Less is More: Label-Guided Efficient Summarization of Procedural and Instructional Videos

arXiv:2601.12243 · cs.CV, cs.AI · Submitted 2026-01-18 · Read on arXiv

cs.CV, cs.AI

Submitted: 2026-01-18

Updated: 2026-10-11

Code: https://github.com/Shreyarajpal12/PRISM-code

Terminology

• Alignment — 1× in this paper · explained in 1 episode
• Large Language Model (LLM) — 1× in this paper · explained in 3 episodes
• Semantic Alignment — 1× in this paper · explained in 3 episodes
• Vision-language models — 1× in this paper · explained in 2 episodes

Sources

• AutoLaparo: A New Dataset of Integrated Multi-tasks for Image-guided Surgical Automation in Laparoscopic Hysterectomy
• Unleashing Hour-Scale Video Training for Long Video-Language Understanding
• Video Summarization Using Fully Convolutional Sequence Networks
• Scaling Up Video Summarization Pretraining with Large Language Models
• Learning Transferable Visual Models From Natural Language Supervision
• BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation
• CLIP-It! Language-Guided Video Summarization
• Weakly-Supervised Video Object Grounding from Text by Loss Weighting and Object Interaction
• Dense-Captioning Events in Videos
• Video Summarization with Long Short-term Memory
• Summarizing Videos with Attention
• CSTA: CNN-based Spatiotemporal Attention for Video Summarization
• Query-Conditioned Three-Player Adversarial Network for Video Summarization
• Video Summarization Techniques: A Comprehensive Review
• FrameRank: A Text Processing Approach to Video Summarization
• BERTScore: Evaluating Text Generation with BERT
• Deep Residual Learning for Image Recognition
• Gemma 3 Technical Report
• The Llama 3 Herd of Models
• MiniCPM-V: A GPT-4V Level MLLM on Your Phone

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models