Sekai: Incremental Event Memory for Generalized Reasoning Video Segmentation
cs.CV
Submitted: 2026-11-04
Updated: 2026-11-04
Code: https://github.com/zenastangbi/Sekai
Project page: https://danielshkao.github.io/cot-rvs.html
Terminology
Sources
- Qwen3-VL Technical Report
- SAM 3: Segment Anything with Concepts
- VideoSEG-O3: A Multi-turn Reinforcement Learning Framework for Reasoning Video Object Segmentation
- Streaming Video Question-Answering with In-context Video KV-Cache Retrieval
- The Devil is in Temporal Token: High Quality Video Reasoning Segmentation
- MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding
- Refer-Agent: A Collaborative Multi-Agent System with Reasoning and Reflection for Referring Video Object Segmentation
- AgentRVOS: Reasoning over Object Tracks for Zero-Shot Referring Video Object Segmentation
- Online Reasoning Video Object Segmentation
- VideoGLaMM: A Large Multimodal Model for Pixel-Level Visual Grounding in Videos
- The 2017 DAVIS Challenge on Video Object Segmentation
- SAM 2: Segment Anything in Images and Videos
- MovieChat: From Dense Token to Sparse Memory for Long Video Understanding
- MuKV: Multi-Grained KV Cache Compression for Long Streaming Video Question-Answering
- Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos
- HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding
- Training-Free Spatio-temporal Decoupled Reasoning Video Segmentation with Adaptive Object Memory
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs