4 papers
AnchorPrune: Relevance-Anchored Contextual Expansion for Visual Token Pruning
Kyuan Oh, Bumsoo Kim
Large vision-language models incur substantial inference costs because high-resolution inputs introduce thousands of visual tokens, many of which are redundant for a given query. E…
ImagePiece: Content-aware Re-tokenization for Efficient Image Recognition
Seungdong Yoa, Seungjun Lee, Hyeseung Cho +2
Vision Transformers (ViTs) have achieved remarkable success in various computer vision tasks. However, ViTs have a huge computational cost due to their inherent reliance on multi-h…
See It All: Contextualized Late Aggregation for 3D Dense Captioning
Minjung Kim, Hyung Suk Lim, Seung Hwan Kim +3
3D dense captioning is a task to localize objects in a 3D scene and generate descriptive sentences for each object. Recent approaches in 3D dense captioning have adopted transforme…
Bi-directional Contextual Attention for 3D Dense Captioning
Minjung Kim, Hyung Suk Lim, Soonyoung Lee +2
3D dense captioning is a task involving the localization of objects and the generation of descriptions for each object in a 3D scene. Recent approaches have attempted to incorporat…