Jiaze Wang

Haowang Cui, Rui Chen, Tao Luo et al.

Training-free image editing has recently attracted increasing attention due to its ability to modify real images using powerful pre-trained diffusion and flow-matching models without additional training. However, existing inversion-based and differential-flow-based methods usually perform global latent transport, which inevitably propagates editing effects to non-target regions and leads to background leakage. To address this problem, we propose SAM-Flow, a source-anchored masked flow framework for localized training-free image editing. Instead of updating the whole latent representation, SAM-Flow first uses a scout image and token-grounded attention maps to localize the editable semantic regions. It then applies differential velocity updates only within these regions, while anchoring the remaining areas to the source-image latent trajectory. To further improve spatial stability and boundary naturalness, we introduce a time-varying source-anchored projection mechanism with dynamic soft masks, transition regions, and temporal mask accumulation. The proposed method is plug-and-play and can be integrated with mainstream flow-matching backbones such as Stable Diffusion 3 and FLUX without any fine-tuning. Extensive qualitative and quantitative experiments demonstrate that SAM-Flow achieves accurate semantic editing while significantly improving background preservation, providing a simple and general localized editing paradigm for training-free image editing. Code is available at: https://github.com/chwbob/Sam-Flow.

Hao Chen, Jiaze Wang, Kun Shao et al.

Trajectory prediction has been a crucial task in building a reliable autonomous driving system by anticipating possible dangers. One key issue is to generate consistent trajectory predictions without colliding. To overcome the challenge, we propose an efficient masked autoencoder for trajectory prediction (Traj-MAE) that better represents the complicated behaviors of agents in the driving environment. Specifically, our Traj-MAE employs diverse masking strategies to pre-train the trajectory encoder and map encoder, allowing for the capture of social and temporal information among agents while leveraging the effect of environment from multiple granularities. To address the catastrophic forgetting problem that arises when pre-training the network with multiple masking strategies, we introduce a continual pre-training framework, which can help Traj-MAE learn valuable and diverse information from various strategies efficiently. Our experimental results in both multi-agent and single-agent settings demonstrate that Traj-MAE achieves competitive results with state-of-the-art methods and significantly outperforms our baseline model.

Yi Wang, Jiaze Wang, Jinpeng Li et al.

Data augmentation is an effective regularization strategy for mitigating overfitting in deep neural networks, and it plays a crucial role in 3D vision tasks, where the point cloud data is relatively limited. While mixing-based augmentation has shown promise for point clouds, previous methods mix point clouds either on block level or point level, which has constrained their ability to strike a balance between generating diverse training samples and preserving the local characteristics of point clouds. Additionally, the varying importance of each part of the point clouds has not been fully considered, cause not all parts contribute equally to the classification task, and some parts may contain unimportant or redundant information. To overcome these challenges, we propose PointPatchMix, a novel approach that mixes point clouds at the patch level and integrates a patch scoring module to generate content-based targets for mixed point clouds. Our approach preserves local features at the patch level, while the patch scoring module assigns targets based on the content-based significance score from a pre-trained teacher model. We evaluate PointPatchMix on two benchmark datasets, ModelNet40 and ScanObjectNN, and demonstrate significant improvements over various baselines in both synthetic and real-world datasets, as well as few-shot settings. With Point-MAE as our baseline, our model surpasses previous methods by a significant margin, achieving 86.3% accuracy on ScanObjectNN and 94.1% accuracy on ModelNet40. Furthermore, our approach shows strong generalization across multiple architectures and enhances the robustness of the baseline model.

Bowen Wang, Chen Liang, Jiaze Wang et al.

Attaining the equilibrium state of a catalyst-adsorbate system is key to fundamentally assessing its effective properties, such as adsorption energy. Machine learning methods with finer supervision strategies have been applied to boost and guide the relaxation process of an atomic system and better predict its properties at the equilibrium state. In this paper, we present a novel graph neural network (GNN) supervision and prediction strategy DR-Label. The method enhances the supervision signal, reduces the multiplicity of solutions in edge representation, and encourages the model to provide node predictions that are graph structural variation robust. DR-Label first Deconstructs finer-grained equilibrium state information to the model by projecting the node-level supervision signal to each edge. Reversely, the model Reconstructs a more robust equilibrium state prediction by transforming edge-level predictions to node-level with a sphere-fitting algorithm. The DR-Label strategy was applied to three radically distinct models, each of which displayed consistent performance enhancements. Based on the DR-Label strategy, we further proposed DRFormer, which achieved a new state-of-the-art performance on the Open Catalyst 2020 (OC20) dataset and the Cu-based single-atom-alloyed CO adsorption (SAA) dataset. We expect that our work will highlight crucial steps for the development of a more accurate model in equilibrium state property prediction of a catalysis system.

