CCTVBench: Contrastive Consistency Traffic VideoQA Benchmark for Multimodal LLMs

• URL: http://arxiv.org/abs/2604.20460v1
• Date: Wed, 22 Apr 2026 11:39:02 GMT
• Title: CCTVBench: Contrastive Consistency Traffic VideoQA Benchmark for Multimodal LLMs
• Abstract summary: We present CCTVBench, a Contrastive Consistency Traffic VideoQA Benchmark built on paired real accident videos and world-model-generated counterfactual counterparts.<n>CCTVBench enforces a single structured decision pattern over each video question quadruple and provides actionable diagnostics.<n>C-TCD, a contrastive decoding approach leveraging a semantically exclusive counterpart video as the contrast input at inference time, improves both instance-level QA and contrastive consistency.
• Score: 43.70351207569419
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Safety-critical traffic reasoning requires contrastive consistency: models must detect true hazards when an accident occurs, and reliably reject plausible-but-false hypotheses under near-identical counterfactual scenes. We present CCTVBench, a Contrastive Consistency Traffic VideoQA Benchmark built on paired real accident videos and world-model-generated counterfactual counterparts, together with minimally different, mutually exclusive hypothesis questions. CCTVBench enforces a single structured decision pattern over each video question quadruple and provides actionable diagnostics that decompose failures into positive omission, positive swap, negative hallucination, and mutual-exclusivity violation, while separating video versus question consistency. Experiments across open-source and proprietary video LLMs reveal a large and persistent gap between standard per-instance QA metrics and quadruple-level contrastive consistency, with unreliable none-of-the-above rejection as a key bottleneck. Finally, we introduce C-TCD, a contrastive decoding approach leveraging a semantically exclusive counterpart video as the contrast input at inference time, improving both instance-level QA and contrastive consistency.

