228 citations · 459 across the 33 of their papers we have counts for
34 papers
Dynamic-TD3: A Novel Algorithm for UAV Path Planning with Dynamic Obstacle Trajectory Prediction
Wentao Chen, Jingtang Chen, Mingjian Fu +4
Deep reinforcement learning (DRL) finds extensive application in autonomous drone navigation within complex, high-risk environments. However, its practical deployment faces a safet…
PanopticQuery: Unified Query-Time Reasoning for 4D Scenes
Ruilin Tang, Yang Zhou, Zhong Ye +3
Understanding dynamic 4D environments through natural language queries requires not only accurate scene reconstruction but also robust semantic grounding across space, time, and vi…
Adapting SAM to Nuclei Instance Segmentation and Classification via Cooperative Fine-Grained Refinement
Jingze Su, Tianle Zhu, Jiaxin Cai +6
Nuclei instance segmentation is critical in computational pathology for cancer diagnosis and prognosis. Recently, the Segment Anything Model has demonstrated exceptional performanc…
A PDE-constrained Optimization Approach to Optimal Trajectory Planning under Uncertainty via Reflected Schrödinger Bridges
Dante Kalise, Wenxin Liu
A computational PDE-constrained optimization approach is proposed for optimal trajectory planning under uncertainty by means of an associated Schroedinger Bridge Problem (SBP). The…
Stable Score Distillation
Haiming Zhu, Yangyang Xu, Chenshu Xu +5
Text-guided image and 3D editing have advanced with diffusion-based models, yet methods like Delta Denoising Score often struggle with stability, spatial control, and editing stren…
URWKV: Unified RWKV Model with Multi-state Perspective for Low-light Image Restoration
Rui Xu, Yuzhen Niu, Yuezhou Li +3
Existing low-light image enhancement (LLIE) and joint LLIE and deblurring (LLIE-deblur) models have made strides in addressing predefined degradations, yet they are often constrain…
Revisiting Network Perturbation for Semi-Supervised Semantic Segmentation
Sien Li, Tao Wang, Ruizhe Hu +1
In semi-supervised semantic segmentation (SSS), weak-to-strong consistency regularization techniques are widely utilized in recent works, typically combined with input-level and fe…
Distractor-aware Event-based Tracking
Yingkai Fu, Meng Li, Wenxi Liu +5
Event cameras, or dynamic vision sensors, have recently achieved success from fundamental vision tasks to high-level vision researches. Due to its ability to asynchronously capture…
Memory-Constrained Semantic Segmentation for Ultra-High Resolution UAV Imagery
Qi Li, Jiaxin Cai, Yuanlong Yu +3
Amidst the swift advancements in photography and sensor technologies, high-definition cameras have become commonplace in the deployment of Unmanned Aerial Vehicles (UAVs) for diver…
Frame-Event Alignment and Fusion Network for High Frame Rate Tracking
Jiqing Zhang, Yuanchen Wang, Wenxi Liu +4
Most existing RGB-based trackers target low frame rate benchmarks of around 30 frames per second. This setting restricts the tracker's functionality in the real world, especially f…
Single-View View Synthesis with Self-Rectified Pseudo-Stereo
Yang Zhou, Hanjie Wu, Wenxi Liu +3
Synthesizing novel views from a single view image is a highly ill-posed problem. We discover an effective solution to reduce the learning ambiguity by expanding the single-view vie…
Monocular BEV Perception of Road Scenes via Front-to-Top View Projection
Wenxi Liu, Qi Li, Weixiang Yang +5
HD map reconstruction is crucial for autonomous driving. LiDAR-based methods are limited due to expensive sensors and time-consuming computation. Camera-based methods usually need…
Monocular Camera-based Complex Obstacle Avoidance via Efficient Deep Reinforcement Learning
Jianchuan Ding, Lingping Gao, Wenxi Liu +5
Deep reinforcement learning has achieved great success in laser-based collision avoidance works because the laser can sense accurate depth information without too much redundant da…
Glance to Count: Learning to Rank with Anchors for Weakly-supervised Crowd Counting
Zheng Xiong, Liangyu Chai, Wenxi Liu +3
Crowd image is arguably one of the most laborious data to annotate. In this paper, we devote to reduce the massive demand of densely labeled crowd data, and propose a novel weakly-…
End-to-End Trajectory Distribution Prediction Based on Occupancy Grid Maps
Ke Guo, Wenxi Liu, Jia Pan
In this paper, we aim to forecast a future trajectory distribution of a moving agent in the real world, given the social scene images and historical trajectories. Yet, it is a chal…
Semi-Supervised Domain Generalization with Evolving Intermediate Domain
Luojun Lin, Han Xie, Zhishu Sun +4
Domain Generalization (DG) aims to generalize a model trained on multiple source domains to an unseen target domain. The source domains always require precise annotations, which ca…
Ultra-high Resolution Image Segmentation via Locality-aware Context Fusion and Alternating Local Enhancement
Wenxi Liu, Qi Li, Xindai Lin +3
Ultra-high resolution image segmentation has raised increasing interests in recent years due to its realistic applications. In this paper, we innovate the widely used high-resoluti…
A Vision-based Irregular Obstacle Avoidance Framework via Deep Reinforcement Learning
Lingping Gao, Jianchuan Ding, Wenxi Liu +4
Deep reinforcement learning has achieved great success in laser-based collision avoidance work because the laser can sense accurate depth information without too much redundant dat…
Crowd-Driven Mapping, Localization and Planning
Tingxiang Fan, Dawei Wang, Wenxi Liu +1
Navigation in dense crowds is a well-known open problem in robotics with many challenges in mapping, localization, and planning. Traditional solutions consider dense pedestrians as…
An Intelligent CNN-VAE Text Representation Technology Based on Text Semantics for Comprehensive Big Data
Genggeng Liu, Canyang Guo, Lin Xie +3
In the era of big data, a large number of text data generated by the Internet has given birth to a variety of text representation methods. In natural language processing (NLP), tex…
HDR-GAN: HDR Image Reconstruction from Multi-Exposed LDR Images with Large Motions
Yuzhen Niu, Jianbin Wu, Wenxi Liu +2
Synthesizing high dynamic range (HDR) images from multiple low-dynamic range (LDR) exposures in dynamic scenes is challenging. There are two major problems caused by the large moti…
Recurrent Distillation based Crowd Counting
Yue Gu, Wenxi Liu
In recent years, with the progress of deep learning technologies, crowd counting has been rapidly developed. In this work, we propose a simple yet effective crowd counting framewor…
Over-crowdedness Alert! Forecasting the Future Crowd Distribution
Yuzhen Niu, Weifeng Shi, Wenxi Liu +3
In recent years, vision-based crowd analysis has been studied extensively due to its practical applications in real world. In this paper, we formulate a novel crowd analysis proble…
Learning Resilient Behaviors for Navigation Under Uncertainty
Tingxiang Fan, Pinxin Long, Wenxi Liu +3
Deep reinforcement learning has great potential to acquire complex, adaptive behaviors for autonomous agents automatically. However, the underlying neural network polices have not…