CEVA: Complementary Evidence Verification via Frame-Level Reorganization for Short-Video Fake News Detection

Wenshen Yang, Junfeng Hao, Jing Li, Decheng Liu, Yangkunfei, Shuyu Jiang, Haizhou WangarXiv 2026 · arXiv

TL;DR

CEVA (Complementary Evidence Verification Approach) is a novel framework for short-video fake news detection that reorganizes video frames into "claim-aligned" and "complementary-context" groups before they are fused with text. By explicitly preserving subtle contextual cues that might contradict a misleading claim—rather than just focusing on frames that match the text—CEVA achieves state-of-the-art performance across multiple datasets and languages.

What Problem Does This Paper Address?

Short videos are a potent medium for spreading misinformation because they can easily pair genuine, persuasive footage with completely unrelated or misleading claims. For example, a video of a staged emergency drill might be reposted as a "real-time crime in progress."

Existing automated detectors typically treat video frames as a uniform stream or use text-frame similarity to pick the "most relevant" frames. The authors argue this is a fundamental flaw: in a fake news video, the frames that most closely match the misleading text actually reinforce the lie. The "smoking gun" evidence that debunks the claim often resides in brief, low-similarity background shots—like a camera gimbal or a "behind-the-scenes" crew member—that traditional similarity-based filters would discard as noise.

Figure 1: Differences in frame-level evidence processing be- tween prior multimodal methods and CEVA.

Methods

The core of the CEVA framework is the Dual-Branch Complementary Reorganization (DBCR) module, which organizes evidence before multimodal fusion.

  1. Shot-Aware Sampling: Instead of uniform sampling, CEVA segments the video into shots and allocates a sampling budget to ensure dynamic segments and broad temporal coverage are preserved.
  2. Multi-View Semantic Profiling: Using a Vision-Language Model (VLM) embedding (Qwen3-VL), each frame is scored against five textual "views": title, claim, summary, details, and OCR text.
  3. Evidence Partitioning: Frames are ranked and split into two disjoint groups:
  4. $G_{align}$ (Explicit Alignment): Frames that strongly match the claim and title.
  5. $G_{comp}$ (Complementary Context): Frames that show high variance across different text views, likely containing the "diagnostic context" needed for verification.
  6. Two-Stage Textualization: The model generates global narrative descriptions ($T_1$) and specific, entity-aware descriptions for the reorganized frame groups ($T_2$).
  7. Fusion & Regularization: Visual features (from DINOv2) and text features (from Qwen2.5) are integrated via gated fusion and cross-attention. During training, a bidirectional contrastive loss (InfoNCE) is used to regularize the alignment between the video and text representations.
Figure 2: Overall architecture of CEVA. DBCR reorganizes candidate frames before fusion, two-stage textualization constructs the global T1 and entity-aware local T2 streams, and bidirectional InfoNCE regularizes the fused representations during training.

Datasets

The authors evaluated CEVA on two major short-video benchmarks:

  • FakeSV: A Chinese dataset containing ~3,600 videos from platforms like Douyin and Kuaishou.
  • FakeTT: An English dataset containing ~2,000 videos from TikTok. The use of an event-level split (ensuring no overlap of events between training and testing) prevents the model from simply memorizing specific news stories.

Key Insights and Ideas

  • Similarity $\neq$ Veracity: High similarity between text and video is a poor proxy for truth in fake news detection. The "complementary" branch ($G_{comp}$) is essential because it captures the subtle contradictions that similarity-only methods ignore.
  • Pre-fusion Organization Matters: Most models perform fusion on a "homogenous" stream of frames. CEVA proves that explicitly categorizing frames by their "evidential role" (supporting vs. contextualizing) before fusion leads to much cleaner feature representations.
  • Transferability: The DBCR module is architecture-agnostic. The authors demonstrated that "plugging" DBCR into other existing detectors (like SV-FEND) significantly boosted their accuracy without changing their underlying fusion logic.

Key Results

CEVA set new performance benchmarks on both datasets:

  • Accuracy: 87.98% on FakeSV and 86.67% on FakeTT, outperforming the previous state-of-the-art (ExMRD) by 1.08 and 2.39 percentage points, respectively.
  • Ablation Success: Removing the $G_{comp}$ branch and its associated text descriptions caused accuracy to drop by over 3 percentage points, confirming the value of the "complementary" evidence.
  • Zero-Shot Comparison: CEVA significantly outperformed large multimodal models (like GPT-4o-mini and Qwen2.5-VL) used in a zero-shot capacity, highlighting the need for task-specific training in misinformation detection.

Limitations and Future Work

The authors identify a specific failure mode: single-shot videos. If a video consists of a single continuous clip with no visual contradictions (e.g., a real explosion clip where only the location name in the caption is faked), CEVA’s reorganization strategy has no "contextual variation" to exploit. In these cases, the model may incorrectly predict "Real" because the footage perfectly matches the (misleading) title.

Figure 6: Case studies showing CEVA correctly identifying a drill (left) but failing on a single-shot explosion with an entity replacement (right).

Future work may involve integrating external knowledge retrieval to verify entities (like specific locations or dates) that cannot be debunked through visual context alone.

Summary updated

Abstract

Short-video platforms are now a common way for the public to follow unfolding events. Their rapid, visually persuasive format also makes fake news easier to spread. Unlike text-image posts, short-video news interleaves multiple modalities and changing scenes, making it difficult to identify which frames verify a claim. Existing detectors either pool sampled frames homogeneously or select them by text-frame similarity. Both overlook that aligned frames may repeat a misleading claim, whereas less dominant context may challenge it. We present CEVA (Complementary Evidence Verification Approach), to our knowledge the first short-video fake news detection framework to explicitly organize frames by their evidential roles before multimodal fusion. Its Dual-Branch Complementary Reorganization (DBCR) module separates explicit-alignment frames from candidate complementary-context frames, and cross-modal fusion with bidirectional contrastive regularization operates on the reorganized evidence. On FakeSV and FakeTT, CEVA achieves the best overall results among the compared methods. Under fixed frame budgets and backbones, DBCR outperforms uniform, random, and similarity-based selection and improves two structurally different detectors. Together, these results establish pre-fusion evidence organization as an effective and transferable component of short-video fake news detection.
BibTeX
@misc{yang2026ceva,
  author = {Wenshen Yang and Junfeng Hao and Jing Li and Decheng Liu and Yangkunfei and Shuyu Jiang and Haizhou Wang},
  title = {{CEVA: Complementary Evidence Verification via Frame-Level Reorganization for Short-Video Fake News Detection}},
  year = {2026},
  eprint = {2611.22141},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2611.22141},
}
Figure