paper-with-me

홈 › Papers

CounterFlow: A Two-Phase Inference-Time Sampling for Counterfactual Video Foley Generation

2026-05-18 · Gyubin Lee, Junwon Lee, Juhan Nam arxiv

We investigate Counterfactual Video Foley Generation, which aims to adopt a sound-source identity that contradicts the visual evidence while remaining temporally synchronized to a silent video. Existing Video&Text-to-Audio (VT2A) models struggle with this, often remaining anchored to the visually implied sound source when video and text contents disagree. We present ConterFlow, an inference-time dual-phase sampling scheme for pretrained flow-matching VT2A models. Phase 1 builds a video-derived temporal structure while suppressing the visually implied source; Phase 2 drops video conditioning to focus entirely on shaping audio timbre toward the target prompt. ConterFlow substantially improves counterfactual Video Foley generation compared to naive negative prompting and state-of-the-art baselines. To evaluate replacement quality, we propose a metric leveraging a text-audio co-embedding space to measure both target-prompt evidence and residual visually implied source leakage. Video demonstrations and code are available at https://gyubin-lee.github.io/counterflow-demo/

📄 PDF Abstract BibTeX arXiv:2605.18916

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

CounterFlowNet: From Minimal Changes to Meaningful Counterfactual Explanations

2026-02-19 · Oleksii Furman, Patryk Marszałek, Jan Masłowski, Piotr Gaiński 외 arxiv

Counterfactual explanations (CFs) provide human-interpretable insights into model's predictions by identifying minimal changes to input features that would alter the model's output. However, existing methods struggle to …

Empowering Language Understanding with Counterfactual Reasoning

2021-06-06 · Findings (ACL) 2021 8 · Fuli Feng, Jizhi Zhang, Xiangnan He, Hanwang Zhang 외

Present language understanding methods have demonstrated extraordinary ability of recognizing patterns in texts via machine learning. However, existing methods indiscriminately use the recognized patterns in the testing …

counterfactualCounterfactual ReasoningNatural Language InferenceSentiment Analysis

Counterfactual Inference under Thompson Sampling

2025-04-03 · Olivier Jeunen

Recommender systems exemplify sequential decision-making under uncertainty, strategically deciding what content to serve to users, to optimise a range of potential objectives. To balance the explore-exploit trade-off suc…

Causal InferencecounterfactualCounterfactual InferenceDecision Making+4

Imputation of Counterfactual Outcomes when the Errors are Predictable

2024-03-12 · Silvia Goncalves, Serena Ng

A crucial input into causal inference is the imputed counterfactual outcome. Imputation error can arise because of sampling uncertainty from estimating the prediction model using the untreated observations, or from out-o…

Causal InferencecounterfactualImputationTime Series

Towards Multimodal Sentiment Analysis Debiasing via Bias Purification

2024-03-08 · Dingkang Yang, Mingcheng Li, Dongling Xiao, Yang Liu 외

Multimodal Sentiment Analysis (MSA) aims to understand human intentions by integrating emotion-related clues from diverse modalities, such as visual, language, and audio. Unfortunately, the current MSA task invariably su…

counterfactualCounterfactual InferenceMultimodal Sentiment AnalysisSentiment Analysis