8 papers
DGSeg: Dynamic Gating of Semantic-Spatial Guided Predictions for Reasoning Segmentation
Ruizhe Zeng, Siyu Cao, Lu Zhang +1
Reasoning segmentation aims to predict pixel-wise masks for targets given complex language queries. Existing approaches leverage Multimodal Large Language Models (MLLMs) for vision…
Retrieving Any Relevant Moments: Benchmark and Models for Generalized Moment Retrieval
Yiming Ding, Siyu Cao, Luyuan Jiao +4
Video Moment Retrieval (VMR) aims to localize temporal segments in videos that correspond to a natural language query, but typically assumes only a single matching moment for each…
Towards Temporal Compositional Reasoning in Long-Form Sports Videos
Siyu Cao, Lu Zhang, Ruizhe Zeng +1
Sports videos are a challenging domain for multimodal understanding because they involve complex and dynamic human activities. Despite rapid progress in Multimodal Large Language M…
GA-Field: Geometry-Aware Vehicle Aerodynamic Field Prediction
Zhenhua Zheng, Lu Zhang, Junhong Zou +4
Accurate aerodynamic field prediction is crucial for vehicle drag evaluation, but the computational cost of high-fidelity CFD hinders its use in iterative design workflows. While l…
FiCoTS: Fine-to-Coarse LLM-Enhanced Hierarchical Cross-Modality Interaction for Time Series Forecasting
Yafei Lyu, Hao Zhou, Lu Zhang +2
Time series forecasting is central to data analysis and web technologies. The recent success of Large Language Models (LLMs) offers significant potential for this field, especially…
Boosting Open-Vocabulary Object Detection by Handling Background Samples
Ruizhe Zeng, Lu Zhang, Xu Yang +1
Open-vocabulary object detection is the task of accurately detecting objects from a candidate vocabulary list that includes both base and novel categories. Currently, numerous open…
Refined Pseudo labeling for Source-free Domain Adaptive Object Detection
Siqi Zhang, Lu Zhang, Zhiyong Liu
Domain adaptive object detection (DAOD) assumes that both labeled source data and unlabeled target data are available for training, but this assumption does not always hold in real…
FIT: Frequency-based Image Translation for Domain Adaptive Object Detection
Siqi Zhang, Lu Zhang, Zhiyong Liu +1
Domain adaptive object detection (DAOD) aims to adapt the detector from a labelled source domain to an unlabelled target domain. In recent years, DAOD has attracted massive attenti…