3 papers
cs.CV2025
Remember Me: Bridging the Long-Range Gap in LVLMs with Three-Step Inference-Only Decay Resilience Strategies
Peng Gao, Yujian Lee, Xiaofeng Zhang +2
Large Vision-Language Models (LVLMs) have achieved impressive performance across a wide range of multimodal tasks. However, they still face critical challenges in modeling long-ran…
cs.CV2025
NCL-CIR: Noise-aware Contrastive Learning for Composed Image Retrieval
Peng Gao, Yujian Lee, Zailong Chen +4
Composed Image Retrieval (CIR) seeks to find a target image using a multi-modal query, which combines an image with modification text to pinpoint the target. While recent CIR metho…
cs.CV2024
Dynamic Identity-Guided Attention Network for Visible-Infrared Person Re-identification
Peng Gao, Yujian Lee, Hui Zhang +3
Visible-infrared person re-identification (VI-ReID) aims to match people with the same identity between visible and infrared modalities. VI-ReID is a challenging task due to the la…