Yingjie Feng, Yi Wang, Jiaze Wang et al.

Self-supervised contrastive learning has emerged as a powerful paradigm for skeleton-based action recognition by enforcing consistency in the embedding space. However, existing methods rely on binary contrastive objectives that overlook the intrinsic continuity of human motion, resulting in fragmented feature clusters and rigid class boundaries. To address these limitations, we propose TranCLR, a Transitional anchor-based Contrastive Learning framework that captures the continuous geometry of the action space. Specifically, the proposed Action Transitional Anchor Construction (ATAC) explicitly models the geometric structure of transitional states to enhance the model's perception of motion continuity. Building upon these anchors, a Multi-Level Geometric Manifold Calibration (MGMC) mechanism is introduced to adaptively calibrate the action manifold across multiple levels of continuity, yielding a smoother and more discriminative representation space. Extensive experiments on the NTU RGB+D, NTU RGB+D 120 and PKU-MMD datasets demonstrate that TranCLR achieves superior accuracy and calibration performance, effectively learning continuous and uncertainty-aware skeleton representations. The code is available at https://github.com/Philchieh/TranCLR.

Jiaze Wang, Qinghao Zhao, Zizheng Chen et al.

Traditional diagnosis of aortic valve disease relies on echocardiography, but its cost and required expertise limit its use in large-scale early screening. Photoplethysmography (PPG) has emerged as a promising screening modality due to its widespread availability in wearable devices and its ability to reflect underlying hemodynamic dynamics. However, the extreme scarcity of gold-standard labeled PPG data severely constrains the effectiveness of data-driven approaches. To address this challenge, we propose and validate a new paradigm, Physiology-Guided Self-Supervised Learning (PG-SSL), aimed at unlocking the value of large-scale unlabeled PPG data for efficient screening of Aortic Stenosis (AS) and Aortic Regurgitation (AR). Using over 170,000 unlabeled PPG samples from the UK Biobank, we formalize clinical knowledge into a set of PPG morphological phenotypes and construct a pulse pattern recognition proxy task for self-supervised pre-training. A dual-branch, gated-fusion architecture is then employed for efficient fine-tuning on a small labeled subset. The proposed PG-SSL framework achieves AUCs of 0.765 and 0.776 for AS and AR screening, respectively, significantly outperforming supervised baselines trained on limited labeled data. Multivariable analysis further validates the model output as an independent digital biomarker with sustained prognostic value after adjustment for standard clinical risk factors. This study demonstrates that PG-SSL provides an effective, domain knowledge-driven solution to label scarcity in medical artificial intelligence and shows strong potential for enabling low-cost, large-scale early screening of aortic valve disease.

Jiayi Tian, Jiaze Wang

Understanding 4D point cloud videos is essential for enabling intelligent agents to perceive dynamic environments. However, temporal scale bias across varying frame rates and distributional uncertainty in irregular point clouds make it highly challenging to design a unified and robust 4D backbone. Existing CNN or Transformer based methods are constrained either by limited receptive fields or by quadratic computational complexity, while neglecting these implicit distortions. To address this problem, we propose a novel dual invariant framework, termed \textbf{Gaussian Aware Temporal Scaling (GATS)}, which explicitly resolves both distributional inconsistencies and temporal. The proposed \emph{Uncertainty Guided Gaussian Convolution (UGGC)} incorporates local Gaussian statistics and uncertainty aware gating into point convolution, thereby achieving robust neighborhood aggregation under density variation, noise, and occlusion. In parallel, the \emph{Temporal Scaling Attention (TSA)} introduces a learnable scaling factor to normalize temporal distances, ensuring frame partition invariance and consistent velocity estimation across different frame rates. These two modules are complementary: temporal scaling normalizes time intervals prior to Gaussian estimation, while Gaussian modeling enhances robustness to irregular distributions. Our experiments on mainstream benchmarks MSR-Action3D (\textbf{+6.62\%} accuracy), NTU RGBD (\textbf{+1.4\%} accuracy), and Synthia4D (\textbf{+1.8\%} mIoU) demonstrate significant performance gains, offering a more efficient and principled paradigm for invariant 4D point cloud video understanding with superior accuracy, robustness, and scalability compared to Transformer based counterparts.

Ziyu Guo, Ray Zhang, Hao Chen et al.

