SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2501.08549 · CVPR · 2025

The Devil is in Temporal Token: High Quality Video Reasoning Segmentation

Lu Zhang, Zongxin Yang, Huchuan Lu, Yunzhi Zhuge, Pingping Zhang, Sitong Gong

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. If it links a repository, it is listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Existing methods for Video Reasoning Segmentation rely heavily on a single special token to represent the object in the keyframe or the entire video, inadequately capturing spatial complexity and inter-frame motion. To overcome these challenges, we propose VRS-HQ, an end-to-end video reasoning segmentation approach that leverages Multimodal Large Language Models (MLLMs) to inject rich spatiotemporal features into hierarchical tokens. Our key innovations include a Temporal Dynamic Aggregation (TDA) and a Token-driven Keyframe Selection (TKS). Specifically, we design frame-level <SEG> and temporal-level <TAK> tokens that utilize MLLM's autoregressive learning to effectively capture both local and global information. Subsequently, we apply a similarity-based weighted fusion and frame selection strategy, then utilize SAM2 to perform keyframe segmentation and propagation. To enhance keyframe localization accuracy, the TKS filters keyframes based on SAM2's occlusion scores during inference. VRS-HQ achieves state-of-the-art performance on ReVOS, surpassing VISA by 5.9%/12.5%/9.1% in J &F scores across the three subsets. These results highlight the strong temporal reasoning and segmentation capabilities of our method. Code and model weights are available at VRS-HQ. * Corresponding Author explicit descriptive phrases like "a person skateboarding", VRS leverages the extensive world knowledge and temporal reasoning capabilities of Multimodal Large Language Models (MLLMs) to transform implicit intent-based expressions into precise object masklets.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2501.08549")
get_code_for_paper("2501.08549")
have("2501.08549")

Connect an agent — have() is free.