paper-with-me

홈 › Papers

Swift Sampling: Selecting Temporal Surprises via Taylor Series

2026-05-21 · Dahye Kim, Bhuvan Sachdeva, Karan Uppal, Naman Gupta, Vineeth N. Balasubramanian, Deepti Ghadiyaram arxiv

While most frames in long-form video are redundant, the critical information resides in temporal surprises: moments where the actual visual features deviate from their predicted evolution. Inspired by the human brain's predictive coding, we introduce Swift Sampling, an elegant, training-free frame selection algorithm that automatically identifies high-information moments in a video. Specifically, we model a video as a differentiable trajectory in the visual latent space and compute the velocity and acceleration of its features. Then, we apply Taylor expansion to project the expected path of subsequent frames. Frames that diverge sharply from this predicted manifold are identified as temporally surprising frames and selected for sampling. Unlike prior training-free methods that rely on auxiliary networks or video-specific hyperparameter tuning, Swift Sampling is incredibly lightweight, adding only 0.02x additional computational cost over baseline making it 30x cheaper overhead than leading baselines. Across three long-video question answering benchmarks and 10 different downstream tasks, Swift Sampling outperforms uniform sampling and prior query-agnostic baselines. It is especially powerful for long videos with limited frame budgets improving accuracy by up to +12.5 points.

📄 PDF Abstract BibTeX arXiv:2605.22678

Code (0)

등록된 구현이 없습니다.

Tasks

Video Question Answering

Similar Papers 제목 키워드 기반

TaylorSwiftNet: Taylor Driven Temporal Modeling for Swift Future Frame Prediction

2021-10-27 · Saber Pourheydari, Emad Bahrami, Mohsen Fayyaz, Gianpiero Francesca 외

While recurrent neural networks (RNNs) demonstrate outstanding capabilities for future video frame prediction, they model dynamics in a discrete time space, i.e., they predict the frames sequentially with a fixed tempora…

Avoiding an AI-imposed Taylor's Version of all music history

2024-02-05 · Nick Collins, Mick Grierson

As future musical AIs adhere closely to human music, they may form their own attachments to particular human artists in their databases, and these biases may in the worst case lead to potential existential threats to all…

AllDiversity

Taylor Unswift: Secured Weight Release for Large Language Models via Taylor Expansion

2024-10-06 · Guanchu Wang, Yu-Neng Chuang, Ruixiang Tang, Shaochen Zhong 외

Ensuring the security of released large language models (LLMs) poses a significant dilemma, as existing mechanisms either compromise ownership rights or raise data privacy concerns. To address this dilemma, we introduce …

SWIFT: A General Sensitive Weight Identification Framework for Fast Sensor-Transfer Pansharpening

2025-07-27 · Zeyu Xia, Chenxi Sun, Tianyu Xin, Yubo Zeng 외 arxiv

Pansharpening aims to fuse high-resolution panchromatic (PAN) images with low-resolution multispectral (LRMS) images to generate high-resolution multispectral (HRMS) images. Although deep learning-based methods have achi…

Minimizing Errors or Surprises?

2024-04-13 · Jiaoying Pei

Traditional finance and macroeconomic models usually assume people can form rational expectations or reach them via a learning path by minimizing prediction errors. The recent Reference Model Based Learning (RMBL) model …