The rapid advancement of Large Multi-modal Models (LMMs) has enabled their application in scientific problem-solving, yet their fine-grained capabilities remain under-explored. In this paper, we introduce SciVerse, a multi-modal scientific evaluation benchmark to thoroughly assess LMMs across 5,735 test instances in five distinct versions. We aim to investigate three key dimensions of LMMs: scientific knowledge comprehension, multi-modal content interpretation, and Chain-of-Thought (CoT) reasoning. To unveil whether LMMs possess sufficient scientific expertise, we first transform each problem into three versions containing different levels of knowledge required for solving, i.e., Knowledge-free, -lite, and -rich. Then, to explore how LMMs interpret multi-modal scientific content, we annotate another two versions, i.e., Vision-rich and -only, marking more question information from texts to diagrams. Comparing the results of different versions, SciVerse systematically examines the professional knowledge stock and visual perception skills of LMMs in scientific domains. In addition, to rigorously assess CoT reasoning, we propose a new scientific CoT evaluation strategy, conducting a step-wise assessment on knowledge and logical errors in model outputs. Our extensive evaluation of different LMMs on SciVerse reveals critical limitations in their scientific proficiency and provides new insights into future developments. Project page: https://sciverse-cuhk.github.io

Donghao Zhou, Jiancheng Huang, Jinbin Bai et al.

Text-to-image diffusion models can generate high-quality images but lack fine-grained control of visual concepts, limiting their creativity. Thus, we introduce component-controllable personalization, a new task that enables users to customize and reconfigure individual components within concepts. This task faces two challenges: semantic pollution, where undesired elements disrupt the target concept, and semantic imbalance, which causes disproportionate learning of the target concept and component. To address these, we design MagicTailor, a framework that uses Dynamic Masked Degradation to adaptively perturb unwanted visual semantics and Dual-Stream Balancing for more balanced learning of desired visual semantics. The experimental results show that MagicTailor achieves superior performance in this task and enables more personalized and creative image generation.

Hao Chen, Jiaze Wang, Ziyu Guo et al.

Sign language recognition (SLR) plays a vital role in facilitating communication for the hearing-impaired community. SLR is a weakly supervised task where entire videos are annotated with glosses, making it challenging to identify the corresponding gloss within a video segment. Recent studies indicate that the main bottleneck in SLR is the insufficient training caused by the limited availability of large-scale datasets. To address this challenge, we present SignVTCL, a multi-modal continuous sign language recognition framework enhanced by visual-textual contrastive learning, which leverages the full potential of multi-modal data and the generalization ability of language model. SignVTCL integrates multi-modal data (video, keypoints, and optical flow) simultaneously to train a unified visual backbone, thereby yielding more robust visual representations. Furthermore, SignVTCL contains a visual-textual alignment approach incorporating gloss-level and sentence-level alignment to ensure precise correspondence between visual features and glosses at the level of individual glosses and sentence. Experimental results conducted on three datasets, Phoenix-2014, Phoenix-2014T, and CSL-Daily, demonstrate that SignVTCL achieves state-of-the-art results compared with previous methods.

Xikai Yang, Juzheng Miao, Yuchen Yuan et al.

Medical large vision-language models (LVLMs) have demonstrated promising performance across various single-image question answering (QA) benchmarks, yet their capability in processing multi-image clinical scenarios remains underexplored. Unlike single image based tasks, medical tasks involving multiple images often demand sophisticated visual understanding capabilities, such as temporal reasoning and cross-modal analysis, which are poorly supported by current medical LVLMs. To bridge this critical gap, we present the Med-MIM instruction dataset, comprising 83.2K medical multi-image QA pairs that span four types of multi-image visual abilities (temporal understanding, reasoning, comparison, co-reference). Using this dataset, we fine-tune Mantis and LLaVA-Med, resulting in two specialized medical VLMs: MIM-LLaVA-Med and Med-Mantis, both optimized for multi-image analysis. Additionally, we develop the Med-MIM benchmark to comprehensively evaluate the medical multi-image understanding capabilities of LVLMs. We assess eight popular LVLMs, including our two models, on the Med-MIM benchmark. Experimental results show that both Med-Mantis and MIM-LLaVA-Med achieve superior performance on the held-in and held-out subsets of the Med-MIM benchmark, demonstrating that the Med-MIM instruction dataset effectively enhances LVLMs' multi-image understanding capabilities in the medical domain.

Yi Wang, Jiaze Wang, Ziyu Guo et al.

