arXiv subjects

Zhengcen Li

Publications and source records attributed to Zhengcen Li.

7 recordsLinked to original sources

arXiv2026

Video as Natural Augmentation: Towards Unified AI-Generated Image and Video Detection

AI-generated content (AIGC) is rapidly improving, creating an urgent need for detectors that generalize across data sources, deployment pipelines, and visual modalities. A strongly generalizable detector should remain robust under distributional variations. However, we identify a consistent failure mode: SOTA AI-generated image detectors often collapse when applied to frames extracted from videos. Through systematic analysis, we show that this cross-modal gap arises from both entangled synthesis-agnostic video processing shifts, including color conversion, codec compression, resizing, and blur, and model-specific fingerprints introduced by modern video generators. Motivated by these findings, we propose VINA (Video as Natural Augmentation), a unified AIGC detection framework that jointly trains on image and video data. VINA uses video frames as physically grounded natural augmentations and further introduces a cross-modal supervised contrastive objective to align image and video representations under a shared real/fake decision boundary. Extensive experiments on 14 image, video, and in-the-wild benchmarks show that VINA delivers bidirectional gains, improves robustness and transferability, and achieves state-of-the-art performance across nearly all evaluated settings without complex augmentation or dataset-specific tuning.

cs.CV↗

arXiv2026

Preserving Forgery Artifacts: AI-Generated Video Detection at Native Scale

The rapid advancement of video generation models has enabled the creation of highly realistic synthetic media, raising significant societal concerns regarding the spread of misinformation. However, current detection methods suffer from critical limitations. They rely on preprocessing operations like fixed-resolution resizing and cropping. These operations not only discard subtle, high-frequency forgery traces but also cause spatial distortion and significant information loss. Furthermore, existing methods are often trained and evaluated on outdated datasets that fail to capture the sophistication of modern generative models. To address these challenges, we introduce a comprehensive dataset and a novel detection framework. First, we curate a large-scale dataset of over 140K videos from 15 state-of-the-art open-source and commercial generators, along with Magic Videos benchmark designed specifically for evaluating ultra-realistic synthetic content. In addition, we propose a novel detection framework built on the Qwen2.5-VL Vision Transformer, which operates natively at variable spatial resolutions and temporal durations. This native-scale approach effectively preserves the high-frequency artifacts and spatiotemporal inconsistencies typically lost during conventional preprocessing. Extensive experiments demonstrate that our method achieves superior performance across multiple benchmarks, underscoring the critical importance of native-scale processing and establishing a robust new baseline for AI-generated video detection.

cs.CV↗

arXiv2026

Parameterizing Dataset Distillation via Gaussian Splatting

Dataset distillation aims to compress training data while preserving training-aware knowledge, alleviating the reliance on large-scale datasets in modern model training. Dataset parameterization provides a more efficient storage structure for dataset distillation, reducing redundancy and accommodating richer information. However, existing methods either rely on complex auxiliary modules or fail to balance representational capacity and efficiency. In this paper, we propose GSDD, a simple, novel, and effective dataset parameterization technique for Dataset Distillation based on Gaussian Splatting. We adapt CUDA-based splatting operators for parallel training in batch, enabling high-quality rendering with minimal computational and memory overhead. Gaussian primitives can effectively capture meaningful training features, allowing a sparse yet expressive representation of individual images. Leveraging both high representational capacity and efficiency, GSDD substantially increases the diversity of distilled datasets under a given storage budget, thereby improving distillation performance. Beyond achieving competitive results on multiple standard benchmarks, GSDD also delivers significant performance gains on large-scale datasets such as ImageNet-1K and on video distillation tasks. In addition, we conduct comprehensive benchmarks to evaluate the computational efficiency, memory footprint, and cross-GPU architectural stability of GSDD. Code is available on https://github.com/j-cyoung/GSDatasetDistillation

cs.CV↗

arXiv2025

Rectifying Soft-Label Entangled Bias in Long-Tailed Dataset Distillation

Dataset distillation compresses large-scale datasets into compact, highly informative synthetic data, significantly reducing storage and training costs. However, existing research primarily focuses on balanced datasets and struggles to perform under real-world long-tailed distributions. In this work, we emphasize the critical role of soft labels in long-tailed dataset distillation and uncover the underlying mechanisms contributing to performance degradation. Specifically, we derive an imbalance-aware generalization bound for model trained on distilled dataset. We then identify two primary sources of soft-label bias, which originate from the distillation model and the distilled images, through systematic perturbation of the data imbalance levels. To address this, we propose ADSA, an Adaptive Soft-label Alignment module that calibrates the entangled biases. This lightweight module integrates seamlessly into existing distillation pipelines and consistently improves performance. On ImageNet-1k-LT with EDC and IPC=50, ADSA improves tail-class accuracy by up to 11.8% and raises overall accuracy to 41.4%. Extensive experiments demonstrate that ADSA provides a robust and generalizable solution under limited label budgets and across a range of distillation techniques. Code is available at: https://github.com/j-cyoung/ADSA_DD.git.

