, where photometric losses may lead to ambiguous depth predictions. To address this, we propose a novel technique that enhances spatial information by applying a distance transform over pre-semantic contours, augmenting discriminative power in low texture regions. Our approach jointly estimates pre-semantic contours, depth and ego-motion. The pre-semantic contours are leveraged to produce new input images, with variance augmented by the distance transform in uniform areas. This approach results in more effective loss functions, enhancing the training process for depth and ego-motion. We demonstrate theoretically that the distance transform is the optimal variance-augmenting technique in this context. Through extensive experiments on KITTI and Cityscapes, our model demonstrates robust performance, surpassing conventional self-supervised methods in MDE.
Spatial Transport Optimization by Repositioning Attention Map for Training-Free Text-to-Image Synthesis
PDF ↗Diffusion-based text-to-image (T2I) models have recently excelled in high-quality image generation, particularly in a training-free manner, enabling cost-effective adaptability and generalization across diverse tasks. However, while the existing methods have been continuously focusing on several challenges such as "missing objects" and "mismatched attributes," another critical issue of "mislocated objects" remains where generated spatial positions fail to align with text prompts. Surprisingly, ensuring such seemingly basic functionality remains challenging in popular T2I models due to the inherent difficulty of imposing explicit spatial guidance via text forms. To address this, we propose STORM (Spatial Transport Optimization by Repositioning Attention Map), a novel training-free approach for spatially coherent T2I synthesis. STORM employs Spatial Transport Optimization (STO), rooted in optimal transport theory, to dynamically adjust object attention maps for precise spatial adherence, supported by a Spatial Transport (ST) Cost function that enhances spatial understanding. Our analysis shows that integrating spatial awareness is most effective in the early denoising stages, while later phases refine details. Extensive experiments demonstrate that STORM surpasses existing methods, effectively mitigating mislocated objects while improving missing and mismatched attributes, setting a new benchmark for spatial alignment in T2I synthesis.