Video Anomaly Detection with Motion and Appearance Guided Patch Diffusion Model

Hang Zhou, Jiale Cai, Yuteng Ye, Yonghui Feng, Chenxing Gao, Junqing Yu, Zikai Song, Wei Yang

Project

• We propose a patch-based diffusion model integrated with motion and appearance conditions to capture fine-grained local information while simultaneously addressing anomalies in both appearance and motion, thereby enhancing anomaly detection accuracy.

Coupled Mamba: Enhanced Multi-modal Fusion with Coupled State Space Model

Wenbing Li, Hang Zhou, Junqing Yu, Zikai Song, Wei Yang

• We present the Coupled SSM model, which enhances multi-modal fusion by coupling state chains while maintaining intra-modality independence, achieving superior performance and efficiency.

Dynamic feature pruning and consolidation for occluded person re-identification

YuTeng Ye, Hang Zhou, Jiale Cai, Chenxing Gao, Youjia Zhang, Junle Wang, Qiang Hu, Junqing Yu, Wei Yang

Project

• We propose a Feature Pruning and Consolidation (FPC) framework to circumvent explicit human structure parse, which consists of a sparse encoder, a global and local feature ranking module, and a feature consolidation decoder.

Progressive Text-to-Image Diffusion with Soft Latent Direction

YuTeng Ye, Jiale Cai, Hang Zhou, Guanwen Li, Youjia Zhang, Zikai Song, Chenxing Gao, Junqing Yu, Wei Yang

Project

• We propose to harness the capabilities of a Large Language Model (LLM) to decompose text descriptions into coherent directives adhering to stringent formats and progressively generate the target image.

Attacking Transformers with Feature Diversity Adversarial Perturbation

Chenxing Gao, Hang Zhou, Junqing Yu, YuTeng Ye, Jiale Cai, Junle Wang, Wei Yang

• We present a label-free white-box attack approach for ViT-based models that exhibits strong transferability to various black-box models by accelerating the feature collapse.

Dual memory units with uncertainty regulation for weakly supervised video anomaly detection

Hang Zhou, Junqing Yu, Wei Yang

Project

• We propose an Uncertainty Regulated Dual Memory Units (UR-DMU) model to learn both the representations of normal data and discriminative features of abnormal data.