Singapore

Gait recognition offers a non-intrusive biometric solution by identifying individuals through their walking patterns. Although discriminative models have achieved notable success in this domain, the full potential of generative models remains largely unexplored. In this paper, we introduce CoD², a novel framework that combines the data distribution modeling capabilities of diffusion models with the semantic representation learning strengths of discriminative models to extract robust gait features. We propose a Multi-level Conditional Control strategy that integrates both high-level identity-aware semantic conditions and low-level visual details. Specifically, the high-level condition, extracted by the discriminative extractor, guides the generation of identity-consistent gait sequences, while low-level visual details, such as appearance and motion, are preserved to enhance consistency. Moreover, the generated sequences facilitate the discriminative extractor&#39;s learning, enabling it to capture more comprehensive high-level semantic features. Extensive experiments on four datasets (SUSTech1K, CCPG, GREW, and Gait3D) demonstrate that CoD² achieves state-of-the-art performance and can be seamlessly integrated with existing discriminative methods, yielding consistent improvements.

AAAI 2026

Gait Recognition via Collaborating Discriminative and Generative Diffusion Models

gesture & pose; cv: video understanding & activity analysis; cv: image and video retrieval

cv: biometrics

face

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.

Gait recognition offers a non-intrusive biometric solution by identifying individuals through their walking patterns. Although discriminative models have achieved notable success in this domain, the full potential of generative models remains largely unexplored. In this paper, we introduce CoD², a novel framework that combines the data distribution modeling capabilities of diffusion models with the semantic representation learning strengths of discriminative models to extract robust gait features. We propose a Multi-level Conditional Control strategy that integrates both high-level identity-aware semantic conditions and low-level visual details. Specifically, the high-level condition, extracted by the discriminative extractor, guides the generation of identity-consistent gait sequences, while low-level visual details, such as appearance and motion, are preserved to enhance consistency. Moreover, the generated sequences facilitate the discriminative extractor's learning, enabling it to capture more comprehensive high-level semantic features. Extensive experiments on four datasets (SUSTech1K, CCPG, GREW, and Gait3D) demonstrate that CoD² achieves state-of-the-art performance and can be seamlessly integrated with existing discriminative methods, yielding consistent improvements.

poster

Spatiotemporal forecasting often relies on computationally intensive models to capture complex dynamics. Knowledge distillation (KD) has emerged as a key technique for creating lightweight student models, with recent advances like frequency-aware KD successfully preserving spectral properties (i.e., high-frequency details and low-frequency trends). However, these methods are fundamentally constrained by operating on pixel-level signals, leaving them blind to the rich semantic and causal context behind the visual patterns. To overcome this limitation, we introduce \textbf{S$^2$-KD}, a novel framework that unifies \textbf{S}emantic priors with \textbf{S}pectral representations for distillation. Our approach begins by training a privileged, multimodal \textbf{teacher} model. This teacher leverages textual narratives from a Large Multimodal Model (LMM) to reason about the underlying causes of events, while its architecture simultaneously decouples spectral components in its latent space. The core of our framework is a new distillation objective that transfers this unified semantic-spectral knowledge into a lightweight, \textbf{vision-only student}. Consequently, the student learns to make predictions that are not only spectrally accurate but also semantically coherent, without requiring any textual input or architectural overhead at inference. Extensive experiments on benchmarks like WeatherBench and TaxiBJ+ show that S$^2$-KD significantly boosts the performance of simple student models, enabling them to outperform state-of-the-art methods, particularly in long-horizon and complex non-stationary scenarios.

S^2-KD: Semantic-Spectral Knowledge Distillation Spatiotemporal Forecasting

Recent advances in transformer-based lightweight object tracking have established new standards across benchmarks, leveraging the global receptive field and powerful feature extraction capabilities of attention mechanisms. Despite these achievements, existing methods universally employ sparse sampling during training—utilizing only one template and one search image per sequence—which fails to comprehensively explore spatiotemporal information in videos. This limitation constrains performance and causes the gap between lightweight and high-performance trackers. To bridge this divide while maintaining real-time efficiency, we propose STDTrack, a framework that pioneers the integration of reliable spatiotemporal dependencies into lightweight trackers. Our approach implements dense video sampling to maximize spatiotemporal information utilization. We introduce a temporally propagating spatiotemporal token to guide per-frame feature extraction. To ensure comprehensive target state representation, we design the Multi-frame Information Fusion Module (MFIFM), which augments current dependencies using historical context. The MFIFM operates on features stored in our constructed Spatiotemporal Token Maintainer (STM), where a quality-based update mechanism ensures information reliability. Considering the scale variation among tracking targets, we develop a multi-scale prediction head to dynamically adapt to objects of different sizes. Extensive experiments demonstrate state-of-the-art results across six benchmarks. Notably, on GOT-10k, STDTrack rivals certain high-performance non-real-time trackers (e.g., MixFormer) while operating at 192 FPS (GPU) and 41 FPS (CPU).

