8 papers
YOLO-Master: MOE-Accelerated with Specialized Transformers for Enhanced Real-time Detection
Xu Lin, Jinlong Peng, Zhenye Gan +2
Existing Real-Time Object Detection (RTOD) methods commonly adopt YOLO-like architectures for their favorable trade-off between accuracy and speed. However, these models rely on st…
Regularizing Subspace Redundancy of Low-Rank Adaptation
Yue Zhu, Haiwen Diao, Shang Gao +8
Low-Rank Adaptation (LoRA) and its variants have delivered strong capability in Parameter-Efficient Transfer Learning (PETL) by minimizing trainable parameters and benefiting from…
Exploring Dynamic Transformer for Efficient Object Tracking
Jiawen Zhu, Xin Chen, Haiwen Diao +6
The speed-precision trade-off is a critical problem for visual object tracking which usually requires low latency and deployment on constrained resources. Existing solutions for ef…
Two-stream Beats One-stream: Asymmetric Siamese Network for Efficient Visual Tracking
Jiawen Zhu, Huayi Tang, Xin Chen +3
Efficient tracking has garnered attention for its ability to operate on resource-constrained platforms for real-world deployment beyond desktop GPUs. Current efficient trackers mai…
Streaming Video Understanding and Multi-round Interaction with Memory-enhanced Knowledge
Haomiao Xiong, Zongxin Yang, Jiazuo Yu +4
Recent advances in Large Language Models (LLMs) have enabled the development of Video-LLMs, advancing multimodal learning by bridging video data with language tasks. However, curre…
3UR-LLM: An End-to-End Multimodal Large Language Model for 3D Scene Understanding
Haomiao Xiong, Yunzhi Zhuge, Jiawen Zhu +2
Multi-modal Large Language Models (MLLMs) exhibit impressive capabilities in 2D tasks, yet encounter challenges in discerning the spatial positions, interrelations, and causal logi…