collaborators

5 papers

cs.CV2026

Knowledge-Refined Dual Context-Aware Network for Partially Relevant Video Retrieval

Junkai Yang, Qirui Wang, Yaoqing Jin +3

Retrieving partially relevant segments from untrimmed videos remains difficult due to two persistent challenges: the mismatch in information density between text and video segments…

cs.RO2025

A Human-Oriented Cooperative Driving Approach: Integrating Driving Intention, State, and Conflict

Qin Wang, Shanmin Pang, Jianwu Fang +4

Human-vehicle cooperative driving serves as a vital bridge to fully autonomous driving by improving driving flexibility and gradually building driver trust and acceptance of autono…

cs.CV2025

Redundant Queries in DETR-Based 3D Detection Methods: Unnecessary and Prunable

Lizhen Xu, Zehao Wu, Wenzhao Qiu +4

Query-based models are extensively used in 3D object detection tasks, with a wide range of pre-trained checkpoints readily available online. However, despite their popularity, thes…

cs.CV2025

Causal-Entity Reflected Egocentric Traffic Accident Video Synthesis

Lei-lei Li, Jianwu Fang, Junbin Xiao +5

Egocentricly comprehending the causes and effects of car accidents is crucial for the safety of self-driving cars, and synthesizing causal-entity reflected accident videos can faci…

cs.CV2025

Accelerate 3D Object Detection Models via Zero-Shot Attention Key Pruning

Lizhen Xu, Xiuxiu Bai, Xiaojun Jia +2

Query-based methods with dense features have demonstrated remarkable success in 3D object detection tasks. However, the computational demands of these models, particularly with lar…