2 citations · 5 across the 10 of their papers we have counts for
11 papers
Linguistic Relative Policy Optimization for Video Anomaly Reasoning
Jiaxu Leng, Jiankang Zheng, Mengjingcheng Mo +4
Video anomaly detection (VAD) with multimodal large language models has shown strong potential, yet most existing methods still depend on large-scale annotations or expert-designed…
Learning to Watch: Active Video Anomaly Understanding via Interleaved Policy Optimization
Mengjingcheng Mo, Jiaxu Leng, Xinbo Gao
Video anomaly understanding (VAU) relies on sparse, context-dependent cues. However, existing passive paradigms suffer from observational aliasing, where static sampling fails to d…
SplatFont3D: Structure-Aware Text-to-3D Artistic Font Generation with Part-Level Style Control
Ji Gan, Lingxu Chen, Jiaxu Leng +1
Artistic font generation (AFG) can assist human designers in creating innovative artistic fonts. However, most previous studies primarily focus on 2D artistic fonts in flat design,…
Video-Level Language-Driven Video-Based Visible-Infrared Person Re-Identification
Shuang Li, Jiaxu Leng, Changjiang Kuang +2
Video-based Visible-Infrared Person Re-Identification (VVI-ReID) aims to match pedestrian sequences across modalities by extracting modality-invariant sequence-level features. As a…
A2Seek: Towards Reasoning-Centric Benchmark for Aerial Anomaly Understanding
Mengjingcheng Mo, Xinyang Tong, Mingpi Tan +7
While unmanned aerial vehicles (UAVs) offer wide-area, high-altitude coverage for anomaly detection, they face challenges such as dynamic viewpoints, scale variations, and complex…
PiercingEye: Dual-Space Video Violence Detection with Hyperbolic Vision-Language Guidance
Jiaxu Leng, Zhanjie Wu, Mingpi Tan +5
Existing weakly supervised video violence detection (VVD) methods primarily rely on Euclidean representation learning, which often struggles to distinguish visually similar yet sem…
EHGCN: Hierarchical Euclidean-Hyperbolic Fusion via Motion-Aware GCN for Hybrid Event Stream Perception
Haosheng Chen, Lian Luo, Mengjingcheng Mo +4
Event cameras, characterized by microsecond temporal resolution and very High Dynamic Range (HDR), emit high-speed event streams for perception tasks. In recent advancements, Graph…
Beyond Euclidean: Dual-Space Representation Learning for Weakly Supervised Video Violence Detection
Jiaxu Leng, Zhanjie Wu, Mingpi Tan +4
While numerous Video Violence Detection (VVD) methods have focused on representation learning in Euclidean space, they struggle to learn sufficiently discriminative features, leadi…
CLIP-Driven Cloth-Agnostic Feature Learning for Cloth-Changing Person Re-Identification
Shuang Li, Jiaxu Leng, Guozhang Li +3
Contrastive Language-Image Pre-Training (CLIP) has shown impressive performance in short-term Person Re-Identification (ReID) due to its ability to extract high-level semantic feat…
Shape-centered Representation Learning for Visible-Infrared Person Re-identification
Shuang Li, Jiaxu Leng, Ji Gan +2
Visible-Infrared Person Re-Identification (VI-ReID) plays a critical role in all-day surveillance systems. However, existing methods primarily focus on learning appearance features…
Ranking-based Adaptive Query Generation for DETRs in Crowded Pedestrian Detection
Feng Gao, Jiaxu Leng, Ji Gan +1
DEtection TRansformer (DETR) and its variants (DETRs) have been successfully applied to crowded pedestrian detection, which achieved promising performance. However, we find that, i…