Search

Multimodal Large Language Models (MLLMs) have recently demonstrated remarkable perceptual and reasoning abilities, typically comprising a Vision Encoder, an Adapter, and a Large Language Model (LLM). The adapter serves as the critical bridge between the visual and language components. However, training adapters with image-level supervision often results in significant misalignment, undermining the LLMs' capabilities and limiting the potential of Multimodal LLMs. To address this, we introduce Supervised Embedding Alignment (SEA), a token-level alignment method that leverages vision-language pre-trained models, such as CLIP, to align visual tokens with the LLM's embedding space through contrastive learning. This approach ensures a more coherent integration of visual and language representations, enhancing the performance and interpretability of multimodal LLMs while preserving their inherent capabilities. Extensive experiments show that SEA effectively improves MLLMs, particularly for smaller models, without adding extra data or inference computation. SEA also lays the groundwork for developing more general and adaptable solutions to enhance multimodal systems.

Diffusion models have demonstrated great success in text-to-video (T2V) generation. However, existing methods may face challenges when handling complex (long) video generation scenarios that involve multiple objects or dynamic changes in object numbers. To address these limitations, we propose VideoTetris, a novel framework that enables compositional T2V generation. Specifically, we propose spatio-temporal compositional diffusion to precisely follow complex textual semantics by manipulating and composing the attention maps of denoising networks spatially and temporally. Moreover, we propose an enhanced video data preprocessing to enhance the training data regarding motion dynamics and prompt understanding, equipped with a new reference frame attention mechanism to improve the consistency of auto-regressive video generation. Extensive experiments demonstrate that our VideoTetris achieves impressive qualitative and quantitative results in compositional T2V generation. Code is available at: https://github.com/YangLing0818/VideoTetris, Comment: Code: https://github.com/YangLing0818/VideoTetris

Recent advancements in text-to-image generation have been propelled by the development of diffusion models and multi-modality learning. However, since text is typically represented sequentially in these models, it often falls short in providing accurate contextualization and structural control. So the generated images do not consistently align with human expectations, especially in complex scenarios involving multiple objects and relationships. In this paper, we introduce the Scene Graph Adapter(SG-Adapter), leveraging the structured representation of scene graphs to rectify inaccuracies in the original text embeddings. The SG-Adapter's explicit and non-fully connected graph representation greatly improves the fully connected, transformer-based text representations. This enhancement is particularly notable in maintaining precise correspondence in scenarios involving multiple relationships. To address the challenges posed by low-quality annotated datasets like Visual Genome, we have manually curated a highly clean, multi-relational scene graph-image paired dataset MultiRels. Furthermore, we design three metrics derived from GPT-4V to effectively and thoroughly measure the correspondence between images and scene graphs. Both qualitative and quantitative results validate the efficacy of our approach in controlling the correspondence in multiple relationships.

This paper reports on the NTIRE 2024 Quality Assessment of AI-Generated Content Challenge, which will be held in conjunction with the New Trends in Image Restoration and Enhancement Workshop (NTIRE) at CVPR 2024. This challenge is to address a major challenge in the field of image and video processing, namely, Image Quality Assessment (IQA) and Video Quality Assessment (VQA) for AI-Generated Content (AIGC). The challenge is divided into the image track and the video track. The image track uses the AIGIQA-20K, which contains 20,000 AI-Generated Images (AIGIs) generated by 15 popular generative models. The image track has a total of 318 registered participants. A total of 1,646 submissions are received in the development phase, and 221 submissions are received in the test phase. Finally, 16 participating teams submitted their models and fact sheets. The video track uses the T2VQA-DB, which contains 10,000 AI-Generated Videos (AIGVs) generated by 9 popular Text-to-Video (T2V) models. A total of 196 participants have registered in the video track. A total of 991 submissions are received in the development phase, and 185 submissions are received in the test phase. Finally, 12 participating teams submitted their models and fact sheets. Some methods have achieved better results than baseline methods, and the winning methods in both tracks have demonstrated superior prediction performance on AIGC.

