Adaptive Video Frame Sampling

Follow this topic Ask about this topic

Latest papers

16 papers2 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

EARS: Evidence-Aware Retrieval via Sound and Motion for Budgeted Video Reasoning
Oct 26, 2026Shih-Yao LinVideo Frame Selection Adaptive Video Frame Sampling
Independent Researcher
Efficient Zero-Shot Video Anomaly Detection via Signal-Aware Adaptive Fusion (SAAF)
Oct 23, 2026Khaled Waleed Dawoud, Muhammad Haris KhanAdaptive Video Frame Sampling Video Anomaly Detection
Mohamed bin Zayed University of Artificial Intelligence, United Arab Emirates
FastBench: Can Streaming VLMs Perceive High-Dynamic Real-World Streams?
Oct 8, 2026Yuxuan Hu, Weikang Shi, Yang Bo +10Adaptive Video Frame Sampling Streaming Video Understanding
CUHK MMLab
MetaSampling: Making Frame Samplers Efficient for Long-Video Question Answering
Sep 27, 2026Ashim Dahal, Bikramjit BanerjeeMultimodal Large Language Models Adaptive Sampling
University of Southern Mississippi Hattiesburg, MS, USA
One Ranking, Any Budget: Matryoshka Evidence-to-Context Frame Selection for Long-Video Understanding
Aug 6, 2026Wang Chen, Yu Chen, Xiang Wang +3Long-Video Understanding Video Frame Selection
Media Analytics and Computing Lab, Xiamen University, Xiamen, China · Amap, Alibaba Group, China · Department of Computer Science, University of Rochester, Rochester, NY, USA
Efficient Frame Selection for Long Videos at Test Time with Attention-Based MLLM Selectors
Jul 17, 2026Yilin Wang, Xiangxi Zheng, Dongxing Mao +6Efficient VLM Inference Multimodal Large Language Models
ZJU · NJU · CSU +2
Video2Code: Generating Interactive Webpages from UI Videos via Action-Aware Revisit
Jun 16, 2026Mingde Xu, Zhen Yang, Yan Wang +7Web Application Generation Adaptive Sampling
University of Waterloo · Tsinghua University · Zhipu AI +1
PEEK: Picking Essential frames via Efficient Knowledge distillation
May 29, 2026Killian Steunou, Anas Filali Razzouki, Khalil Guetari +2Efficient VLM Inference Video Captioning
Télécom SudParis — SAMOVAR Institut Polytechnique de Paris Palaiseau, France · Moments Lab 69 Avenue Pierre Grenier Boulogne-Billancourt, France
DynFrame: Adaptive Reasoning-Driven Multimodal Framework with Dynamic Frame Augmentation for Complex Video Understanding
May 26, 2026Peng Zhang, Guanghao Zhang, Wanggui He +10Multimodal Large Language Models Video Reasoning
Zhejiang University · Alibaba Group
Swift Sampling: Selecting Temporal Surprises via Taylor Series
May 21, 2026Dahye Kim, Bhuvan Sachdeva, Karan Uppal +3Video Frame Selection Long-Video QA
Boston University · Microsoft Research India
LDDR: Linear-DPP Dynamic-Resolution Frame Sampling for Video MLLMs
May 12, 2026Jingfeng Chen, Jiawen Qian, Wendi Deng +5Video Frame Selection Multimodal Large Language Models
Carnegie Mellon University · Individual Researcher · National University Singapore +2
CREST: Curvature-Regulated Event-Centric Sampling for Efficient Long-Video Understanding
May 9, 2026Mehrajul Abadin Miraj, Abdul Mohaimen Al Radi, Shariful Islam Rayhan +4Data Selection Long-Video Understanding
Dept. of CSE, University of Dhaka · Dept. of CSE, University of Central Florida
Adaptive Greedy Frame Selection for Long Video Understanding
Mar 20, 2026Yuning Huang, Xiaoyu Ji, Joseph Huang +2Query-Aware Video Frame Selection Adaptive Video Frame Sampling
Purdue University, West Lafayette, IN 47906
Shot-Aware Frame Sampling for Video Understanding
Mar 18, 2026Mengyu Zhao, Di Fu, Yongyu Xie +4Video Frame Selection Adaptive Video Frame Sampling
ByteDance · Rutgers University · Georgia Tech
PyVision-RL: Forging Open Agentic Vision Models via RL
Feb 24, 2026Shitian Zhao, Shaoheng Lin, Ming Li +4Adaptive Video Frame Sampling Multimodal Agents
Shanghai AI Lab · UMD · CUHK +3
Learning Compact Video Representations for Efficient Long-form Video Understanding in Large Multimodal Models
Feb 19, 2026Yuxiao Chen, Jue Wang, Zhikang Zhang +8Adaptive Video Frame Sampling Long-Video Understanding
Amazon AGI

Oct 26, 2026J/K move · Enter open · S save

EARS: Evidence-Aware Retrieval via Sound and Motion for Budgeted Video Reasoning

Shih-Yao Lin

Independent Researcher

Video Frame Selection Adaptive Video Frame Sampling Audio-Visual Understanding

Open paper AskPDF arXiv

Uniform frame sampling can miss brief evidence in sparse-event videos when the VLM sees only K frames. We propose EARS (Evidence-Aware Retrieval via Sound and motion), a training-free, query-free front-end that ranks frames using optical-flow motion and audio energy, then applies temporal non-maximum suppression for diversity. The evidence score alone has frame-level AP 0.39; used only to select frames for the VLM, EARS with temporal diversity reaches localization AP 0.94, compared with 0.88 under Uniform sampling. In the updated matched study, at K = 1 EARS reaches XD-subset F1 0.660 versus 0.614 for centered Uniform (the paired interval includes zero); earlier backbone studies use separate protocols. On mostly-silent UCF-Crime, however, EARS slightly trails Uniform. A single configuration is used across both benchmarks; the new controls do not repeat the original held-out search. EARS therefore targets low-budget videos whose salient evidence aligns with motion or audio; on dense narratives or stealthy events, uniform or semantic selection remains preferable, and cheap modality statistics cannot reliably route between them. Code: https://github.com/mikeslin-ir/EARS