Exploring Reliable Spatiotemporal Dependencies for Efficient Visual Tracking

Data augmentation is an intuitive solution to increase the diversity of training instances in the machine learning community. Mixup is acknowledged as an effective and efficient mix-based data augmentation method, following a linear alignment assumption that the linear interpolations of features align the corresponding linear interpolations of labels. Unfortunately, this assumption can be violated in many complex scenarios, resulting in augmented instances with noisy labels, especially for regression problems. To solve this problem, we propose an easy-to-implement mixup method, namely DEnosing MIXUP (DE-mixup), which iteratively corrects the noisy response targets by leveraging an auxiliary noise estimation task with mixup deep features. Additionally, we suggest an efficient optimization method with alternating direction method of multipliers. We compare DE-mixup with the existing mixup variants and other prevalent data augmentation methods across benchmark regression datasets. Empirical results indicate the effectiveness of DE-mixup under the in-distribution and out-of-distribution cases.

Denoising Mixup for Regression

Recent diffusion-based Single-image 3D portrait generation methods typically employ 2D diffusion models to provide multi-view knowledge, which is then distilled into 3D representations. However, these methods usually struggle to produce high-fidelity 3D models, frequently yielding excessively blurred textures. We attribute this issue to the insufficient consideration of cross-view consistency during the diffusion process, resulting in significant disparities between different views and ultimately leading to blurred 3D representations. In this paper, we address this issue by comprehensively exploiting multi-view priors in both the conditioning and diffusion procedures to produce consistent, detail-rich portraits. From the conditioning standpoint, we propose a Hybrid Priors Diffusion model, which explicitly and implicitly incorporates multi-view priors as conditions to enhance the status consistency of the generated multi-view portraits. From the diffusion perspective, considering the significant impact of the diffusion noise distribution on detailed texture generation, we propose a Multi-View Noise Resampling Strategy integrated within the optimization process leveraging cross-view priors to enhance representation consistency. Extensive experiments show that our method produces 3D portraits with accurate geometry and rich details from a single image.

Towards High-Fidelity 3D Portrait Generation with Rich Details by Cross-View Prior-Aware Diffusion

Intelligent fault-tolerant (FT) computing has recently demonstrated significant advantages in predicting and diagnosing faults proactively, thereby ensuring reliable service delivery. However, due to the heterogeneity of fault knowledge, dynamic workloads, and limited data support, existing deep learning-based FT algorithms face challenges in fault detection quality and training efficiency. This is primarily because their homogenization of fault knowledge perception difficuties to fully capture diverse and complex fault patterns. To address these challenges, we propose FT-MoE, a sustainable-learning fault-tolerant computing framework based on a dual-path architecture for high-accuracy fault detection and classification. This model employs a mixture-of-experts (MoE) architecture, enabling different parameters to learn distinct fault knowledge. Additionally, we adopt a two-stage learning scheme that combines comprehensive offline training with continual online tuning, allowing the model to adaptively optimize its parameters in response to evolving real-time workloads. To facilitate realistic evaluation, we construct a new fault detection and classification dataset for edge networks, comprising 10,000 intervals with fine-grained resource features, surpassing existing datasets in both scale and granularity. Finally, we conduct extensive experiments on the FT benchmark to verify the effectiveness of FT-MoE. Results demonstrate that our model outperforms state-of-the-art methods. The code will be made available upon publication.

FT-MoE: Sustainable-learning Mixture of Experts for Fault-Tolerant Computing

This paper introduces Gaussian Spatial Transport (GST), a novel framework that leverages Gaussian splatting to facilitate transport from the probability measure in the image coordinate space to the annotation map. We propose a Gaussian splatting-based method to estimate pixel-annotation correspondence, which is then used to compute a transport plan derived from Bayesian probability. To integrate the resulting transport plan into standard network optimization in typical computer vision tasks, we derive a loss function that measures discrepancy after transport. Extensive experiments on representative computer vision tasks, including crowd counting and landmark detection, validate the effectiveness of our approach. Compared to conventional optimal transport schemes, GST eliminates iterative transport plan computation during training, significantly improving efficiency. The code will be released upon acceptance.

