Showing 2026Show all
2 papers · 1 filter
cs.CV2026
Prompting-MammAlps: Fine-Grained Text-to-Video Retrieval for Camera-Trap Data
Valentin Gabeff, Baptiste Maquignaz, Jennifer Shan +5
Automatically retrieving videos from large camera-trap datasets remains challenging. Text-to-Video retrieval (TVR) methods based on large video-language models (VLMs) have potentia…
cs.CV2026
AdaptToken: Entropy-based Adaptive Token Selection for MLLM Long Video Understanding
Haozhe Qi, Kevin Qu, Mahdi Rad +3
Long video understanding remains challenging for Multi-modal Large Language Models (MLLMs) due to high memory costs and context-length limits. Prior approaches mitigate this by sco…