cs.CV↗

arXiv2025

Gradient of White Matter Functional Variability via fALFF Differential Identifiability

Functional variability in both gray matter (GM) and white matter (WM) is closely associated with human brain cognitive and developmental processes, and is commonly assessed using functional connectivity (FC). However, as a correlation-based approach, FC captures the co-fluctuation between brain regions rather than the intensity of neural activity in each region. Consequently, FC provides only a partial view of functional variability, and this limitation is particularly pronounced in WM, where functional signals are weaker and more susceptible to noise. To tackle this limitation, we introduce fractional amplitude of low-frequency fluctuation (fALFF) to measure the intensity of spontaneous neural activity and analyze functional variability in WM. Specifically, we propose a novel method to quantify WM functional variability by estimating the differential identifiability of fALFF. Higher differential identifiability is observed in WM fALFF compared to FC, which indicates that fALFF is more sensitive to WM functional variability. Through fALFF differential identifiability, we evaluate the functional variabilities of both WM and GM, and find the overall functional variability pattern is similar although WM shows slightly lower variability than GM. The regional functional variabilities of WM are associated with structural connectivity, where commissural fiber regions generally exhibit higher variability than projection fiber regions. Furthermore, we discover that WM functional variability demonstrates a spatial gradient ascending from the brainstem to the cortex by hypothesis testing, which aligns well with the evolutionary expansion. The gradient of functional variability in WM provides novel insights for understanding WM function. To the best of our knowledge, this is the first attempt to investigate WM functional variability via fALFF.

q-bio.NC↗

arXiv2024

Skeleton-based Group Activity Recognition via Spatial-Temporal Panoramic Graph

Group Activity Recognition aims to understand collective activities from videos. Existing solutions primarily rely on the RGB modality, which encounters challenges such as background variations, occlusions, motion blurs, and significant computational overhead. Meanwhile, current keypoint-based methods offer a lightweight and informative representation of human motions but necessitate accurate individual annotations and specialized interaction reasoning modules. To address these limitations, we design a panoramic graph that incorporates multi-person skeletons and objects to encapsulate group activity, offering an effective alternative to RGB video. This panoramic graph enables Graph Convolutional Network (GCN) to unify intra-person, inter-person, and person-object interactive modeling through spatial-temporal graph convolutions. In practice, we develop a novel pipeline that extracts skeleton coordinates using pose estimation and tracking algorithms and employ Multi-person Panoramic GCN (MP-GCN) to predict group activities. Extensive experiments on Volleyball and NBA datasets demonstrate that the MP-GCN achieves state-of-the-art performance in both accuracy and efficiency. Notably, our method outperforms RGB-based approaches by using only estimated 2D keypoints as input. Code is available at https://github.com/mgiant/MP-GCN

cs.CV↗

arXiv2022

Two-person Graph Convolutional Network for Skeleton-based Human Interaction Recognition

Graph convolutional networks (GCNs) have been the predominant methods in skeleton-based human action recognition, including human-human interaction recognition. However, when dealing with interaction sequences, current GCN-based methods simply split the two-person skeleton into two discrete graphs and perform graph convolution separately as done for single-person action classification. Such operations ignore rich interactive information and hinder effective spatial inter-body relationship modeling. To overcome the above shortcoming, we introduce a novel unified two-person graph to represent inter-body and intra-body correlations between joints. Experiments show accuracy improvements in recognizing both interactions and individual actions when utilizing the proposed two-person graph topology. In addition, We design several graph labeling strategies to supervise the model to learn discriminant spatial-temporal interactive features. Finally, we propose a two-person graph convolutional network (2P-GCN). Our model achieves state-of-the-art results on four benchmarks of three interaction datasets: SBU, interaction subsets of NTU-RGB+D and NTU-RGB+D 120.

cs.CV↗