4 accepted papers
Video Large Language Models (VideoLLMs), which adopt large language models for video understanding, have been demonstrated for single-shot videos. However, they usually struggle in multi-shot videos with frequent shot changes, varying camera angles, etc., which makes VideoLLMs hardly answer question
3D vision-language (3D-VL) reasoning, connecting natural language with 3D physical world, represents a milestone in advancing spatial intelligence. While transformer-based methods dominate 3D-VL research, their quadratic complexity and simplistic positional embedding mechanisms severely limits effec…
"simplify the pipeline by discarding previous matching blocks, relying only pure self-attention for matching result in using only an MLP can directly regress the coordinates from the support keypoint. Category-Agnostic Pose Estimation (CAPE) aims to localize keypoints on an object of any category gi…
Automatic and interactive matting largely improve image matting by respectively alleviating the need for auxiliary input and enabling object selection. Due to different settings on whether prompts exist they either suffer from weakness in instance completeness or region details. Also when dealing wi…