Recently Transformer-based models have advanced point cloud understanding by leveraging self-attention mechanisms, however, these methods often overlook latent information in less prominent regions, leading to increased sensitivity to perturbations and limited global comprehension. To solve this issue, we introduce PointACL, an attention-driven contrastive learning framework designed to address these limitations. Our method employs an attention-driven dynamic masking strategy that guides the model to focus on under-attended regions, enhancing the understanding of global structures within the point cloud. Then we combine the original pre-training loss with a contrastive learning loss, improving feature discrimination and generalization. Extensive experiments validate the effectiveness of PointACL, as it achieves state-of-the-art performance across a variety of 3D understanding tasks, including object classification, part segmentation, and few-shot learning. Specifically, when integrated with different Transformer backbones like Point-MAE and PointGPT, PointACL demonstrates improved performance on datasets such as ScanObjectNN, ModelNet40, and ShapeNetPart. This highlights its superior capability in capturing both global and local features, as well as its enhanced robustness against perturbations and incomplete data.

Quanjian Song, Donghao Zhou, Jingyu Lin et al.

Recent text-to-image models have revolutionized image generation, but they still struggle with maintaining concept consistency across generated images. While existing works focus on character consistency, they often overlook the crucial role of scenes in storytelling, which restricts their creativity in practice. This paper introduces scene-oriented story generation, addressing two key challenges: (i) scene planning, where current methods fail to ensure scene-level narrative coherence by relying solely on text descriptions, and (ii) scene consistency, which remains largely unexplored in terms of maintaining scene consistency across multiple stories. We propose SceneDecorator, a training-free framework that employs VLM-Guided Scene Planning to ensure narrative coherence across different scenes in a ``global-to-local'' manner, and Long-Term Scene-Sharing Attention to maintain long-term scene consistency and subject diversity across generated stories. Extensive experiments demonstrate the superior performance of SceneDecorator, highlighting its potential to unleash creativity in the fields of arts, films, and games.

Haowang Cui, Rui Chen, Tao Luo et al.

The task of synthesizing novel views from a single image is highly ill-posed due to multiple explanations for unobserved areas. Most current methods tend to generate unseen regions from ambiguity priors and interpolation near input views, which often lead to severe distortions. To address this limitation, we propose a novel model dubbed as UniView, which can leverage reference images from a similar object to provide strong prior information during view synthesis. More specifically, we construct a retrieval and augmentation system and employ a multimodal large language model (MLLM) to assist in selecting reference images that meet our requirements. Additionally, a plug-and-play adapter module with multi-level isolation layers is introduced to dynamically generate reference features for the target views. Moreover, in order to preserve the details of an original input image, we design a decoupled triple attention mechanism, which can effectively align and integrate multi-branch features into the synthesis process. Extensive experiments have demonstrated that our UniView significantly improves novel view synthesis performance and outperforms state-of-the-art methods on the challenging datasets.

Jiaze Wang, Rui Chen, Haowang Cui

Recent spatial control methods for text-to-image (T2I) diffusion models have shown compelling results. However, these methods still fail to precisely follow the control conditions and generate the corresponding images, especially when encountering the textual prompts that contain multiple objects or have complex spatial compositions. In this work, we present a LLM-guided framework called LLM\_Control to address the challenges of the controllable T2I generation task. By improving grounding capabilities, LLM\_Control is introduced to accurately modulate the pre-trained diffusion models, where visual conditions and textual prompts influence the structures and appearance generation in a complementary way. We utilize the multimodal LLM as a global controller to arrange spatial layouts, augment semantic descriptions and bind object attributes. The obtained control signals are injected into the denoising network to refocus and enhance attention maps according to novel sampling constraints. Extensive qualitative and quantitative experiments have demonstrated that LLM\_Control achieves competitive synthesis quality compared to other state-of-the-art methods across various pre-trained T2I models. It is noteworthy that LLM\_Control allows the challenging input conditions on which most of the existing methods

Zixu Zhao, Jiaze Wang, Max Horn et al.

Unsupervised object-centric learning methods allow the partitioning of scenes into entities without additional localization information and are excellent candidates for reducing the annotation burden of multiple-object tracking (MOT) pipelines. Unfortunately, they lack two key properties: objects are often split into parts and are not consistently tracked over time. In fact, state-of-the-art models achieve pixel-level accuracy and temporal consistency by relying on supervised object detection with additional ID labels for the association through time. This paper proposes a video object-centric model for MOT. It consists of an index-merge module that adapts the object-centric slots into detection outputs and an object memory module that builds complete object prototypes to handle occlusions. Benefited from object-centric learning, we only require sparse detection labels (0%-6.25%) for object localization and feature binding. Relying on our self-supervised Expectation-Maximization-inspired loss for object association, our approach requires no ID labels. Our experiments significantly narrow the gap between the existing object-centric model and the fully supervised state-of-the-art and outperform several unsupervised trackers.

