2 citations · 7 across the 42 of their papers we have counts for
43 papers
ExPhy: A Benchmark for Explicit Physical Property Learning in Multi-Object Trajectory Forecasting
Rui Wang, Yeteng Wu, Xianlin Zhang +1
Understanding object dynamics requires not only predicting future trajectories but also examining whether a model captures the physical properties that govern motion. However, exis…
VTO: Visual Tool Orchestration for Video Anomaly Detection
Rui Wang, Yeteng Wu, Xianling Zhang +1
Video anomaly detection (VAD) is a critical yet challenging task due to the complex and diverse nature of real-world scenarios. Traditional deep learning approaches are fundamental…
Boosting Robustness for All-Weather Self-Supervised Depth Estimation in Autonomous Driving
Mengshi Qi, Xiaoyang Bi, Xianlin Zhang +1
Self-supervised depth estimation is challenging for safe autonomous driving under various adverse weather conditions due to sensor perception degradation. These challenges arise fr…
CritiqueDriveVLM: From Verifier-Guided Reinforcement Learning to Latent Thought Distillation for Autonomous Driving
Zhaohong Liu, Hao Ye, Xianlin Zhang +1
End-to-end Vision-Language Models (VLMs) show immense potential in autonomous driving. However, standard Supervised Fine-Tuning (SFT) often suffers from reasoning hallucinations an…
A DVDrive Approach for doScenes Instructed Driving Challenge
Zijian Fu, Xiangyang Chu, Mengshi Qi +3
Instruction-conditioned trajectory prediction is an emerging problem in autonomous driving, where a model predicts the future ego trajectory not only from visual scene context and…
Question-Aware Evidence Ledgers for Video Relational Reasoning
Yilin Ou, Mengshi Qi, Huadong Ma
The VRR-QA challenge evaluates visual relational reasoning in videos, where answers often depend on implicit spatial relations, event boundaries, target identity, and dialogue cont…
SGFormer++: Semantic Graph Transformer for Incremental 3D Scene Graph Generation
Mengshi Qi, Changsheng Lv, Zijian Fu +2
In this paper, we propose SGFormer++, a novel Semantic Graph Transformer for 3D scene graph generation (SGG), which aims to parse point cloud scenes into semantic structural graphs…
Leveraging Metric Depth for Relative Depth Prediction
Xiaoyang Bi, Shuaikun Liu, Zhaohong Liu +5
We present our solution to the 2025 SoccerNet Monocular Depth Estimation Competition Challenge. Predicting the relative depth in football scenarios is challenging, especially with…
A VideoMAE-v2 Approach to Zero-Shot Traffic Accident Anticipation
Siyuan Li, Xiaoyang Bi, Mengshi Qi
Traffic accident anticipation -- predicting the likelihood of an imminent collision at every frame of a dashcam video -- is safety-critical yet difficult to scale, because collecti…
Claude Code-Driving Scenario Mining for the Argoverse 2 Challenge
Wei Deng, Caoshengzhe Xue, Shuaikun Liu +3
We present our submission to the CVPR 2026 Argoverse 2 Scenario Mining Challenge. Our system uses a four-stage pipeline: (1) autonomous code generation via a Claude Code agent powe…
Global-Local Monte Carlo Tree Search in Vision-Language Models for Text-to-3D Indoor Scene Generation
Mengshi Qi, Wei Deng, Xianlin Zhang +1
Large Vision-Language Models have achieved significant reasoning performance in various tasks. However, there are few studies on text-to-3D indoor scene generation with LVLMs. The…
Active Exploring like a Pigeon: Reinforcing Spatial Reasoning via Agentic Vision-Language Models
Wei Deng, Xianlin Zhang, Mengshi Qi
Enabling Vision-Language Models (VLMs) to perform spatial reasoning remains challenging. Existing approaches treat VLMs as passive observers, which is difficult for real-world appl…
Reason-Then-Retrieve for CoVR-R with Structured Edit Prompts and Dense-Sparse Fusion
Dongqing Liu, Mengshi Qi, Hongwei Ji
CoVR-R studies reason-aware composed video retrieval: given a reference video and an edit instruction, the system must retrieve the target video that satisfies the edit. The main d…
Explainable Action Form Assessment by Exploiting Multimodal Chain-of-Thoughts Reasoning
Mengshi Qi, Yeteng Wu, Wulian Yun +2
Evaluating whether human action is standard or not and providing reasonable feedback to improve action standardization is very crucial but challenging in real-world scenarios. Howe…
RoboDriveVLM: A Novel Benchmark and Baseline towards Robust Vision-Language Models for Autonomous Driving
Dacheng Liao, Mengshi Qi, Peng Shu +4
Current Vision-Language Model (VLM)-based end-to-end autonomous driving systems often leverage large language models to generate driving decisions directly based on their understan…
Multi-Modal Scene Graph with Kolmogorov-Arnold Experts for Audio-Visual Question Answering
Zijian Fu, Changsheng Lv, Xianlin Zhang +2
In this paper, we propose a novel Multi-Modal Scene Graph with Kolmogorov-Arnold Expert Network for Audio-Visual Question Answering (SHRIKE). The task aims to mimic human reasoning…
Synergistic Tensor and Pipeline Parallelism
Mengshi Qi, Jiaxuan Peng, Jie Zhang +3
In the machine learning system, the hybrid model parallelism combining tensor parallelism (TP) and pipeline parallelism (PP) has become the dominant solution for distributed traini…
SoccerNet 2025 Challenges Results
Silvio Giancola, Anthony Cioppa, Marc Gutiérrez-Pérez +115
The SoccerNet 2025 Challenges mark the fifth annual edition of the SoccerNet open benchmarking effort, dedicated to advancing computer vision research in football video understandi…
SafeDriveRAG: Towards Safe Autonomous Driving with Knowledge Graph-based Retrieval-Augmented Generation
Hao Ye, Mengshi Qi, Zhaohong Liu +2
In this work, we study how vision-language models (VLMs) can be utilized to enhance the safety for the autonomous driving system, including perception, situational understanding, a…
DC-SAM: In-Context Segment Anything in Images and Videos via Dual Consistency
Mengshi Qi, Pengfei Zhu, Xiangtai Li +4
Given a single labeled example, in-context segmentation aims to segment corresponding objects. This setting, known as one-shot segmentation in few-shot learning, explores the segme…
Chain-of-Evidence Multimodal Reasoning for Few-shot Temporal Action Localization
Mengshi Qi, Hongwei Ji, Wulian Yun +2
Traditional temporal action localization (TAL) methods rely on large amounts of detailed annotated data, whereas few-shot TAL reduces this dependence by using only a few training s…
Global-Local Tree Search in VLMs for 3D Indoor Scene Generation
Wei Deng, Mengshi Qi, Huadong Ma
Large Vision-Language Models (VLMs), such as GPT-4, have achieved remarkable success across various fields. However, there are few studies on 3D indoor scene generation with VLMs.…
Robust Disentangled Counterfactual Learning for Physical Audiovisual Commonsense Reasoning
Mengshi Qi, Changsheng Lv, Huadong Ma
In this paper, we propose a new Robust Disentangled Counterfactual Learning (RDCL) approach for physical audiovisual commonsense reasoning. The task aims to infer objects' physics…
VLM-Assisted Continual learning for Visual Question Answering in Self-Driving
Yuxin Lin, Mengshi Qi, Liang Liu +1
In this paper, we propose a novel approach for solving the Visual Question Answering (VQA) task in autonomous driving by integrating Vision-Language Models (VLMs) with continual le…