7 papers
ReFoCUS: Reinforcement-guided Frame Optimization for Contextual Understanding
Hosu Lee, Junho Kim, Hyunjun Kim +1
Recent progress in Large Multi-modal Models (LMMs) has enabled effective vision-language reasoning, yet the ability to video understanding remains constrained by suboptimal frame s…
Robust Grounding with MLLMs Against Occlusion and Small Objects via Language-Guided Semantic Cues
Beomchan Park, Seongho Kim, Hyunjun Kim +2
While Multimodal Large Language Models (MLLMs) have enhanced grounding capabilities in general scenes, their robustness in crowded scenes remains underexplored. Crowded scenes enta…
DIP-R1: Deep Inspection and Perception with RL Looking Through and Understanding Complex Scenes
Sungjune Park, Hyunjun Kim, Junho Kim +2
MLLMs have demonstrated significant visual understanding capabilities, yet their fine-grained visual perception in complex real-world scenarios, such as densely crowded public area…
Language-guided Learning for Object Detection Tackling Multiple Variations in Aerial Images
Sungjune Park, Hyunjun Kim, Beomchan Park +1
Despite recent advancements in computer vision research, object detection in aerial images still suffers from several challenges. One primary challenge to be mitigated is the prese…
SALOVA: Segment-Augmented Long Video Assistant for Targeted Retrieval and Routing in Long-Form Video Analysis
Junho Kim, Hyunjun Kim, Hosu Lee +1
Despite advances in Large Multi-modal Models, applying them to long and untrimmed video content remains challenging due to limitations in context length and substantial memory over…
Personalized Lip Reading: Adapting to Your Unique Lip Movements with Vision and Language
Jeong Hun Yeo, Chae Won Kim, Hyunjun Kim +4
Lip reading aims to predict spoken language by analyzing lip movements. Despite advancements in lip reading technologies, performance degrades when models are applied to unseen spe…