Jiaze Wang, Kai Chen, Qi Dou

Category-level 6D pose estimation, aiming to predict the location and orientation of unseen object instances, is fundamental to many scenarios such as robotic manipulation and augmented reality, yet still remains unsolved. Precisely recovering instance 3D model in the canonical space and accurately matching it with the observation is an essential point when estimating 6D pose for unseen objects. In this paper, we achieve accurate category-level 6D pose estimation via cascaded relation and recurrent reconstruction networks. Specifically, a novel cascaded relation network is dedicated for advanced representation learning to explore the complex and informative relations among instance RGB image, instance point cloud and category shape prior. Furthermore, we design a recurrent reconstruction network for iterative residual refinement to progressively improve the reconstruction and correspondence estimations from coarse to fine. Finally, the instance 6D pose is obtained leveraging the estimated dense correspondences between the instance point cloud and the reconstructed 3D model in the canonical space. We have conducted extensive experiments on two well-acknowledged benchmarks of category-level 6D pose estimation, with significant performance improvement over existing approaches. On the representatively strict evaluation metrics of $3D_{75}$ and $5^{\circ}2 cm$, our method exceeds the latest state-of-the-art SPD by $4.9\%$ and $17.7\%$ on the CAMERA25 dataset, and by $2.7\%$ and $8.5\%$ on the REAL275 dataset. Codes are available at https://wangjiaze.cn/projects/6DPoseEstimation.html.

Anyi Rao, Jiaze Wang, Linning Xu et al.

Shots are key narrative elements of various videos, e.g. movies, TV series, and user-generated videos that are thriving over the Internet. The types of shots greatly influence how the underlying ideas, emotions, and messages are expressed. The technique to analyze shot types is important to the understanding of videos, which has seen increasing demand in real-world applications in this era. Classifying shot type is challenging due to the additional information required beyond the video content, such as the spatial composition of a frame and camera movement. To address these issues, we propose a learning framework Subject Guidance Network (SGNet) for shot type recognition. SGNet separates the subject and background of a shot into two streams, serving as separate guidance maps for scale and movement type classification respectively. To facilitate shot type analysis and model evaluations, we build a large-scale dataset MovieShots, which contains 46K shots from 7K movie trailers with annotations of their scale and movement types. Experiments show that our framework is able to recognize these two attributes of shot accurately, outperforming all the previous methods.

Qingqiu Huang, Yu Xiong, Anyi Rao et al.

Recent years have seen remarkable advances in visual understanding. However, how to understand a story-based long video with artistic styles, e.g. movie, remains challenging. In this paper, we introduce MovieNet -- a holistic dataset for movie understanding. MovieNet contains 1,100 movies with a large amount of multi-modal data, e.g. trailers, photos, plot descriptions, etc. Besides, different aspects of manual annotations are provided in MovieNet, including 1.1M characters with bounding boxes and identities, 42K scene boundaries, 2.5K aligned description sentences, 65K tags of place and action, and 92K tags of cinematic style. To the best of our knowledge, MovieNet is the largest dataset with richest annotations for comprehensive movie understanding. Based on MovieNet, we set up several benchmarks for movie understanding from different angles. Extensive experiments are executed on these benchmarks to show the immeasurable value of MovieNet and the gap of current approaches towards comprehensive movie understanding. We believe that such a holistic dataset would promote the researches on story-based long video understanding and beyond. MovieNet will be published in compliance with regulations at https://movienet.github.io.

Zhuotao Tian, Hengshuang Zhao, Michelle Shu et al.

Albeit intensively studied, false prediction and unclear boundaries are still major issues of salient object detection. In this paper, we propose a Region Refinement Network (RRN), which recurrently filters redundant information and explicitly models boundary information for saliency detection. Different from existing refinement methods, we propose a Region Refinement Module (RRM) that optimizes salient region prediction by incorporating supervised attention masks in the intermediate refinement stages. The module only brings a minor increase in model size and yet significantly reduces false predictions from the background. To further refine boundary areas, we propose a Boundary Refinement Loss (BRL) that adds extra supervision for better distinguishing foreground from background. BRL is parameter free and easy to train. We further observe that BRL helps retain the integrity in prediction by refining the boundary. Extensive experiments on saliency detection datasets show that our refinement module and loss bring significant improvement to the baseline and can be easily applied to different frameworks. We also demonstrate that our proposed model generalizes well to portrait segmentation and shadow detection tasks.