5 papers · 1 filter
Video Parallel Scaling: Aggregating Diverse Frame Subsets for VideoLLMs
Hyungjin Chung, Hyelin Nam, Jiyeon Kim +6
Video Large Language Models (VideoLLMs) face a critical bottleneck: increasing the number of input frames to capture fine-grained temporal detail leads to prohibitive computational…
Event-based Facial Keypoint Alignment via Cross-Modal Fusion Attention and Self-Supervised Multi-Event Representation Learning
Donghwa Kang, Junho Kim, Dongwoo Kang
Event cameras offer unique advantages for facial keypoint alignment under challenging conditions, such as low light and rapid motion, due to their high temporal resolution and robu…
CAPA: Contribution-Aware Pruning and FFN Approximation for Efficient Large Vision-Language Models
Samyak Jha, Junho Kim
Efficient inference in Large Vision-Language Models is constrained by the high cost of processing thousands of visual tokens, yet it remains unclear which tokens and computations c…
CapeLLM: Support-Free Category-Agnostic Pose Estimation with Multimodal Large Language Models
Junho Kim, Hyungjin Chung, Byung-Hoon Kim
Category-agnostic pose estimation (CAPE) has traditionally relied on support images with annotated keypoints, a process that is often cumbersome and may fail to fully capture the n…
D-Cube: Exploiting Hyper-Features of Diffusion Model for Robust Medical Classification
Minhee Jang, Juheon Son, Thanaporn Viriyasaranon +2
The integration of deep learning technologies in medical imaging aims to enhance the efficiency and accuracy of cancer diagnosis, particularly for pancreatic and breast cancers, wh…