collaborators

5 papers

cs.CV2025

WeDetect: Fast Open-Vocabulary Object Detection as Retrieval

Shenghao Fu, Yukun Su, Fengyun Rao +3

Open-vocabulary object detection aims to detect arbitrary classes via text prompts. Methods without cross-modal fusion layers (non-fusion) offer faster inference by treating recogn…

cs.CV2025

LOVE-R1: Advancing Long Video Understanding with an Adaptive Zoom-in Mechanism via Multi-Step Reasoning

Shenghao Fu, Qize Yang, Yuan-Ming Li +3

Long video understanding is still challenging for recent Large Video-Language Models (LVLMs) due to the conflict between long-form temporal understanding and detailed spatial perce…

cs.CV2025

Reinforcing Video Reasoning with Focused Thinking

Jisheng Dang, Jingze Wu, Teng Wang +6

Recent advancements in reinforcement learning, particularly through Group Relative Policy Optimization (GRPO), have significantly improved multimodal large language models for comp…

cs.CV2025

A Hierarchical Semantic Distillation Framework for Open-Vocabulary Object Detection

Shenghao Fu, Junkai Yan, Qize Yang +3

Open-vocabulary object detection (OVD) aims to detect objects beyond the training annotations, where detectors are usually aligned to a pre-trained vision-language model, eg, CLIP,…

cs.CV2024

Frozen-DETR: Enhancing DETR with Image Understanding from Frozen Foundation Models

Shenghao Fu, Junkai Yan, Qize Yang +3

Recent vision foundation models can extract universal representations and show impressive abilities in various tasks. However, their application on object detection is largely over…