Singapore

Understanding motion is crucial for visual object tracking in complex and dynamic motion scenarios. However, existing methods often rely on simple template updates or temporal feature propagation, neglecting the effective mining and utilization of motion information. To address this issue, we propose a motion-aware spatio-temporal framework that achieves motion perception by explicitly matching motion patterns and modeling motion relationships between frames. Specifically, our method introduces a motion pattern dictionary that encodes diverse and representative motion patterns as learnable features, enabling effective motion modeling. During tracking, features from the search region retrieve the most relevant motion patterns from the dictionary to capture current motion dynamics. The decoder then integrates temporal motion correlations for enhanced motion awareness. Additionally, we incorporate geometric cues into the search region features to enhance spatial perception, mitigate occlusion-induced ambiguity, and improve foreground-background separation. Extensive experiments on seven challenging benchmarks show that our approach consistently outperforms existing methods, confirming the effectiveness of motion pattern modeling and geometry-guided enhancement in alleviating tracking drift. Our MoDTrack achieves a 1.2\% higher AUC score on the LaSOT benchmark compared to the latest state-of-the-art methods, further validating the superiority of our approach.

AAAI 2026

Motion-Aware Object Tracking via Motion and Geometry-Aware Cues

learning & optimization for cv

multi-modal vision

motion & tracking

### Welcome to the AE-PCOS Society's 20th Annual Meeting!


The AE-PCOS Society’s 20th Annual Meeting's theme will be Reflections and Directions. The meeting will aim to incorporate the perspectives of both long-time, contributing members of the Society and newer members of the Society, while highlighting the latest research findings in PCOS-related clinical and basic research.

The recorded content will be available to registrants only for three months after the meeting. 


To gain access to this event page you are required to register. 

For tickets to the event, please register [here](https://secure.ae-society.org/np/clients/aesociety/eventRegistration.jsp?forwardedFromSecureDomain=1&event=2). 

Please register for the AE-PCOS 2022 Conference to join the event.

AE-PCOS 2022

The AE-PCOS Society’s 20th Annual Meeting's theme are Reflections and Directions. The meeting aims to incorporate the perspectives of both long-time, contributing members of the Society and newer members of the Society, while highlighting the latest research findings in PCOS-related clinical and basic research.

poster

We are pleased to announce the Fortieth AAAI Conference on Artificial Intelligence (AAAI-26), which will be held in Singapore EXPO from January 20 to January 27, 2026.

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. AAAI-26 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and a range of other activities to be announced.<br><br>

To access this event page, you need to log in with the **email address you registered with**. <br>Access credentials will be sent to your email from Underline -  subject line "Welcome to AAAI 2026". Please be sure to check your spam email folder if you do not see an email confirmation right away.

Please log in

To access this event page, you are required to register.
Please complete your registration to continue.

We recommend reading [**the registration information**](https://aaai.org/conference/aaai/aaai-26/registration/) first.

**Online Registration Form**: https://aaai.getregistered.net/conference-2026 

Registration Required

We are pleased to announce the Fortieth AAAI Conference on Artificial Intelligence (AAAI-26), which will be held in Singapore EXPO from January 20 to January 27, 2026.

Microvascular invasion (MVI) is a critical prognostic factor that significantly impacts postoperative outcomes in hepatocellular carcinoma (HCC). As the current gold standard for the diagnosis of MVI is based on the postoperative histopathological examination of whole slide images, accurate preoperative prediction of MVI status using magnetic resonance imaging (MRI) presents both a substantial clinical imperative and a significant challenge. In order to discover reliable MRI-based imaging biomarkers to support clinical decision making and enhance the interpretability of deep learning-based diagnostic models, we propose a novel interpretable MVI prediction framework in which the shared latent visual attributes are first learned and then used for potential imaging biomarker extraction and MVI diagnosis, respectively. To ensure that the visual attributes of these biomarkers are generalizable across diverse patients, the similarity constraints at the intra-patient level and the inter-patient level are enforced within the learned feature space, enabling intuitive biomarker discovery directly from the original image space. To guarantee semantic alignment between biomarkers and the characteristics of individual patients, we introduce a novel classification mechanism that directly links the alignment between each biomarker and patient-specific characteristics with the prediction outcome, thereby ensuring a precise prediction of MVI. Furthermore, the interpretability of the model is enhanced by integrating a mask-based visual explanation method that regions in patient images that correspond to the identified biomarkers. Extensive experiments on two MVI prediction datasets: HCC-WCH and HCC-ZSH unequivocally demonstrate our method's superior performance in both classification accuracy and interpretability. Our code will be made publicly available shortly after publication.

