Shot-Aware Frame Sampling for Video Understanding

• URL: http://arxiv.org/abs/2603.17374v1
• Date: Wed, 18 Mar 2026 05:36:57 GMT
• Title: Shot-Aware Frame Sampling for Video Understanding
• Abstract summary: InfoShot is a task-agnostic, shot-aware frame sampler for long-video understanding.<n>Design is guided by an information-theoretic objective that encourages the sampled set to retain high information about both shot structure and sparse within-shot deviations.<n>Experiments show that InfoShot improves anomaly hit rate and downstream Video-QA accuracy under frame number constraints.
• Score: 10.771430339569795
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Video frame sampling is essential for efficient long-video understanding with Vision-Language Models (VLMs), since dense inputs are costly and often exceed context limits. Yet when only a small number of frames can be retained, existing samplers often fail to balance broad video coverage with brief but critical events, which can lead to unreliable downstream predictions. To address this issue, we present InfoShot, a task-agnostic, shot-aware frame sampler for long-video understanding. InfoShot first partitions a video into semantically consistent shots, and then selects two complementary keyframes from each shot: one to represent the main content and one to capture unusual within-shot changes. This design is guided by an information-theoretic objective that encourages the sampled set to retain high information about both shot structure and sparse within-shot deviations. In this way, it improves the chance of preserving both overall video context and short decision-critical moments without requiring any retraining. To better evaluate such short-lived events, we further introduce SynFlash, a synthetic benchmark with controllable sub-second anomaly patterns and frame-level ground truth, and we also evaluate InfoShot on existing anomaly datasets and general video understanding tasks. Experiments show that InfoShot improves anomaly hit rate and downstream Video-QA accuracy under frame number constraints, while matching or outperforming strong baselines on standard video understanding benchmarks.

Related papers

• Video-MME-v2: Towards the Next Stage in Benchmarks for Comprehensive Video Understanding [98.3098451637867]
  Video-MME-v2 is a comprehensive benchmark designed to rigorously evaluate the robustness and faithfulness of video understanding.<n>To guarantee data quality, Video-MME-v2 is constructed through a rigorously controlled human annotation pipeline.
  arXiv  Detail & Related papers  (2026-04-06T17:59:56Z)
• UniE2F: A Unified Diffusion Framework for Event-to-Frame Reconstruction with Video Foundation Models [67.24086328473437]
  Event cameras excel at recording relative intensity changes rather than absolute intensity.<n>The resulting data streams suffer from a significant loss of spatial information and static texture details.<n>We address this limitation by leveraging a pre-trained video diffusion model to reconstruct high-fidelity video frames from sparse event data.
  arXiv  Detail & Related papers  (2026-02-22T14:06:49Z)
• DESSERT: Diffusion-based Event-driven Single-frame Synthesis via Residual Training [25.438410354399053]
  Video frame prediction extrapolates future frames from previous frames, but suffers from prediction errors in dynamic scenes.<n>We propose DESSERT, a diffusion-based event-driven single-frame synthesis framework via residual training.
  arXiv  Detail & Related papers  (2025-12-19T08:12:20Z)
• Factorized Video Generation: Decoupling Scene Construction and Temporal Synthesis in Text-to-Video Diffusion Models [76.7535001311919]
  State-of-the-art Text-to-Video (T2V) diffusion models can generate visually impressive results, yet they often fail to compose complex scenes or follow logical temporal instructions.<n>We introduce Factorized Video Generation (FVG), a pipeline that decouples these tasks by decomposing the Text-to-Video generation into three specialized stages.<n>Our approach sets a new state-of-the-art on the T2V CompBench benchmark and significantly improves all tested models on VBench2.
  arXiv  Detail & Related papers  (2025-12-18T10:10:45Z)
• DUAL-VAD: Dual Benchmarks and Anomaly-Focused Sampling for Video Anomaly Detection [8.294763803639391]
  Video Anomaly Detection (VAD) is critical for surveillance and public safety.<n>Existing benchmarks are limited to either frame-level or video-level tasks.<n>This work introduces a softmax-based frame allocation strategy that prioritizes anomaly-dense segments while maintaining full-video coverage.
  arXiv  Detail & Related papers  (2025-09-15T05:48:22Z)
• Episodic Memory Representation for Long-form Video Understanding [52.33907540905242]
  Large Video Language Models excel at general video understanding but struggle with long-form context window limits.<n>We introduce Video-EM, a training free framework inspired by the principles of human memory.<n>Video-EM achieves performance gains of 4-9 percent over respective baselines while utilizing fewer frames.
  arXiv  Detail & Related papers  (2025-08-13T04:33:07Z)
• CMTA: Cross-Modal Temporal Alignment for Event-guided Video Deblurring [44.30048301161034]
  Video deblurring aims to enhance the quality of restored results in motion-red videos by gathering information from adjacent video frames. We propose two modules: 1) Intra-frame feature enhancement operates within the exposure time of a single blurred frame, and 2) Inter-frame temporal feature alignment gathers valuable long-range temporal information to target frames. We demonstrate that our proposed methods outperform state-of-the-art frame-based and event-based motion deblurring methods through extensive experiments conducted on both synthetic and real-world deblurring datasets.
  arXiv  Detail & Related papers  (2024-08-27T10:09:17Z)
• Three-Stage Cascade Framework for Blurry Video Frame Interpolation [23.38547327916875]
  Blurry video frame (BVFI) aims to generate high-frame-rate clear videos from low-frame-rate blurry videos. BVFI methods usually fail to fully leverage all valuable information, which ultimately hinders their performance. We propose a simple end-to-end three-stage framework to fully explore useful information from blurry videos.
  arXiv  Detail & Related papers  (2023-10-09T03:37:30Z)
• SSVOD: Semi-Supervised Video Object Detection with Sparse Annotations [12.139451002212063]
  SSVOD exploits motion dynamics of videos to utilize large-scale unlabeled frames with sparse annotations. Our method achieves significant performance improvements over existing methods on ImageNet-VID, Epic-KITCHENS, and YouTube-VIS.
  arXiv  Detail & Related papers  (2023-09-04T06:41:33Z)
• MHSCNet: A Multimodal Hierarchical Shot-aware Convolutional Network for Video Summarization [61.69587867308656]
  We propose a multimodal hierarchical shot-aware convolutional network, denoted as MHSCNet, to enhance the frame-wise representation. Based on the learned shot-aware representations, MHSCNet can predict the frame-level importance score in the local and global view of the video.
  arXiv  Detail & Related papers  (2022-04-18T14:53:33Z)
• Video Demoireing with Relation-Based Temporal Consistency [68.20281109859998]
  Moire patterns, appearing as color distortions, severely degrade image and video qualities when filming a screen with digital cameras. We study how to remove such undesirable moire patterns in videos, namely video demoireing.
  arXiv  Detail & Related papers  (2022-04-06T17:45:38Z)

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.