2D Gaussians Spatial Transport for Point-supervised Density Regression

The rise of AI-generated image tools has made localized forgeries increasingly realistic, posing challenges for visual content integrity.
Although recent efforts have explored localized AIGC detection, existing datasets predominantly focus on object-level forgeries while overlooking broader scene edits in regions such as sky or ground.
To address these limitations, we introduce \textbf{BR-Gen}, a large-scale dataset of 150,000 locally forged images with diverse scene-aware annotations, which are based on semantic calibration to ensure high-quality samples. 
BR-Gen is constructed through a fully automated ``Perception-Creation-Evaluation'' pipeline to ensure semantic coherence and visual realism.
In addition, we further propose \textbf{NFA-ViT}, a Noise-guided Forgery Amplification Vision Transformer that enhances the detection of localized forgeries by amplifying subtle forgery-related features across the entire image. 
NFA-ViT mines heterogeneous regions in images, \emph{i.e.}, potential edited areas, by noise fingerprints. Subsequently, attention mechanism is introduced to compel the interaction between normal and abnormal features, thereby propagating the traces throughout the entire image, allowing subtle forgeries to influence a broader context and improving overall detection robustness.
Extensive experiments demonstrate that BR-Gen constructs entirely new scenarios that are not covered by existing methods.
Take a step further, NFA-ViT outperforms existing methods on BR-Gen and generalizes well across current benchmarks. Our code are available at \url{https://github.com/clpbc/BR-Gen}.

Zooming In on Fakes: A Novel Dataset for Localized AI-Generated Image Detection with Forgery Amplification Approach

Visual neural decoding is an important research topic at the intersection of cognitive neuroscience and machine learning. While recent progress has been made in EEG-based neural decoding, reconstructing dynamic visual content remains challenging. In the field of EEG decoding, current models either utilize pre-trained encoders for feature extraction or employ graph neural networks to represent the spatio-temporal information embedding, resulting in poor model representation and high complexity. We propose EVOKE -- an innovative framework for zero-shot decoding of high-fidelity videos from EEG signals. EVOKE employs Implicit Neural Representations to perform complete spatial modeling of EEG and continuously decouples information in the EEG-INR perceptual space. Additionally, we construct a Hierarchical-aware Attention Module (HAM) to decode EEG from three feature anchors: visual, semantic, motion, and progressively control task inference. The Motion Attention Flow (MAF) we developed overcomes the limitations of capturing motion features in dynamic stimuli, creating a more robust representation that enhances reconstruction consistency. Comprehensive experiments prove that SOTA performance of EVOKE (0.353 SSIM, 0.715 CLIP-pcc). We provide an effective method for converting brain activity into rich visual experiences and set a new benchmark for brain multimodal generation.

EVOKE: Efficient and High-Fidelity EEG-to-Video Reconstruction via Decoupling Implicit Neural Representation

Multi-annotator learning (MAL) aims to model annotator-specific labeling patterns. However, existing methods face a critical challenge: they simply skip updating annotator-specific model parameters when encountering missing labels—a common scenario in real-world crowdsourced datasets where each annotator labels only small subsets of samples. This leads to inefficient data utilization and overfitting risks. To this end, we propose a novel similarity-weighted semi-supervised learning framework (SimLabel) that leverages inter-annotator similarities to generate weighted soft labels for missing annotations, enabling the utilization of unannotated samples rather than skipping them entirely. We further introduce a confidence-based iterative refinement mechanism that combines maximum probability with entropy-based uncertainty to prioritize predicted high-quality pseudo-labels to impute missing labels, jointly enhancing similarity estimation and model performance over time. For evaluation, we contribute a new multimodal multi-annotator dataset, AMER2, with high and more variable missing rates, reflecting real-world annotation sparsity and enabling evaluation across different sparsity levels. Extensive experiments validate the effectiveness of our method.

SimLabel: Similarity-Weighted Semi-supervision for Multi-annotator Learning with Missing Labels

Modern image super-resolution (SR) networks match photographic detail but remain impractical for memory- and latency-constrained devices. Post-training quantization (PTQ) compresses such models without full retraining; yet standard PTQ treats weight and activation quantizers independently and therefore ignores their coupled behaviour in the frequency domain. A Fourier analysis reveals a consistent asymmetry: quantizing weights blurs colour and shape at low frequencies, while quantizing activations erodes edges and textures at high frequencies. Because these distortions interact multiplicatively rather than add linearly, separate optimisation leaves considerable perceptual quality unrealised. We introduce HarmoQ, a harmonised PTQ framework that accounts for this coupling. HarmoQ first applies a closed-form spectral residual projection, editing weights once to cancel high-frequency artefacts caused by activation clipping. It then enforces an equal-error scaling law that analytically balances mean-squared error between weights and activations, followed by an adaptive boundary refinement routine that fine-tunes clipping thresholds while periodically restoring that balance.

Downloads

Next from AAAI 2026

S^2-KD: Semantic-Spectral Knowledge Distillation Spatiotemporal Forecasting

Similar lecture

Language-Guided and Motion-Aware Gait Representation for Generalizable Recognition

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from AAAI 2026

S^2-KD: Semantic-Spectral Knowledge Distillation Spatiotemporal Forecasting

Similar lecture

Language-Guided and Motion-Aware Gait Representation for Generalizable Recognition

Downloads