Learning Latent Imaging Biomarkers for Interpretable Microvascular Invasion Prediction in Hepatocellular Carcinoma

Despite the tremendous success of neural networks, benign images can be corrupted by adversarial perturbations to deceive these models. Intriguingly, images differ in their attackability. Specifically, given an attack configuration, some images are easily corrupted, whereas others are more resistant. Evaluating image attackability has important applications in active learning, adversarial training, and attack enhancement. This prompts a growing interest in developing attackability measures. However, existing methods are scarce and suffer from two major limitations: (1) They rely on a model proxy to provide prior knowledge (e.g., gradients or minimal perturbation) to extract model-dependent image features. Unfortunately, in practice, many task-specific models are not readily accessible. (2) Extracted features characterizing image attackability lack visual interpretability, obscuring their direct relationship with the images. To address these, we propose a novel **Object Texture Intensity (OTI)**, a model-free and visually interpretable measure of image attackability, which measures image attackability as the texture intensity of the image's semantic object. Theoretically, we describe the principles of OTI from the perspectives of decision boundaries as well as the mid- and high-frequency characteristics of adversarial perturbations. Comprehensive experiments demonstrate that OTI is effective and computationally efficient. In addition, our OTI provides the adversarial machine learning community with a visual understanding of attackability.

OTI: A Model-free and Visually Interpretable Measure of Image Attackability

High-precision scene parsing tasks, including image matting and dichotomous segmentation, aim to accurately predict masks with extremely fine details (such as hair). Most existing methods focus on salient, single foreground objects. While interactive methods allow for target adjustment, their class-agnostic design restricts generalization across different categories. Furthermore, the scarcity of high-quality annotation has led to a reliance on inharmonious synthetic data, resulting in poor generalization to real-world scenarios. To this end, we propose a Foreground Consistent Learning model, dubbed as FCLM, to address the aforementioned issues. Specifically, we first introduce a Depth-Aware Distillation strategy where we transfer the depth-related knowledge for better foreground representation. Considering the data dilemma, we term the processing of synthetic data as domain adaptation problem where we propose a domain-invariant learning strategy to focus on foreground learning. To support interactive prediction, we contribute an Object-Oriented Decoder that can receive both visual and language prompts to predict the referring target. Experimental results show that our method quantitatively and qualitatively outperforms SOTA methods. The codes will be open-sourced upon acceptance of the paper.

Toward Real-World High-Precision Image Matting and Segmentation

3D Gaussian Splatting (3DGS) achieves impressive quality and rendering speed, but with millions of 3D Gaussians and significant storage and transmission costs. In this paper, we aim to develop a simple yet effective method called NeuralGS that compresses the original 3DGS into a compact representation. Our observation is that neural fields like NeRF can represent complex 3D scenes with Multi-Layer Perceptron (MLP) neural networks using only a few megabytes. Thus, NeuralGS effectively adopts the neural field representation to encode the attributes of 3D Gaussians with MLPs, only requiring a small storage size even for a large-scale scene. To achieve this, we adopt a clustering strategy and fit the Gaussians within each cluster using different tiny MLPs, based on importance scores of Gaussians as fitting weights. We experiment on multiple datasets, achieving a 91$\times$ average model size reduction without harming the visual quality.