As an alternative to expensive expert evaluation, Image Aesthetic Assessment (IAA) stands out as a crucial task in computer vision. However, traditional IAA methods are typically constrained to a single data source or task, restricting the universality and broader application. In this work, to better align with human aesthetics, we propose a Unified Multi-modal Image Aesthetic Assessment (UNIAA) framework, including a Multi-modal Large Language Model (MLLM) named UNIAA-LLaVA and a comprehensive benchmark named UNIAA-Bench. We choose MLLMs with both visual perception and language ability for IAA and establish a low-cost paradigm for transforming the existing datasets into unified and high-quality visual instruction tuning data, from which the UNIAA-LLaVA is trained. To further evaluate the IAA capability of MLLMs, we construct the UNIAA-Bench, which consists of three aesthetic levels: Perception, Description, and Assessment. Extensive experiments validate the effectiveness and rationality of UNIAA. UNIAA-LLaVA achieves competitive performance on all levels of UNIAA-Bench, compared with existing MLLMs. Specifically, our model performs better than GPT-4V in aesthetic perception and even approaches the junior-level human. We find MLLMs have great potential in IAA, yet there remains plenty of room for further improvement. The UNIAA-LLaVA and UNIAA-Bench will be released.

Previous methods for Video Frame Interpolation (VFI) have encountered challenges, notably the manifestation of blur and ghosting effects. These issues can be traced back to two pivotal factors: unavoidable motion errors and misalignment in supervision. In practice, motion estimates often prove to be error-prone, resulting in misaligned features. Furthermore, the reconstruction loss tends to bring blurry results, particularly in misaligned regions. To mitigate these challenges, we propose a new paradigm called PerVFI (Perception-oriented Video Frame Interpolation). Our approach incorporates an Asymmetric Synergistic Blending module (ASB) that utilizes features from both sides to synergistically blend intermediate features. One reference frame emphasizes primary content, while the other contributes complementary information. To impose a stringent constraint on the blending process, we introduce a self-learned sparse quasi-binary mask which effectively mitigates ghosting and blur artifacts in the output. Additionally, we employ a normalizing flow-based generator and utilize the negative log-likelihood loss to learn the conditional distribution of the output, which further facilitates the generation of clear and fine details. Experimental results validate the superiority of PerVFI, demonstrating significant improvements in perceptual quality compared to existing methods. Codes are available at \url{https://github.com/mulns/PerVFI}, Comment: Accepted by CVPR 2024

In this research, we present a novel approach to motion customization in video generation, addressing the widespread gap in the thorough exploration of motion representation within video generative models. Recognizing the unique challenges posed by video's spatiotemporal nature, our method introduces Motion Embeddings, a set of explicit, temporally coherent one-dimensional embeddings derived from a given video. These embeddings are designed to integrate seamlessly with the temporal transformer modules of video diffusion models, modulating self-attention computations across frames without compromising spatial integrity. Our approach offers a compact and efficient solution to motion representation and enables complex manipulations of motion characteristics through vector arithmetic in the embedding space. Furthermore, we identify the Temporal Discrepancy in video generative models, which refers to variations in how different motion modules process temporal relationships between frames. We leverage this understanding to optimize the integration of our motion embeddings. Our contributions include the introduction of a tailored motion embedding for customization tasks, insights into the temporal processing differences in video models, and a demonstration of the practical advantages and effectiveness of our method through extensive experiments., Comment: Project Page: https://wileewang.github.io/MotionInversion/

