Saved in:
Bibliographic Details
Main Authors: Heo, Miran, Chen, Min-Hung, Huang, De-An, Liu, Sifei, Radhakrishnan, Subhashree, Kim, Seon Joo, Wang, Yu-Chiang Frank, Hachiuma, Ryo
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2501.08326
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908277382578176
author Heo, Miran
Chen, Min-Hung
Huang, De-An
Liu, Sifei
Radhakrishnan, Subhashree
Kim, Seon Joo
Wang, Yu-Chiang Frank
Hachiuma, Ryo
author_facet Heo, Miran
Chen, Min-Hung
Huang, De-An
Liu, Sifei
Radhakrishnan, Subhashree
Kim, Seon Joo
Wang, Yu-Chiang Frank
Hachiuma, Ryo
contents We present Omni-RGPT, a multimodal large language model designed to facilitate region-level comprehension for both images and videos. To achieve consistent region representation across spatio-temporal dimensions, we introduce Token Mark, a set of tokens highlighting the target regions within the visual feature space. These tokens are directly embedded into spatial regions using region prompts (e.g., boxes or masks) and simultaneously incorporated into the text prompt to specify the target, establishing a direct connection between visual and text tokens. To further support robust video understanding without requiring tracklets, we introduce an auxiliary task that guides Token Mark by leveraging the consistency of the tokens, enabling stable region interpretation across the video. Additionally, we introduce a large-scale region-level video instruction dataset (RegVID-300k). Omni-RGPT achieves state-of-the-art results on image and video-based commonsense reasoning benchmarks while showing strong performance in captioning and referring expression comprehension tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2501_08326
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Omni-RGPT: Unifying Image and Video Region-level Understanding via Token Marks
Heo, Miran
Chen, Min-Hung
Huang, De-An
Liu, Sifei
Radhakrishnan, Subhashree
Kim, Seon Joo
Wang, Yu-Chiang Frank
Hachiuma, Ryo
Computer Vision and Pattern Recognition
We present Omni-RGPT, a multimodal large language model designed to facilitate region-level comprehension for both images and videos. To achieve consistent region representation across spatio-temporal dimensions, we introduce Token Mark, a set of tokens highlighting the target regions within the visual feature space. These tokens are directly embedded into spatial regions using region prompts (e.g., boxes or masks) and simultaneously incorporated into the text prompt to specify the target, establishing a direct connection between visual and text tokens. To further support robust video understanding without requiring tracklets, we introduce an auxiliary task that guides Token Mark by leveraging the consistency of the tokens, enabling stable region interpretation across the video. Additionally, we introduce a large-scale region-level video instruction dataset (RegVID-300k). Omni-RGPT achieves state-of-the-art results on image and video-based commonsense reasoning benchmarks while showing strong performance in captioning and referring expression comprehension tasks.
title Omni-RGPT: Unifying Image and Video Region-level Understanding via Token Marks
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2501.08326