NeuralGS: Bridging Neural Fields and 3D Gaussian Splatting for Compact 3D Representations

Image fusion aims to integrate comprehensive information from images acquired through multiple sources. However, images captured by diverse sensors often encounter various degradations that can negatively affect fusion quality. Traditional fusion methods generally treat image enhancement and fusion as separate processes, overlooking the inherent correlation between them; notably, the dominant regions in one modality of a fused image often indicate areas where the other modality might benefit from enhancement. Inspired by this observation, we introduce the concept of dominant regions for image enhancement and present a Dynamic Relative EnhAnceMent framework for Image Fusion (Dream-IF). This framework quantifies the relative dominance of each modality across different layers and leverages this information to facilitate reciprocal cross-modal enhancement. By integrating the relative dominance derived from image fusion, our approach supports not only image restoration but also a broader range of image enhancement applications. Furthermore, we employ prompt-based encoding to capture degradation-specific details, which dynamically steer the restoration process and promote coordinated enhancement in both multi-modal image fusion and image enhancement scenarios. Extensive experimental results demonstrate that Dream-IF consistently outperforms its counterparts.

Dream-IF: Dynamic Relative EnhAnceMent for Image Fusion

The rapid emergence of image synthesis models poses challenges to the generalization of AI-generated image detectors. However, existing methods often rely on model-specific features, leading to overfitting and poor generalization. In this paper, we introduce the Multi-Cue Aggregation Network (MCAN), a novel framework that integrates different yet complementary cues as input. MCAN employs a mixture-of-encoders adapter to dynamically process these cues, enabling more adaptive and robust feature representation. Our cues include the input image itself, which represents the overall content, and high-frequency components that emphasize edge details. Additionally, we introduce a Chromatic Inconsistency (CI) cue, which normalizes intensity values and captures noise information introduced during the image acquisition process in real images, making these noise patterns more distinguishable from those in AI-generated content. Unlike prior methods, MCAN employs a multi-cue aggregation strategy, leveraging spatial, frequency, and chromaticity-based cues. These cues are intrinsically more indicative of real images, enhancing cross-model generalization. Extensive experiments on the GenImage, Chameleon, and UniversalFakeDetect benchmark validate the state-of-the-art performance of MCAN. In the GenImage dataset, MCAN outperforms the best state-of-the-art method by up to 7.4\% in average ACC across eight different image generators.

Aggregating Diverse Cue Experts for AI-Generated Image Detection

Blind image quality assessment (BIQA) methods often incorporate auxiliary tasks to improve performance. However, existing approaches face limitations due to insufficient integration and a lack of flexible uncertainty estimation, leading to suboptimal performance. To address these challenges, we propose a multitasks-based Deep Evidential Fusion Network (DEFNet) for BIQA, which performs multitask optimization with the assistance of scene and distortion type classification tasks. The framework employs a trustworthy information fusion strategy at two levels: cross sub-region and local-global. The former combines diverse features and patterns across sub-regions, while the latter fuses information from fine- to coarse-grained scales and balances local and global perspectives. Moreover, DEFNet exploits advanced uncertainty estimation technique inspired by evidential learning with the help of normal-inverse gamma distribution mixture. Extensive experiments on both synthetic and authentic distortion datasets demonstrate the effectiveness and robustness of the proposed framework in comparison with state-of-the-art BIQA methods. Additional evaluation and analysis are carried out to highlight its strong generalization capability and adaptability to previously unseen scenarios.

