Reproduce “CEVA: Complementary Evidence Verification via Frame-Level Reorganization for Short-Video Fake News Detection” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Wenshen Yang, Junfeng Hao, Jing Li, Decheng Liu, Yangkunfei, Shuyu Jiang, Haizhou Wang
CEVA reorganizes sampled video frames before fusion, separating claim-aligned frames from a disjoint group of potentially complementary context frames. DBCR ranks the groups using similarities across multiple text views, but does not verify their evidential roles. On FakeSV, it reaches 87.98% accuracy and 87.96% macro-F1, modestly above uniform selection; this supports improved detection on tested data, not general fact verification.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.