We present the \textbf{D}ecoupled \textbf{VI}deo \textbf{S}egmentation (DVIS) framework, a novel approach for the challenging task of universal video segmentation, including video instance segmentation (VIS), video semantic segmentation (VSS), and video panoptic segmentation (VPS). Unlike previous methods that model video segmentation in an end-to-end manner, our approach decouples video segmentation into three cascaded sub-tasks: segmentation, tracking, and refinement. This decoupling design allows for simpler and more effective modeling of the spatio-temporal representations of objects, especially in complex scenes and long videos. Accordingly, we introduce two novel components: the referring tracker and the temporal refiner. These components track objects frame by frame and model spatio-temporal representations based on pre-aligned features. To improve the tracking capability of DVIS, we propose a denoising training strategy and introduce contrastive learning, resulting in a more robust framework named DVIS++. Furthermore, we evaluate DVIS++ in various settings, including open vocabulary and using a frozen pre-trained backbone. By integrating CLIP with DVIS++, we present OV-DVIS++, the first open-vocabulary universal video segmentation framework. We conduct extensive experiments on six mainstream benchmarks, including the VIS, VSS, and VPS datasets. Using a unified architecture, DVIS++ significantly outperforms state-of-the-art specialized methods on these benchmarks in both close- and open-vocabulary settings. Code:~\url{https://github.com/zhang-tao-whu/DVIS_Plus}.

The Segment Anything Model (SAM) achieves remarkable promptable segmentation given high-quality prompts which, however, often require good skills to specify. To make SAM robust to casual prompts, this paper presents the first comprehensive analysis on SAM's segmentation stability across a diverse spectrum of prompt qualities, notably imprecise bounding boxes and insufficient points. Our key finding reveals that given such low-quality prompts, SAM's mask decoder tends to activate image features that are biased towards the background or confined to specific object parts. To mitigate this issue, our key idea consists of calibrating solely SAM's mask attention by adjusting the sampling locations and amplitudes of image features, while the original SAM model architecture and weights remain unchanged. Consequently, our deformable sampling plugin (DSP) enables SAM to adaptively shift attention to the prompted target regions in a data-driven manner, facilitated by our effective robust training strategy (RTS). During inference, dynamic routing plugin (DRP) is proposed that toggles SAM between the deformable and regular grid sampling modes, conditioned on the input prompt quality. Thus, our solution, termed Stable-SAM, offers several advantages: 1) improved SAM's segmentation stability across a wide range of prompt qualities, while 2) retaining SAM's powerful promptable segmentation efficiency and generality, with 3) minimal learnable parameters (0.08 M) and fast adaptation (by 1 training epoch). Extensive experiments across multiple datasets validate the effectiveness and advantages of our approach, underscoring Stable-SAM as a more robust solution for segmenting anything. Codes will be released upon acceptance. https://github.com/fanq15/Stable-SAM, Comment: Smaller file size for the easy access. Codes will be released upon acceptance. https://github.com/fanq15/Stable-SAM

Video instance segmentation is a challenging task that serves as the cornerstone of numerous downstream applications, including video editing and autonomous driving. In this report, we present further improvements to the SOTA VIS method, DVIS. First, we introduce a denoising training strategy for the trainable tracker, allowing it to achieve more stable and accurate object tracking in complex and long videos. Additionally, we explore the role of visual foundation models in video instance segmentation. By utilizing a frozen VIT-L model pre-trained by DINO v2, DVIS demonstrates remarkable performance improvements. With these enhancements, our method achieves 57.9 AP and 56.0 AP in the development and test phases, respectively, and ultimately ranked 1st in the VIS track of the 5th LSVOS Challenge. The code will be available at https://github.com/zhang-tao-whu/DVIS.

Existing methods for interactive segmentation in radiance fields entail scene-specific optimization and thus cannot generalize across different scenes, which greatly limits their applicability. In this work we make the first attempt at Scene-Generalizable Interactive Segmentation in Radiance Fields (SGISRF) and propose a novel SGISRF method, which can perform 3D object segmentation for novel (unseen) scenes represented by radiance fields, guided by only a few interactive user clicks in a given set of multi-view 2D images. In particular, the proposed SGISRF focuses on addressing three crucial challenges with three specially designed techniques. First, we devise the Cross-Dimension Guidance Propagation to encode the scarce 2D user clicks into informative 3D guidance representations. Second, the Uncertainty-Eliminated 3D Segmentation module is designed to achieve efficient yet effective 3D segmentation. Third, Concealment-Revealed Supervised Learning scheme is proposed to reveal and correct the concealed 3D segmentation errors resulted from the supervision in 2D space with only 2D mask annotations. Extensive experiments on two real-world challenging benchmarks covering diverse scenes demonstrate 1) effectiveness and scene-generalizability of the proposed method, 2) favorable performance compared to classical method requiring scene-specific optimization.

