paper-with-me

홈 › Papers

Improving Streaming Video Segmentation with Early and Mid-Level Visual Processing

2014-02-14 · Subarna Tripathi, Youngbae Hwang, Serge Belongie, Truong Nguyen

Despite recent advances in video segmentation, many opportunities remain to improve it using a variety of low and mid-level visual cues. We propose improvements to the leading streaming graph-based hierarchical video segmentation (streamGBH) method based on early and mid level visual processing. The extensive experimental analysis of our approach validates the improvement of hierarchical supervoxel representation by incorporating motion and color with effective filtering. We also pose and illuminate some open questions towards intermediate level video analysis as further extension to streamGBH. We exploit the supervoxels as an initialization towards estimation of dominant affine motion regions, followed by merging of such motion regions in order to hierarchically segment a video in a novel motion-segmentation framework which aims at subsequent applications such as foreground recognition.

📄 PDF Abstract BibTeX arXiv:1402.3557

Code (0)

등록된 구현이 없습니다.

Tasks

Motion SegmentationSegmentationVideo SegmentationVideo Semantic Segmentation

Similar Papers 제목 키워드 기반

ObjectStream: Latent Objects as Memory Anchors for Streaming Video Understanding

2026-07-30 · Mingkang Dong, Muxin Pu, Jie Li, Bohan Guo 외 arxiv

Streaming video understanding requires models to continuously retain useful visual evidence before future questions are known. Existing approaches primarily manage the growing visual context according to token importance…

VideoScaffold: Elastic-Scale Visual Hierarchies for Streaming Video Understanding in MLLMs

2025-12-23 · Naishan Zheng, Jie Huang, Qingpei Guo, Feng Zhao arxiv

Understanding long videos with multimodal large language models (MLLMs) remains challenging due to the heavy redundancy across frames and the need for temporally coherent representations. Existing static strategies, such…

Event Segmentation

SAM2Dual: Training-Free, Dual Memory for Long-Term Video Object Segmentation

2026-08-19 · JeongRae Kim, Changwon Lim arxiv

Long-term video object segmentation (VOS) remains challenging due to error accumulation under extended occlusions, re-appearance, and scene changes. Although SAM2 provides strong zero-shot performance, its streaming memo…

Video Object Segmentation

FlowNar: Scalable Streaming Narration for Long-Form Videos

2026-05-30 · Zeyun Zhong, Manuel Martin, Chengzhi Wu, David Schneider 외 arxiv

Recent Large Multimodal Models (LMMs), primarily designed for offline settings, are ill-suited for the dynamic requirements of streaming video. While recent online adaptations improve real-time processing, they still fac…

Morphe: High-Fidelity Generative Video Streaming with Vision Foundation Model

2026-02-03 · Tianyi Gong, Zijian Cao, Zixing Zhang, Jiangkai Wu 외 arxiv

Video streaming is a fundamental Internet service, while the quality still cannot be guaranteed especially in poor network conditions such as bandwidth-constrained and remote areas. Existing works mainly work towards two…