← Search

Fang Nan

10 accepted papers

2025

A Mixed-Language Multi-Document News Summarization Dataset and a Graphs-Based Extract-Generate Model

NAACL 2025long

Existing research on news summarization primarily focuses on single-language single-document (SLSD), single-language multi-document (SLMD) or cross-language single-document (CLSD). However, in real-world scenarios, news about an international event often involves multiple documents in different lang…

2025

Density-aware and Depth-aware Visual Representation for Zero-Shot Object Counting

ICASSP 2025accepted

Previous methods often utilize CLIP semantic classifiers with class names for zero-shot object counting. However, they ignore crucial density and depth knowledge for counting tasks. Thus, we propose a density-aware and depth-aware prompt counting model, which captures density information via learnin…

Cited by 0SourceScholar
2025

Exploring Triple Knowledge Cues for Zero-Shot Human-Object Interaction Detection

ICASSP 2025accepted

Current zero-shot human-object interaction detection methods often follow a two-phase pipeline, which uses a pre-trained detector to detect instances and then adopts CLIP to perform interaction prediction. During the second phase, they either obtain pairwise representations by directly performing Ro…

Cited by 0SourceScholar
2025

Using Depth-Enhanced Spatial Transformation for Student Gaze Target Estimation in Dual-View Classroom Images

ICASSP 2025accepted

Dual-view gaze target estimation in classroom environments has not been thoroughly explored. Existing methods lack consideration of depth information, primarily focusing on 2D image information and neglecting the latent 3D spatial context, which could lead to suboptimal transformation and cause the…

Cited by 0SourceScholar
2024

Dynamic Throwing with Robotic Material Handling Machines

IROS 2024poster

Automation of hydraulic material handling machinery is currently limited to semi-static pick-and-place cycles. Dynamic throwing motions which utilize the passive joints, can greatly improve time efficiency as well as increase the dumping workspace. In this work, we use Reinforcement Learning (RL) to…

Cited by 1SourceScholar
2024

Reinforcement Learning Control for Autonomous Hydraulic Material Handling Machines with Underactuated Tools

IROS 2024poster

The precise and safe control of heavy material handling machines presents numerous challenges due to the hard-to-model hydraulically actuated joints and the need for collision-free trajectory planning with a free-swinging end-effector tool. In this work, we propose an RL-based controller that comman…

Cited by 3SourceScholar