The Target Is a Predicate: Predicate-State Grounding for Semantic-Level Video Reasoning Segmentation
cs.CV
Submitted: 2026-11-10
Updated: 2026-11-10
Terminology
Sources
- CoVLA: Comprehensive Vision-Language-Action Dataset for Autonomous Driving
- SAM 3: Segment Anything with Concepts
- AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark
- Video-of-Thought: Step-by-Step Video Reasoning from Perception to Cognition
- CoT-RVS: Zero-Shot Chain-of-Thought Reasoning Segmentation for Videos
- ReVSeg: Incentivizing the Reasoning Chain for Video Segmentation with Reinforcement Learning
- SAM 2: Segment Anything in Images and Videos
- AnyCap Project: A Unified Framework, Dataset, and Benchmark for Controllable Omni-modal Captioning
- SIN-Bench: Tracing Native Evidence Chains in Long-Context Multimodal Scientific Interleaved Literature
- Reasoning Segmentation for Images and Videos: A Survey
- Kimi K2.5: Visual Agentic Intelligence
- Qwen3-VL Technical Report
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