conftrace_

dynamic image

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

video understanding (2) temporal prompt (1) rank pooling (1) spatio-temporal interaction (1) rotary position embedding (1) visual prompt (1) multimodal large language model (1) convolutional neural network (1) video analysis (1) temporal information (1)

Papers

DynImg: Key Frames with Visual Prompts are Good Representation for Multi-Modal Video Understanding ICCV 2025 Dynamic Image Networks for Action Recognition CVPR 2016