5 papers
A Unified Reasoning Framework for Holistic Zero-Shot Video Anomaly Analysis
Dongheng Lin, Mengxue Qu, Kunyang Han +3
Most video-anomaly research stops at frame-wise detection, offering little insight into why an event is abnormal, typically outputting only frame-wise anomaly scores without spatia…
3DResT: A Strong Baseline for Semi-Supervised 3D Referring Expression Segmentation
Wenxin Chen, Mengxue Qu, Weitai Kang +3
3D Referring Expression Segmentation (3D-RES) typically requires extensive instance-level annotations, which are time-consuming and costly. Semi-supervised learning (SSL) mitigates…
ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model
Kunyang Han, Yibo Hu, Mengxue Qu +3
Advances in CLIP and large multimodal models (LMMs) have enabled open-vocabulary and free-text segmentation, yet existing models still require predefined category prompts, limiting…
Intent3D: 3D Object Detection in RGB-D Scans Based on Human Intention
Weitai Kang, Mengxue Qu, Jyoti Kini +3
In real-life scenarios, humans seek out objects in the 3D world to fulfill their daily needs or intentions. This inspires us to introduce 3D intention grounding, a new task in 3D o…
ChatVTG: Video Temporal Grounding via Chat with Video Dialogue Large Language Models
Mengxue Qu, Xiaodong Chen, Wu Liu +2
Video Temporal Grounding (VTG) aims to ground specific segments within an untrimmed video corresponding to the given natural language query. Existing VTG methods largely depend on…