Research map / Vision-language and multimodal / Visual question answering
LLCP: Learning Latent Causal Processes for Reasoning-based Video Question Answer
Guangyi Chen, Yuke Li, Xiao Liu, Zijian Li, Eman Al Suradi, Donglai Wei, Kun Zhang
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes LLCP, a latent causal process framework for reasoning-based video question answering, modeling causal structure over video content to answer questions such as accident attribution.
Problem
Video question answering mainly relies on cross-modality matching, which needs heavy annotation and lacks causal reasoning capacity (e.g., attributing accidents).
Approach
A causal framework that learns latent causal processes via a multivariate (latent) process model at the heart of the method, aiming to support causal video reasoning beyond cross-modal matching; the full mechanism is not described in the available abstract.
Closest papers by meaning
- CausalStep: A Benchmark for Explicit Stepwise Causal Reasoning in Videos (AAAI 2026 · similarity 0.91)
- Two Causally Related Needles in a Video Haystack (NeurIPS 2025 · similarity 0.88)
- MECD: Unlocking Multi-Event Causal Discovery in Video Reasoning (NeurIPS 2024 · similarity 0.87)
- STAIR: Spatial-Temporal Reasoning with Auditable Intermediate Results for Video Question Answering (AAAI 2024 · similarity 0.87)
- MoReVQA: Exploring Modular Reasoning Models for Video Question Answering (CVPR 2024 · similarity 0.87)
- Cross-modal Causal Relation Alignment for Video Question Grounding (CVPR 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