Recent interactive segmentation methods iteratively take source image, user guidance and previously predicted mask as the input without considering the invariant nature of the source image. As a result, extracting features from the source image is repeated in each interaction, resulting in substantial computational redundancy. In this work, we propose the Feature Decoupling-Recycling Network (FDRN), which decouples the modeling components based on their intrinsic discrepancies and then recycles components for each user interaction. Thus, the efficiency of the whole interactive process can be significantly improved. To be specific, we apply the Decoupling-Recycling strategy from three perspectives to address three types of discrepancies, respectively. First, our model decouples the learning of source image semantics from the encoding of user guidance to process two types of input domains separately. Second, FDRN decouples high-level and low-level features from stratified semantic representations to enhance feature learning. Third, during the encoding of user guidance, current user guidance is decoupled from historical guidance to highlight the effect of current user guidance. We conduct extensive experiments on 6 datasets from different domains and modalities, which demonstrate the following merits of our model: 1) superior efficiency than other methods, particularly advantageous in challenging scenarios requiring long-term interactions (up to 4.25x faster), while achieving favorable segmentation performance; 2) strong applicability to various methods serving as a universal enhancement technique; 3) well cross-task generalizability, e.g., to medical image segmentation, and robustness against misleading user guidance., Comment: Accepted to ACM MM 2023

We present an experimental study of Rayleigh-B\'enard convection using liquid metal alloy gallium-indium-tin as the working fluid with a Prandtl number of $Pr=0.029$. The flow state and the heat transport were measured in a Rayleigh number range of $1.2\times10^{4} \le Ra \le 1.3\times10^{7}$. The temperature fluctuation at the cell centre is used as a proxy for the flow state. It is found that, as $Ra$ increases from the lower end of the parameter range, the flow evolves from a convection state to an oscillation state, a chaotic state, and finally a turbulent state for $Ra>10^5$. The study suggests that the large-scale circulation in the turbulent state is a residual of the cell structures near the onset of convection, which is in contrast with the case of $Pr\sim1$, where the cell structure is replaced by high-order flow modes transiently before the emergence of the large-scale circulation in the turbulent state. The evolution of the flow state is also reflected by the heat transport characterised by the Nusselt number $Nu$ and the probability density function (PDF) of the temperature fluctuation at the cell centre. It is found that the effective local heat transport scaling exponent $\gamma$, i.e., $Nu\sim Ra^{\gamma}$, changes continuously from $\gamma=0.49$ at $Ra\sim 10^4$ to $\gamma=0.25$ for $Ra>10^6$. Meanwhile, the PDF at the cell centre gradually evolves from a Gaussian-like shape before the transition to turbulence to an exponential-like shape in the turbulent state. For $Ra>10^6$, the flow shows self-similar behaviour, which is revealed by the universal shape of the PDF of the temperature fluctuation at the cell centre and a $Nu=0.19Ra^{0.25}$ scaling for the heat transport., Comment: 12 pages, 5 figures; Accepted for publication in the Journal of Fluid Mechanics

Video panoptic segmentation is a challenging task that serves as the cornerstone of numerous downstream applications, including video editing and autonomous driving. We believe that the decoupling strategy proposed by DVIS enables more effective utilization of temporal information for both "thing" and "stuff" objects. In this report, we successfully validated the effectiveness of the decoupling strategy in video panoptic segmentation. Finally, our method achieved a VPQ score of 51.4 and 53.7 in the development and test phases, respectively, and ultimately ranked 1st in the VPS track of the 2nd PVUW Challenge. The code is available at https://github.com/zhang-tao-whu/DVIS

