7 papers
Depth-Guided Video Object Counting in Crowded Scenes
Yuanjing Xu, Xinyan Liu, Weidong Chen +5
Our primary objective is to advance video object counting in crowded scenes, aiming to robustly count all instances of a target category based on given text or visual prompts. Exis…
Video Individual Counting and Tracking from Moving Drones: A Benchmark and Methods
Yaowu Fan, Jia Wan, Tao Han +3
Counting and tracking dense crowds in large-scale scenes is a highly practical yet challenging problem. Existing methods mostly rely on fixed-camera datasets with limited scene cov…
Foresee-to-Ground: From Predictive Temporal Perception to Evidence-Driven Reasoning for Video Temporal Grounding
Zelin Zheng, Xinyan Liu, Ruixin Li +4
Current Video-LLM approaches for Video Temporal Grounding (VTG) typically rely on direct timestamp generation from an unstructured visual-token stream, often leading to brittle num…
Multi-view Crowd Tracking Transformer with View-Ground Interactions Under Large Real-World Scenes
Qi Zhang, Jixuan Chen, Kaiyi Zhang +3
Multi-view crowd tracking estimates each person's tracking trajectories on the ground of the scene. Recent research works mainly rely on CNNs-based multi-view crowd tracking archit…
TowerDataset: A Heterogeneous Benchmark for Transmission Corridor Segmentation with a Global-Local Fusion Framework
Xu Cui, Xinyan Liu, Chen Yang +4
Fine-grained semantic segmentation of transmission-corridor point clouds is fundamental for intelligent power-line inspection. However, current progress is limited by realistic dat…
Dense Point-to-Mask Optimization with Reinforced Point Selection for Crowd Instance Segmentation
Hongru Chen, Jiyang Huang, Jia Wan +1
Crowd instance segmentation is a crucial task with a wide range of applications, including surveillance and transportation. Currently, point labels are common in crowd datasets, wh…