Multitasks-based Deep Evidential Fusion Network for Blind Image Quality Assessment

Recommendation systems often rely on implicit feedback, where only positive user-item interactions can be observed.
Negative sampling is therefore crucial to provide proper negative training signals.
However, existing methods tend to mislabel potentially positive but unobserved items as negatives and lack precise control over negative sample selection. 
We aim to address these by generating controllable negative samples, rather than sampling from the existing item pool.
In this context, we propose Adaptive Diffusion-based Augmentation for Recommendation (ADAR), a novel and model-agnostic augmentation module that leverages diffusion to synthesize informative negatives.
Inspired by the progressive corruption process in diffusion, ADAR simulates a continuous transition from positive to negative, allowing for fine-grained control over sample hardness. 
To mine suitable negative samples, we theoretically identify the transition point at which a positive sample turns negative and derive a score-aware function to adaptively determine the optimal sampling timestep.
By identifying this transition point, ADAR generates challenging negatives that effectively refine the model's decision boundary.
Experiments confirm that ADAR is broadly compatible and boosts the performance of existing recommendation models substantially, including collaborative filtering and sequential recommendation, without architectural modifications.

Adaptive Diffusion-based Augmentation for Recommendation

Deep learning methods for pansharpening have advanced rapidly, yet models pretrained on data from a specific sensor often generalize poorly to data from other sensors.
Existing methods to tackle such cross-sensor degradation include retraining model or zero-shot methods, but they are highly time-consuming or even need extra training data. 
To address these challenges, our method first performs modular decomposition on deep learning-based pansharpening models, revealing a general yet critical interface where high-dimensional fused features begin mapping to the channel space of the final image. % may need revisement
A Feature Tailor is then integrated at this interface to address cross-sensor degradation at the feature level, and is trained efficiently with physics-aware unsupervised losses. Moreover, our method operates in a patch-wise manner, training on partial patches and performing parallel inference on all patches to boost efficiency.
Our method offer two key advantages: (1) $\textit{Improved Generalization Ability}$: it significantly enhance performance in cross-sensor cases. (2) $\textit{Low Generalization Cost}$: it achieves sub-second training and inference, requiring only partial test inputs and no external data, whereas prior methods often take minutes or even hours.
Experiments on the real-world data from multiple datasets demonstrate that our method achieves state-of-the-art quality and efficiency in tackling cross-sensor degradation. For example, training and inference of $512\times512\times8$ image within $\textit{0.2 seconds}$ and $4000\times4000\times8$ image within $\textit{3 seconds}$ at the fastest setting on a commonly used RTX 3090 GPU, which is over 100 times faster than zero-shot methods.

Training and Inference Within 1 Second – Tackle Cross-Sensor Degradation of Real-World Pansharpening with Efficient Residual Feature Tailoring

While Diffusion Transformers (DiTs) have achieved breakthroughs in video generation, this long sequence generation task remains constrained by the quadratic complexity of attention mechanisms, resulting in significant inference latency. Through detailed analysis of attention maps in Video Diffusion Transformer (vDiT), we identify three recurring sparsity patterns: diagonal, multi-diagonal, and vertical-stripe structures. And even 3-6\% attention heads can be skipped. Crucially, these patterns exhibit strong layer-depth and head-position correlations but show limited dependence on the input content. Leveraging these findings, we propose Sparse-vDiT, a sparsity acceleration framework for vDiT comprising: 1) Pattern-optimized sparse kernels that replace dense attention with computationally efficient implementations for each identified sparsity pattern. 2) An offline sparse diffusion search algorithm that selects the optimal sparse computation strategy per layer and head via hardware-aware cost modeling. After determining the optimal configuration, we fuse heads within the same layer that share the same attention strategy, enhancing inference efficiency. Integrated into state-of-the-art vDiT models (CogVideoX1.5, HunyuanVideo, and Wan2.1), Sparse-vDiT achieves 2.09$\times$, 2.38$\times$, and 1.67$\times$ theoretical FLOP reduction, and actual inference speedups of 1.76$\times$, 1.85$\times$, and 1.58$\times$, respectively, while maintaining high visual fidelity, with PSNR values reaching 24.13, 27.09, and 22.59. Our work demonstrates that latent structural sparsity in vDiTs can be systematically exploited for long video synthesis.

Downloads

Next from AAAI 2026

Learning Latent Imaging Biomarkers for Interpretable Microvascular Invasion Prediction in Hepatocellular Carcinoma

Similar lecture

For the motion