Electromagnetic ion cyclotron waves are known to exhibit frequency chirping, contributing to the rapid scattering and acceleration of energetic particles. However, the physical mechanism of chirping remains elusive. Here, we propose a new model to explain the chirping and provide direct observational evidence for validation. Our results relate the frequency chirping of the wave to both the wave amplitude and magnetic field inhomogeneity for the first time. The general applicability of the model's underlying principle opens a new path toward understanding the frequency chirping of other waves., Comment: 8 pages, 3 figures

Magnetic field line curvature (FLC) scattering is a collisionless scattering mechanism that arises when a particle's gyro-radius is comparable to the magnetic field line's curvature radius, resulting in the breaking of the conservation of the first adiabatic invariant. Studies in recent years have explored the implications of FLC scattering on the precipitation of both ring current ions and radiation belt electrons. In this work, we first compare two previous FLC scattering coefficients using test particle calculations. Then, we systematically calculate diffusion coefficients from FLC scattering in radial and MLT directions for particles of various energy levels, as well as its sensitivity to the $Kp$ index. We find that the timescale of FLC scattering is sufficient to account for the sudden loss of MeV electrons near the geostationary orbit during disturbed times. Additionally, the decay time of ring current protons is on the order of hours to minutes, providing an explanation for the ring current decay throughout the recovery phase of magnetic storms. Lastly, we compare the effects of wave-particle resonant scattering and FLC scattering in the vicinity of the midnight equator. Our findings suggest that the impacts of FLC scattering on MeV electrons or hundreds keV protons with smaller pitch angle is comparable to, or even more significant than, the effects of whistler mode or EMIC wave resonant scattering. Our quantitative results should be useful to evaluate the importance of the effects of FLC scattering while modeling the dynamics of radiation belt and ring current.

Capitalizing on the rapid development of neural networks, recent video frame interpolation (VFI) methods have achieved notable improvements. However, they still fall short for real-world videos containing large motions. Complex deformation and/or occlusion caused by large motions make it an extremely difficult problem in video frame interpolation. In this paper, we propose a simple yet effective solution, H-VFI, to deal with large motions in video frame interpolation. H-VFI contributes a hierarchical video interpolation transformer (HVIT) to learn a deformable kernel in a coarse-to-fine strategy in multiple scales. The learnt deformable kernel is then utilized in convolving the input frames for predicting the interpolated frame. Starting from the smallest scale, H-VFI updates the deformable kernel by a residual in succession based on former predicted kernels, intermediate interpolated results and hierarchical features from transformer. Bias and masks to refine the final outputs are then predicted by a transformer block based on interpolated results. The advantage of such a progressive approximation is that the large motion frame interpolation problem can be decomposed into several relatively simpler sub-tasks, which enables a very accurate prediction in the final results. Another noteworthy contribution of our paper consists of a large-scale high-quality dataset, YouTube200K, which contains videos depicting a great variety of scenarios captured at high resolution and high frame rate. Extensive experiments on multiple frame interpolation benchmarks validate that H-VFI outperforms existing state-of-the-art methods especially for videos with large motions.

This paper proposes a novel video inpainting method. We make three main contributions: First, we extended previous Transformers with patch alignment by introducing Deformed Patch-based Homography (DePtH), which improves patch-level feature alignments without additional supervision and benefits challenging scenes with various deformation. Second, we introduce Mask Pruning-based Patch Attention (MPPA) to improve patch-wised feature matching by pruning out less essential features and using saliency map. MPPA enhances matching accuracy between warped tokens with invalid pixels. Third, we introduce a Spatial-Temporal weighting Adaptor (STA) module to obtain accurate attention to spatial-temporal tokens under the guidance of the Deformation Factor learned from DePtH, especially for videos with agile motions. Experimental results demonstrate that our method outperforms recent methods qualitatively and quantitatively and achieves a new state-of-the-art.