Related papers

• VADER: Adaptive Debiasing for Hallucination Mitigation in Video Large Language Models [30.792102059830274]
  Video-Adaptive Debiasing via Evidence Reweighting (VADER) is a training-free framework with two complementary modules.<n>Visual Focus Reallocation (VFR) automatically instantiates an intervention policy for each video-question input.<n> Selective Evidence Erasure (SEE) independently masks high-importance visual tokens in every frame.
  arXiv  Detail & Related papers  (2026-08-09T10:09:11Z)
• Counterfactual Reasoning for Fine-Grained Evidence Disentanglement in VideoQA [16.471093160007587]
  VideoQA systems often rely on spurious statistical correlations rather than answer-relevant causal evidence.<n>Existing methods either rely on cross-modality correlations, costly curated training resources, or insufficient causal assumptions and constraints.<n>We propose a Counterfactual Reasoning framework for fine-grained Evidence Disentanglement (CREDiT)
  arXiv  Detail & Related papers  (2026-06-08T08:20:42Z)
• Causal Bootstrapped Alignment for Unsupervised Video-Based Visible-Infrared Person Re-Identification [52.784239635604735]
  VVI-ReID is a critical technique for all-day surveillance, where temporal information provides additional cues beyond static images.<n>Existing approaches rely heavily on fully supervised learning with expensive cross-modality annotations, limiting scalability.<n>We propose a Causal Bootstrapped Alignment framework that explicitly exploits inherent video priors.
  arXiv  Detail & Related papers  (2026-04-17T02:15:59Z)
• Interpreting Video Representations with Spatio-Temporal Sparse Autoencoders [3.3192479135000426]
  We present the first systematic study of Sparseencoencoders (SAEs) on video representations.<n>Standard SAEs decompose into interpretable, monosemantic features but destroy temporal coherence.<n>TopK selection produces unstable feature assignments across frames, reducing autocorrelation by 36%.
  arXiv  Detail & Related papers  (2026-04-05T01:08:19Z)
• INFACT: A Diagnostic Benchmark for Induced Faithfulness and Factuality Hallucinations in Video-LLMs [69.11382230669491]
  hallucinations are outputs that contradict either video evidence (faithfulness) or verifiable world knowledge (factuality)<n>textscINFACT evaluates models in four modes: Base (clean), Visual Degradation, Evidence, and Temporal Intervention for order-sensitive items.<n>Experiments on 14 representative Video-LLMs reveal that higher Base-mode accuracy does not reliably translate to higher reliability in the induced modes.
  arXiv  Detail & Related papers  (2026-03-12T03:03:16Z)
• Video-R2: Reinforcing Consistent and Grounded Reasoning in Multimodal Language Models [56.851611990473174]
  Reasoning over dynamic visual content remains a central challenge for large language models.<n>We propose a reinforcement learning approach that enhances both temporal precision and reasoning consistency.<n>The resulting model, Video R2, achieves consistently higher TAC, VAS, and accuracy across multiple benchmarks.
  arXiv  Detail & Related papers  (2025-11-28T18:59:58Z)
• CLASH: A Benchmark for Cross-Modal Contradiction Detection [15.134491772506196]
  CLASH is a novel benchmark for multimodal contradiction detection.<n>It features COCO images paired with contradictory captions containing controlled object-level or attribute-level contradictions.
  arXiv  Detail & Related papers  (2025-11-24T15:09:07Z)
• Self-Calibrated Consistency can Fight Back for Adversarial Robustness in Vision-Language Models [31.920092341939593]
  Self-Calibrated Consistency is an effective test-time defense against adversarial attacks.<n> SCC consistently improves the zero-shot robustness of CLIP while maintaining accuracy.<n>These findings highlight the great potential of establishing an adversarially robust paradigm from CLIP.
  arXiv  Detail & Related papers  (2025-10-26T18:37:12Z)
• Token Constraint Decoding Improves Robustness on Question Answering for Large Language Models [4.078176555898098]
  We introduce and evaluate Token Constraint Decoding (TCD)<n>This simple yet effective inference-time algorithm enforces alignment between token-level predictions to enhance robustness in noisy settings.<n>Our findings establish TCD as a practical, model-agnostic approach for improving reasoning stability under real-world imperfections.
  arXiv  Detail & Related papers  (2025-06-11T05:33:56Z)
• VCR-Bench: A Comprehensive Evaluation Framework for Video Chain-of-Thought Reasoning [22.357792064450955]
  Chain-of-Thought (CoT) reasoning has significantly enhanced the capabilities of large language models (LLMs) and large vision-language models (LVLMs)<n>We introduce VCR-Bench, a novel benchmark designed to comprehensively evaluate LVLMs' Video Chain-of-Thought Reasoning capabilities.<n> VCR-Bench comprises 859 videos spanning a variety of video content and durations, along with 1,034 high-quality question-answer pairs.
  arXiv  Detail & Related papers  (2025-04-10T17:59:03Z)
• Temporal Inconsistency Guidance for Super-resolution Video Quality Assessment [63.811519474030234]
  We propose a perception-oriented approach to quantify frame-wise temporal inconsistency.<n>Inspired by the human visual system, we develop an Inconsistency Guided Temporal Module.<n>Our method significantly outperforms state-of-the-art VQA approaches.
  arXiv  Detail & Related papers  (2024-12-25T15:43:41Z)
• VideoEspresso: A Large-Scale Chain-of-Thought Dataset for Fine-Grained Video Reasoning via Core Frame Selection [61.54044967253421]
  We introduce VideoEspresso, a novel dataset that features VideoQA pairs preserving essential spatial details and temporal coherence. Our construction pipeline employs a semantic-aware method to reduce redundancy, followed by generating QA pairs using GPT-4o. We propose a Hybrid LVLMs Collaboration framework, featuring a Frame Selector and a two-stage instruction fine-tuned reasoning LVLM.
  arXiv  Detail & Related papers  (2024-11-22T08:33:36Z)
• Capturing Co-existing Distortions in User-Generated Content for No-reference Video Quality Assessment [9.883856205077022]
  Video Quality Assessment (VQA) aims to predict the perceptual quality of a video. VQA faces two under-estimated challenges unresolved in User Generated Content (UGC) videos. We propose textitVisual Quality Transformer (VQT) to extract quality-related sparse features more efficiently.
  arXiv  Detail & Related papers  (2023-07-31T16:29:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.