With the development of vehicular technologies on automation, electrification, and digitalization, vehicles are becoming more intelligent while being exposed to more complex, uncertain, and frequently occurring faults. In this paper, we look into the maintenance planning of an operating vehicle under fault condition and formulate it as a multi-criteria decision-making problem. The maintenance decisions are generated by route searching in road networks and evaluated based on risk assessment considering the uncertainty of vehicle breakdowns. Particularly, we consider two criteria, namely the risk of public time loss and the risk of mission delay, representing the concerns of the public sector and the private sector, respectively. A public time loss model is developed to evaluate the traffic congestion caused by a vehicle breakdown and the corresponding towing process. The Pareto optimal set of non-dominated decisions is derived by evaluating the risk of the decisions. We demonstrate the relevance of the problem and the effectiveness of the proposed method by numerical experiments derived from real-world scenarios. The experiments show that neglecting the risk of vehicle breakdown on public roads can cause a high risk of public time loss in dense traffic flow. With the proposed method, alternate decisions can be derived to reduce the risks of public time loss significantly with a low increase in the risk of mission delay. This study aims at catalyzing public-private partnership through collaborative decision-making between the private sector and the public sector, thus archiving a more sustainable transportation system in the future.

Temporal modeling is crucial for video super-resolution. Most of the video super-resolution methods adopt the optical flow or deformable convolution for explicitly motion compensation. However, such temporal modeling techniques increase the model complexity and might fail in case of occlusion or complex motion, resulting in serious distortion and artifacts. In this paper, we propose to explore the role of explicit temporal difference modeling in both LR and HR space. Instead of directly feeding consecutive frames into a VSR model, we propose to compute the temporal difference between frames and divide those pixels into two subsets according to the level of difference. They are separately processed with two branches of different receptive fields in order to better extract complementary information. To further enhance the super-resolution result, not only spatial residual features are extracted, but the difference between consecutive frames in high-frequency domain is also computed. It allows the model to exploit intermediate SR results in both future and past to refine the current SR output. The difference at different time steps could be cached such that information from further distance in time could be propagated to the current frame for refinement. Experiments on several video super-resolution benchmark datasets demonstrate the effectiveness of the proposed method and its favorable performance against state-of-the-art methods., Comment: CVPR 2022

This paper addresses the challenges of decision-making for autonomous vehicles under faults during a transport mission. A real-time decision-making problem of vehicle routing planning considering maintenance management is formulated as an optimization problem. The goal is to minimize the total time to finish the transport mission by selecting the optimal workshop to conduct the maintenance and the corresponding routes. Two methods are proposed to solve the optimization problem based on two methods of fundamental solutions: (1) Mixed Integer Programming; (2) Dijkstra's algorithm. We adapt these methods to solve the optimization problem and consider improving the computation efficiency. Numerical studies of test cases of highway and urban scenarios are presented to demonstrate the proposed methods, which show the feasibility and high computational efficiency of both methods., Comment: Accepted by the IEEE 9th International Conference on Industrial Engineering and Applications (ICIEA 2022). Date: November 2021. Email: taoxin@kth.se, zhaoyuan@hi.is, zhaoyuan.epslab@gmail.com

Scenario-based approaches have been receiving a huge amount of attention in research and engineering of automated driving systems. Due to the complexity and uncertainty of the driving environment, and the complexity of the driving task itself, the number of possible driving scenarios that an ADS or ADAS may encounter is virtually infinite. Therefore it is essential to be able to reason about the identification of scenarios and in particular critical ones that may impose unacceptable risk if not considered. Critical scenarios are particularly important to support design, verification and validation efforts, and as a basis for a safety case. In this paper, we present the results of a systematic literature review in the context of autonomous driving. The main contributions are: (i) introducing a comprehensive taxonomy for critical scenario identification methods; (ii) giving an overview of the state-of-the-art research based on the taxonomy encompassing 86 papers between 2017 and 2020; and (iii) identifying open issues and directions for further research. The provided taxonomy comprises three main perspectives encompassing the problem definition (the why), the solution (the methods to derive scenarios), and the assessment of the established scenarios. In addition, we discuss open research issues considering the perspectives of coverage, practicability, and scenario space explosion., Comment: 37 pages, 24 figures